Showing 1–50 of 220 results for author: An, S

LineageRAG: Harnessing GraphRAG by Constructing Evidence Lineages with Source Grounding

Authors: Linyao Zheng, Xuhang Shi, Zhifang Mao, Sai Zhou, Shuaixian An, Xiuquan Hou, Jinze Li

Abstract: Graph-based Retrieval-Augmented Generation (GraphRAG) retrieves evidence for multi-hop questions over structured cor- pus graphs. Existing GraphRAG methods leave the connection between evidence discovery and source grounding implicit. We propose LineageRAG, which constructs one evidence lin- eage for each query-derived evidence demand and completes it with a verbatim source span when the selected… ▽ More Graph-based Retrieval-Augmented Generation (GraphRAG) retrieves evidence for multi-hop questions over structured cor- pus graphs. Existing GraphRAG methods leave the connection between evidence discovery and source grounding implicit. We propose LineageRAG, which constructs one evidence lin- eage for each query-derived evidence demand and completes it with a verbatim source span when the selected evidence supports that demand. LineageRAG first initializes the evi- dence demands. It then expands each lineage through demand- conditioned retrieval over the corpus graph while retaining the demand associated with every candidate. Lineage completion uses this provenance to select complementary passages and grounds supported demands in verbatim source text. Experi- ments on HotpotQA, 2WikiMultiHopQA, and MuSiQue show that LineageRAG improves R@5, EM, and F1 by 3.51, 5.96, and 5.22 points on average over leading GraphRAG baselines. △ Less

Submitted 16 August, 2026; originally announced August 2026.

The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance

Authors: Shailja Thakur, Sungeun An, Chad DeLuca, Hima Patel

Abstract: A benchmark score comes from a single phrasing of each problem. That single phrasing is treated as if it stood for the whole space of ways the same problem could be asked, but it does not. We show that rephrasing a problem while keeping its meaning and answer fixed routinely flips a model's answer in both directions, so some failures become successes and some successes become failures. We call thi… ▽ More A benchmark score comes from a single phrasing of each problem. That single phrasing is treated as if it stood for the whole space of ways the same problem could be asked, but it does not. We show that rephrasing a problem while keeping its meaning and answer fixed routinely flips a model's answer in both directions, so some failures become successes and some successes become failures. We call this drift. BenchDrift generates meaning-preserving variations of benchmark problems along four axes, namely linguistic, referential, pragmatic, and structural, and measures how often, and why, correctness flips under each. Across eight models and three benchmarks (GSM8K, MMLU, MATH-Hard), we observe that drift is large in both directions. Two findings stand out. First, phrasing sensitivity does not fade as models get better. Instead, it changes sign. Weak models gain more from rephrasing than they lose, while strong models lose far more than they gain. We find that the best models on a benchmark are therefore the ones whose scores depend most on the wording they happened to be given. Second, the models largely agree on which rephrasings cost the most correct answers even though they differ in how much they drift, so fragility belongs to the rephrasing and not to the model. Furthermore, rephrasing breaks answers a model was confident about, whether the problem is made shorter or longer. Code and Data: https://github.com/IBM/BenchDrift/tree/demo-ui △ Less

Submitted 12 August, 2026; originally announced August 2026.

Fast Trainable Multilinear Bases for Image Compression

Authors: Shiwen An, Zhongyi Ni, Huanhai Zhou, Jin-Guo Liu

Abstract: The Discrete Fourier Transform, the Discrete Cosine Transform, and their block-wise variants underpin most deployed image and video codecs. Their effectiveness rests on three properties: they run in near-linear time (linear up to a polylogarithmic factor), they are exactly invertible, and they carry few to no parameters. In this work, we generalize these bases to isometric multilinear bases, allow… ▽ More The Discrete Fourier Transform, the Discrete Cosine Transform, and their block-wise variants underpin most deployed image and video codecs. Their effectiveness rests on three properties: they run in near-linear time (linear up to a polylogarithmic factor), they are exactly invertible, and they carry few to no parameters. In this work, we generalize these bases to isometric multilinear bases, allowing a small number of extra parameters, polylogarithmic in the image size, while preserving all three properties. Given an image dataset, we develop a systematic framework that searches this family for the basis compressing the dataset most effectively: the basis is parameterized as an isometric tensor network, inspired by quantum many-body theory, and trained with Riemannian optimization on the manifold of unitary matrices. Across natural photographs and line drawings, the trained bases consistently improve on their fixed, non-parametric counterparts. On Quick Draw line-drawing compression, they store images in roughly $20\%$ fewer bytes than JPEG's $8 \times 8$ block cosine transform at the same reconstruction quality. △ Less

Submitted 17 August, 2026; v1 submitted 26 July, 2026; originally announced August 2026.

HumanCLAW: Can Vision-Language Models Act Through a Body?

Authors: Li Siyao, Jiawei Gu, Shuai Liu, Kairui Hu, Zekun Li, Linjie Li, Chengcheng Tang, Po-Chen Wu, Ivan Shugurov, Lingni Ma, Michael Zollhoefer, Sizhe An, Abhay Mittal, Amy Zhao, Ranjay Krishna, Manling Li, Ziwei Liu, Chuan Guo

Abstract: Evaluating whether a vision-language model (VLM) can act through a physical body is challenging. The outcome of an action couples the VLM's decision with motor control. When a task fails, it is hard to tell whether the VLM made a bad choice or the motor controller simply failed to execute it, e.g., losing balance and falling. In this work, we introduce HumanCLAW, an evaluation framework that decou… ▽ More Evaluating whether a vision-language model (VLM) can act through a physical body is challenging. The outcome of an action couples the VLM's decision with motor control. When a task fails, it is hard to tell whether the VLM made a bad choice or the motor controller simply failed to execute it, e.g., losing balance and falling. In this work, we introduce HumanCLAW, an evaluation framework that decouples action decision-making from low-level execution. At every step, a harnessed, off-the-shelf VLM issues an atomic skill command, and the command is translated into a sub-second chunk of continuous full-body motion with real physical consequences, including gravity and collisions. The body can therefore act freely in the physical world, while execution-side disturbances, balance and motor errors, are factored out. What remains measurable is the model's action intelligence: its moment-to-moment choice of what the body should execute next. Based on this framework, we build HumanCLAW-Bench: 1,218 long-horizon, egocentric find-navigate-interact episodes across 41 indoor scenes. We test nine state-of-the-art VLMs and find that none solves the benchmark; the best model reaches only a 16.8% success rate. Recognizing the target is not the bottleneck. What current VLMs lack is embodied self-awareness: they lose track of their own body, failing to tell where it is, whether it has reached the goal, or whether it has hit an obstacle. △ Less

Submitted 3 August, 2026; v1 submitted 29 July, 2026; originally announced July 2026.

Comments: Project page: https://human-claw.github.io/

Ms. Forcing: Efficient Streaming Video Generation with Multi-Scale Patchification and Attention

Authors: Zekun Li, Xiaoyan Cong, Hongyu Li, Zhiyang Dou, Chuan Guo, Abhay Mittal, Sizhe An, Srinath Sridhar

Abstract: Streaming video diffusion models have made substantial progress toward interactive and dynamic world simulation, but the nested autoregressive and denoising loops of conventional next-frame generation hinder real-time deployment. Recent rolling-window methods pipeline denoising across multiple consecutive frames at different noise levels, improving throughput and long-horizon stability. However, t… ▽ More Streaming video diffusion models have made substantial progress toward interactive and dynamic world simulation, but the nested autoregressive and denoising loops of conventional next-frame generation hinder real-time deployment. Recent rolling-window methods pipeline denoising across multiple consecutive frames at different noise levels, improving throughput and long-horizon stability. However, they tokenize every state at the same fine spatial granularity, leaving substantial noise-dependent redundancy in the joint denoising window. We propose Ms.Forcing, an efficient streaming video generation paradigm that adapts spatial granularity to each state's noise level. Its Multi-Scale Patchification (MSP) assigns coarser patches to noisier states, reducing the active-window token count by 45%, while Multi-Scale Self-Attention (MSSA) matches the density of visible non-sink keys and values to each query scale to further reduce attention cost. Because both schedules are fixed by window position, Ms.Forcing retains a static, hardware-friendly computation graph. We further introduce Homogeneous-Noise-Level DMD (H-DMD), which assembles each fake video from clean predictions sharing the same source noise level, thereby reducing the mismatch between DMD training sequences and inference-time rollouts. The multi-scale design helps offset the additional training cost of backpropagating through overlapping windows. We include both quantitative and qualitative experiments to show that Ms.Forcing reaches 22.84 FPS on a single H200 GPU, 39.6% faster than Rolling Forcing, while significantly improving VBench scores in both short video and long video generation setting. △ Less

Submitted 23 July, 2026; originally announced July 2026.

GraphContainer: A Unified Platform for Comparing and Debugging Graph RAG Methods

Authors: Seonho An, Chaejeong Hyun, Min-Soo Kim

Abstract: Graph RAG mitigates hallucinations and stale knowledge in LLMs, particularly for multi-hop question answering. However, existing approaches remain highly fragmented and incompatible. The structural heterogeneity of graph formats across different frameworks and the lack of granular visualization tools make it exceedingly difficult to evaluate and compare retrieval behaviors. To bridge this gap, we… ▽ More Graph RAG mitigates hallucinations and stale knowledge in LLMs, particularly for multi-hop question answering. However, existing approaches remain highly fragmented and incompatible. The structural heterogeneity of graph formats across different frameworks and the lack of granular visualization tools make it exceedingly difficult to evaluate and compare retrieval behaviors. To bridge this gap, we propose GraphContainer, a novel platform designed to unify and visualize diverse graph RAG workflows. GraphContainer features two key components: (1) a Unified Graph Representation (UGR) layer that seamlessly standardizes multi-format graphs, and (2) a Graph Recorder that tracks and visually renders the step-by-step retrieval process. Through an interactive web interface, we demonstrate GraphContainer's ability to import heterogeneous graphs and perform live, traceable visual debugging of graph RAG methods. Ultimately, we show how GraphContainer enables controlled comparisons of various graph formats and retrieval strategies, lowering the barrier for researchers and practitioners to design optimal graph RAG pipelines. A demonstration video is available at https://youtu.be/O02eNJLwkU0. △ Less

Submitted 4 June, 2026; originally announced July 2026.

Comments: VLDB 2026 demo accepted

Assistant or Actor? Student Trust, Control, and Delegation Regret When Using a General-Purpose AI Agent

Authors: Shiva Pochampally, Shengwei An, Yan Chen

Abstract: When AI agents shift from answering questions to taking actions, users face a new problem: deciding what to delegate, to a system whose action space they cannot fully anticipate. We call the resulting dissatisfaction delegation regret, a pattern in which users regret not that the agent erred, but that it acted beyond what they would have authorized. In a controlled study, 20 university students co… ▽ More When AI agents shift from answering questions to taking actions, users face a new problem: deciding what to delegate, to a system whose action space they cannot fully anticipate. We call the resulting dissatisfaction delegation regret, a pattern in which users regret not that the agent erred, but that it acted beyond what they would have authorized. In a controlled study, 20 university students completed five common daily tasks using OpenClaw, a general-purpose AI agent, across tasks chosen to vary in privacy, stakes, and reversibility. For each task we measured trust, perceived control, transparency, supervision burden, and approval preference on 5-point Likert scales, and collected free-text reflections analyzed through thematic coding. Three findings emerged. First, participants calibrated trust per task rather than per agent: they granted wide autonomy for advisory and low-stakes tasks but demanded confirmation for irreversible, externally visible actions. Second, irreversibility combined with external visibility, rather than stakes alone, appeared to drive trust withdrawal: the moderate-stakes email task triggered the sharpest drop in trust (M = 3.10) and the highest demand for approval (M = 4.65), whereas a high-stakes but verifiable task did not produce the same response. Third, delegation regret appeared consistently when the agent executed actions without preview, even when the output was rated as successful. We discuss implications for agent designs that expose action boundaries, support per-task autonomy policies, and separate advisory output from agentic execution. △ Less

Submitted 14 May, 2026; originally announced July 2026.

Comments: 10 pages, 3 figures

Rotational Motion-Induced Error Compensation for Phase-Shifting Profilometry-Based Eye Reconstruction

Authors: Seong-Jin An, Sanghoon Jeon, Yatong An, Jae-Sang Hyun

Abstract: With the proliferation of immersive Head-Mounted Displays (HMDs) for Virtual and Augmented Reality (VR/AR), reliable and high-precision eye tracking has become increasingly important. Conventional 2D image-based methods offer low system complexity but remain limited in stability, accuracy, and robustness. Three-dimensional ocular surface reconstruction can provide richer geomet-ric information, an… ▽ More With the proliferation of immersive Head-Mounted Displays (HMDs) for Virtual and Augmented Reality (VR/AR), reliable and high-precision eye tracking has become increasingly important. Conventional 2D image-based methods offer low system complexity but remain limited in stability, accuracy, and robustness. Three-dimensional ocular surface reconstruction can provide richer geomet-ric information, and structured light profilometry is particularly attractive because it enables dense and accurate surface measurement. However, Phase-Shifting Profilometry (PSP), which estimates phase from sequentially acquired fringe images, is highly susceptible to motion-induced errors when the eye rotates between frames. This study proposes a rotational motion compensation framework for PSP-based dynamic 3D eye reconstruction. Relative eye rotation is estimated from image-based motion cues using a user-specific 3D eye model in a spherical-coordinate domain. The estimated motion is then used to compensate for camera-pixel mismatch and phase-shift errors caused by inter-frame rotation. A region-wise optimization strategy is further introduced to reduce residual artifacts by inde-pendently refining the compensation strength in different ocular regions. Experiments with a rotating fake eye under non-uniform motion demonstrate that the proposed method substantially suppresses motion-induced deformation and improves reconstruction accuracy. An additional experiment with a non-spherical rigid object indicates that the compensation principle is not restricted to spherical eye geometry. These results establish a practical basis for stable PSP-based dynamic 3D eye reconstruction toward future high-precision eye tracking in immersive environments. △ Less

Submitted 16 July, 2026; originally announced July 2026.

LoCA: Spatially-Aware Low-Rank Convolutional Adaptation of Vision Foundation Models

Authors: Sojung An, Junha Lee, Sujeong You, Nam Ik Cho, Donghyun Kim

Abstract: Pre-trained Vision Foundation Models (VFMs) provide strong visual representations for diverse downstream tasks. The key challenge of VFM adaptation stems from the prohibitive costs of full fine-tuning and catastrophic forgetting. To address this, Low-Rank Adaptation (LoRA) has emerged as the prevailing paradigm for Parameter-Efficient Fine-Tuning (PEFT). However, LoRA is typically designed for tra… ▽ More Pre-trained Vision Foundation Models (VFMs) provide strong visual representations for diverse downstream tasks. The key challenge of VFM adaptation stems from the prohibitive costs of full fine-tuning and catastrophic forgetting. To address this, Low-Rank Adaptation (LoRA) has emerged as the prevailing paradigm for Parameter-Efficient Fine-Tuning (PEFT). However, LoRA is typically designed for transformer self-attention layers parameterized by 2D matrices. Since convolutional kernels inherently couple spatial and channel information within a 4D tensor, forcing them into a monolithic 2D matrix disrupts the inherent spatial topology. In this paper, we propose Low-Rank Convolutional Adaptation (LoCA), a convolution-aware PEFT framework that addresses spatial-channel entanglement by decoupling channel and spatial adaptation. LoCA introduces a low-rank channel adaptation for dense cross-channel mixing and refines spatial bases extracted from pre-trained kernels via Singular Value Decomposition (SVD). Experimental results show that LoCA preserves pre-trained spatial priors and achieves competitive or state-of-the-art performance across fine-grained classification, domain-generalized semantic segmentation, and generative benchmarks. △ Less

Submitted 6 August, 2026; v1 submitted 7 July, 2026; originally announced July 2026.

Comments: Accepted by ECCV 2026

Predicting Therapeutic Outcome via Aligning Patient-Specific Knowledge Graph and Gene-Level Perturbation Representations

Authors: Dongmin Bang, Sugyun An, Inyoung Sung, Ilho Yun, Sun Kim, Sangseon Lee

Abstract: Accurate prediction of patient-specific therapeutic response from pre-treatment transcriptomes is hindered by the scarcity of matched clinical response labels and post-treatment molecular profiles. Preclinical transfer-learning models can simulate drug-induced expression changes but are often hard to interpret and unstable, whereas knowledge-graph methods provide mechanistic context yet remain sta… ▽ More Accurate prediction of patient-specific therapeutic response from pre-treatment transcriptomes is hindered by the scarcity of matched clinical response labels and post-treatment molecular profiles. Preclinical transfer-learning models can simulate drug-induced expression changes but are often hard to interpret and unstable, whereas knowledge-graph methods provide mechanistic context yet remain static and fail to capture drug-induced transcriptomic perturbation dynamics. We propose PREDIKTOR, a patient-centered multi-view framework that aligns a personalized network view with a transferable transcriptomic perturbation view to predict clinical drug response. For each patient, we construct an individualized gene regulatory network from tumor expression using DysRegNet and augment it with drug-target links from DrugBank; a graph neural encoder yields a drug-centric, mechanistically grounded embedding. In parallel, a frozen condition-specific gene-gene attention model pretrained on LINCS L1000 generates a simulated post-perturbation transcriptomic profile for the same patient-drug pair. We align the two views in a shared latent space via a CLIP-style contrastive objective with drug-context hard negatives, then concatenate the representations for end-to-end response classification. On TCGA, PREDIKTOR consistently outperforms state-of-the-art baselines under patient-, drug-, and tissue-split evaluations, and transfers zero-shot to the I-SPY2 trial, improving AUROC by 5.6% over competing methods. The aligned embeddings yield stable gene and pathway attributions that recover known mechanisms, supporting actionable and interpretable precision oncology. △ Less

Submitted 5 July, 2026; originally announced July 2026.

Comments: 12 pages, 5 figures, 5 tables. Accepted at BIOKDD 2026, held in conjunction with ACM SIGKDD 2026

Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist

Authors: Yuanhao Ban, Tong Xie, Sohyun An, Yunqi Hong, Evan Frick, I-Hung Hsu, Wei-Lin Chiang, Ion Stoica, Cho-Jui Hsieh

Abstract: Faithfulness -- how precisely a generated image aligns with its prompt -- is increasingly central to the real-world utility of text-to-image (T2I) models. Existing faithfulness benchmarks, however, rely on simple atomic instructions, on which top-tier systems already achieve near-perfect scores. As T2I models enter creative workflows, users issue multi-faceted requests combining intricate spatial… ▽ More Faithfulness -- how precisely a generated image aligns with its prompt -- is increasingly central to the real-world utility of text-to-image (T2I) models. Existing faithfulness benchmarks, however, rely on simple atomic instructions, on which top-tier systems already achieve near-perfect scores. As T2I models enter creative workflows, users issue multi-faceted requests combining intricate spatial relationships, stylistic constraints, and complex text rendering. In this setting, a single binary VLM-judge score no longer captures which specific constraints the model fails to satisfy. We introduce Arena-T2I Hard, a 310-prompt stress benchmark drawn from real arena T2I logs, with approximately 30 decomposed yes/no constraints per prompt spanning six categories, including text rendering. The strongest closed-source system we evaluate reaches 0.855 with a 33~pp performance gap across 11 systems, demonstrating substantial discriminative power. Moreover, high public-arena rankings fail to predict faithfulness, confirming that holistic Bradley-Terry (BT) preference scores prioritize aesthetics over fine-grained prompt adherence. We propose a dependency-aware checklist reward that decomposes each prompt into a DAG of yes/no questions and zeroes descendants of failed parents, turning faithfulness into a per-constraint training signal. Combined with a BT aesthetic reward via group-decoupled normalization (GDPO), which standardizes each reward within its rollout group so neither collapses, the recipe attains a strictly better faithfulness-aesthetics trade-off on SD3.5-Medium and FLUX.1-dev under MMRB2 pairwise comparisons than every single-reward, naive weighted-sum, or 4-reward BT-ensemble baseline. △ Less

Submitted 30 June, 2026; originally announced June 2026.

Directed Low Diameter Decomposition for Structured Digraphs

Authors: Shinwoo An, Arnold Filtser

Abstract: Low diameter decompositions, or LDDs for short, are a fundamental primitive in the design of efficient graph algorithms. Roughly speaking, an LDD is a distribution over partitions of the vertices into bounded-diameter clusters such that nearby vertices are likely to be clustered together. Recently, there has been growing interest in lifting the notion of LDDs into \emph{directed graphs}. In partic… ▽ More Low diameter decompositions, or LDDs for short, are a fundamental primitive in the design of efficient graph algorithms. Roughly speaking, an LDD is a distribution over partitions of the vertices into bounded-diameter clusters such that nearby vertices are likely to be clustered together. Recently, there has been growing interest in lifting the notion of LDDs into \emph{directed graphs}. In particular, there are two natural directed analogues. The first is a directed LDD, where after removing a random subset of edges, every strongly connected component has a small diameter. The second is a quasipartition, which imposes the stronger requirement that whenever one vertex can still reach another after the edge removal, the two vertices must be close in the original directed metric. Every quasipartition yields an LDD, but the converse does not necessarily hold. In this work, we initiate the systematic study of LDDs in structured directed graphs. As our first main result, we show that any directed graph with pathwidth $\mathsf{pw}$ admits an $(O(\mathsf{pw}), Δ)$-LDD. This improves upon the previous best-known $(2^{O(\mathsf{pw}^2)}, Δ)$-LDD construction, which was implicitly derived from the quasipartition result of Salmasi, Sidiropoulos, and Sridhar [SODA'19]. As our second result, we show that the integrality gap of the Directed Non-Bipartite Sparsest-Cut LP relaxation on an $n$-vertex graph with treewidth $\mathsf{tw}$ is $O(\mathsf{tw} \log n)$. This improves upon the $O(\mathsf{tw}\log^2 n)$ bound of Mémoli, Sidiropoulos, and Sridhar [ICALP'16, Algorithmica'18]. We obtain this result through the refined analysis of the quasipartition construction of Mémoli et al. for bounded treewidth graphs. △ Less

Submitted 30 June, 2026; originally announced June 2026.

Comments: To appear in APPROX 2026. 35pages

ManimAgent: Self-Evolving Multimodal Agents for Visual Education

Authors: Wenjia Jiang, Zongyuan Cai, Yuanhang Shao, Chenru Wang, Boyan Han, Zhixue Song, Keyu Chen, Shengwei An, Xu Yang, Zhou Yang

Abstract: Multi-round reflection lets agents built on large language models recover from failures within a single task, but each task remains an isolated episode: lessons learned across many reflection rounds on one task are discarded before the next begins. We study this gap on a code-generation task: from a scientific paper section, the agent writes Python in the open-source Manim library to render a math… ▽ More Multi-round reflection lets agents built on large language models recover from failures within a single task, but each task remains an isolated episode: lessons learned across many reflection rounds on one task are discarded before the next begins. We study this gap on a code-generation task: from a scientific paper section, the agent writes Python in the open-source Manim library to render a mathematical animation. We present ManimAgent, a self-evolving multimodal agent that carries reflection experience across tasks through a dual-channel Episodic Memory Bank grown entirely from its own task stream, with no weight updates and no human seeds. After each animation converges, a vision-language model scores the rendered keyframes; the resulting signals populate a positive channel M+ that stores success rationales as soft Reference Examples, and a negative channel M- that stores validated failure patterns as hard Known Pitfalls. On a fixed-probe evaluation against no-memory, matched-budget retrieval-augmented generation, and shuffled-memory baselines, blind human Pass@1 rises and reflection rounds fall as memory size grows. We will release the code, frozen memory snapshots, and the task stream. △ Less

Submitted 1 July, 2026; v1 submitted 29 June, 2026; originally announced June 2026.

Comments: Project page: https://manimagent.github.io/. Code: https://github.com/jwj1342/Paper2Manim

ACM Class: I.2.7; I.2.11; I.2.10

A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design

Authors: Tong Xie, Yuanhao Ban, Yunqi Hong, Sohyun An, Yihang Chen, Cho-Jui Hsieh

Abstract: Supervised fine-tuning (SFT) typically maximizes the likelihood of every token in a demonstrated trajectory. However, an observed token can be non-unique, noisy, or misaligned with the model prior. Strictly fitting toward this one-hot target may be suboptimal, especially when the pretrained model encodes a rich knowledge prior. In this work, we reinterpret SFT as target distribution design: instea… ▽ More Supervised fine-tuning (SFT) typically maximizes the likelihood of every token in a demonstrated trajectory. However, an observed token can be non-unique, noisy, or misaligned with the model prior. Strictly fitting toward this one-hot target may be suboptimal, especially when the pretrained model encodes a rich knowledge prior. In this work, we reinterpret SFT as target distribution design: instead of studying only the loss objective, we analyze the token-level target that the loss drives the model to match. We introduce the Q-target framework, which decomposes SFT supervision into two explicit choices: (1) how strongly to rely on the observed token, and (2) how to allocate the remaining probability mass over alternatives. This perspective unifies many existing SFT variants as implicit choices of the target distribution Q. Building on this view, we propose Target-SFT which constructs the training objective directly from the desired target distribution. This method consistently outperforms across the ten reasoning dataset-model settings evaluated, showing the effectiveness of this target-based approach. Overall, our formulation reveals a more fundamental design principle for SFT training and opens a broader search space for SFT objectives. △ Less

Submitted 9 June, 2026; originally announced June 2026.

MoG: Mixture of Experts for Graph-based Retrieval-Augmented Generation

Authors: Zheng Yuan, Chuang Zhou, Linhao Luo, Siyu An, Di Yin, Xing Sun, Xiao Huang

Abstract: Retrieval-augmented generation is intensively studied to ground large language models on external evidence. However, retrieving from a unified knowledge base could inevitably introduce irrelevant information that may mislead generation for complex reasoning. Inspired by the conditional computation of mixture of experts (MoE), where a router sparsely selects specialized experts alongside shared one… ▽ More Retrieval-augmented generation is intensively studied to ground large language models on external evidence. However, retrieving from a unified knowledge base could inevitably introduce irrelevant information that may mislead generation for complex reasoning. Inspired by the conditional computation of mixture of experts (MoE), where a router sparsely selects specialized experts alongside shared ones for each input, we propose \textbf{M}ixture \textbf{o}f experts for \textbf{G}raph-based Retrieval-Augmented Generation, i.e., \textbf{MoG}. It organizes knowledge into two core components: (i) diverse, always-accessible hub graphs that encode semantically and structurally central knowledge and provide contextual clues for expert activation, and (ii) sparsely activated expert graphs that contain domain-specific evidence. MoG first accesses hub graphs to identify general evidence and derive contextual clues. Then, a topology-aware router dynamically activates a limited set of expert graphs conditioned on the query, thereby confining retrieval to a focused evidence subspace. Extensive experiments on challenging benchmarks show that MoG consistently outperforms strong baselines, with over 20\% relative improvement on MuSiQue. Our code is available in https://github.com/DEEP-PolyU/MoG. △ Less

Submitted 29 May, 2026; originally announced May 2026.

KSAFE-MM: A Multimodal Safety Benchmark via Localized Contextualization for Korean Cultural Risks

Authors: Yongwoo Kim, Sojung An, Yunjin Park, Jungwon Yoon, Dujin Lee, HyunBeom Cho, Jaewon Lee, Wonhyuk Lee, Youngchol Kim, JeongYeop Kim, Donghyun Kim

Abstract: Multimodal Large Language Models (MLLMs) exacerbate safety risks by introducing vulnerabilities across multiple modalities, such as language and vision. Current MLLM safety evaluation tools, however, suffer from major limitations: 1) English-centric dataset construction, and 2) a focus on generic risks that are not tied to local cultural contexts. This paper introduces KSAFE-MM, a benchmark for Ko… ▽ More Multimodal Large Language Models (MLLMs) exacerbate safety risks by introducing vulnerabilities across multiple modalities, such as language and vision. Current MLLM safety evaluation tools, however, suffer from major limitations: 1) English-centric dataset construction, and 2) a focus on generic risks that are not tied to local cultural contexts. This paper introduces KSAFE-MM, a benchmark for Korean multimodal safety evaluation that covers both general safety risks and culture-specific vulnerabilities. KSAFE-MM consists of two parts, KSAFE-MM-G and KSAFE-MM-C. KSAFE-MM-G evaluates globally shared risks in Korean contexts through linguistic contextualization, which transforms generic safety queries into contextually grounded multimodal samples. KSAFE-MM-C targets culture-dependent MLLM safety vulnerabilities using localized visual queries derived from real-world contexts. It pairs these visual queries with jailbreak-style textual queries to cover multimodal safety risks involving cultural visual cues and malicious textual intent. Together, these components provide a general-to-local construction pipeline for evaluating both globally shared safety risks and culture-specific vulnerabilities. We evaluate 12 state-of-the-art MLLMs on KSAFE-MM and reveal that models exhibit greater vulnerability to culturally grounded attacks than to generic ones. Notably, jailbreaking strategies substantially amplify attack success rates, with ProgramExecution yielding up to 74.2% ASR compared to 13.4% for standard queries. Furthermore, we identify a systematic trade-off between safety and over-refusal, where models achieving low ASR tend to exhibit excessive refusal behavior on benign queries. These findings highlight the urgent need for culturally grounded safety evaluation beyond English-centric benchmarks. △ Less

Submitted 27 May, 2026; originally announced May 2026.

Toward Native Multimodal Modeling: A Roadmap

Authors: Siyu An, Junru Lu, Junnan Dong, Qiufeng Wang, Yinghui Li, Weizhi Fei, Zichao Yu, Zheng Yuan, Biao Liu, Haopeng Wang, Renzhao Liang, Yixuan Yang, Yunhang Shen, Bo Ke, Keyu Chen, Linhao Luo, Difan Zou, Xiao Huang, Di Yin, Ruizhi Qiao, Xing Sun

Abstract: Multimodal modeling represents a vital step from modality-agnostic reasoning toward world modeling. While early approaches predominantly rely on late-fusion that assembles encoders and frozen language backbones with output heads, recent efforts have shifted the paradigm toward native multimodal modeling (NMM) with the intrinsic integration of modalities for superior multimodal performance. Despite… ▽ More Multimodal modeling represents a vital step from modality-agnostic reasoning toward world modeling. While early approaches predominantly rely on late-fusion that assembles encoders and frozen language backbones with output heads, recent efforts have shifted the paradigm toward native multimodal modeling (NMM) with the intrinsic integration of modalities for superior multimodal performance. Despite its potential, the design space of native architectures remains insufficiently defined. In this paper, we present the community with a formalized roadmap for this transition. Specifically, we formally define the architectural nativity, distinguishing mid-fusion and early-fusion from non-native paradigms. We further organize the existing native models through the lens of input-output duality into three categories: (i) Multi-to-Text for cross-modal comprehension with text-only output; (ii) Multi-to-Target for scenario-oriented generation, e.g., image, audio and video generation, and (iii) Multi-to-Multi for unified modeling with symmetric input-output. We deliver a comprehensive and industrial-grade investigation into the transition toward the definitive NMM framework, where understanding and generation seamlessly coexist within a unified transformer paradigm. We systematically unpack the end-to-end pipeline from industrial perspectives from architectural coordination, massive data curation, to full-stack training recipes, inference & deployment, and the comprehensive evaluation for truly native modeling. △ Less

Submitted 24 May, 2026; originally announced May 2026.

Comments: 52 pages, 5 figures, 3 tables, ~300 references

Backdooring Masked Diffusion Language Models

Authors: Daniel Yiming Cao, Chengzhong Wang, Sheng-Yen Chou, Chengyu Huang, Pin-Yu Chen, Shengwei An

Abstract: Masked diffusion language models (MDLMs) are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored. Existing backdoor attacks on Gaussian diffusion models or autoregressive language models do not directly apply to MDLMs because MDLMs rely on discrete state corruption and iterative denoising rather than continuous noising or left-to-r… ▽ More Masked diffusion language models (MDLMs) are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored. Existing backdoor attacks on Gaussian diffusion models or autoregressive language models do not directly apply to MDLMs because MDLMs rely on discrete state corruption and iterative denoising rather than continuous noising or left-to-right prediction. In this work, we present the first systematic study of training-time backdoor attacks on MDLMs. We propose SHADOWMASK, a backdoor attack that modifies the MDLM forward corruption process by replacing the standard all-mask terminal distribution with a trigger-mask mixture prior. This creates a dedicated denoising pathway from trigger-corrupted states to attacker-specified targets while preserving clean denoising behavior. We further provide a principled mathematical formulation by defining the backdoored forward process, deriving the reverse-time posterior, and obtaining the continuous-time training objective. Evaluations on DiT-based MDLM and LLaDA-8B-Instruct across WikiText-103, OpenWebText, and Alpaca show that SHADOWMASK achieves near-100% attack success, substantially outperforms standard data poisoning, largely preserves clean utility, remains effective under full-model and parameter-efficient fine-tuning, and is robust against representative defenses. △ Less

Submitted 2 June, 2026; v1 submitted 18 May, 2026; originally announced May 2026.

Estimating Subgraph Importance with Structural Prior Domain Knowledge

Authors: Changhyun Kim, Seunghwan An, Jong-June Jeon

Abstract: We propose a subgraph importance estimation method for pretrained Graph Neural Networks (GNNs) on graph-level tasks, formulated as a linear Group Lasso regression problem in the embedding space. Our method effectively leverages prior domain knowledge of graph substructures, while remaining independent of the specific form of the output layer or readout function used in the GNN architecture, and it… ▽ More We propose a subgraph importance estimation method for pretrained Graph Neural Networks (GNNs) on graph-level tasks, formulated as a linear Group Lasso regression problem in the embedding space. Our method effectively leverages prior domain knowledge of graph substructures, while remaining independent of the specific form of the output layer or readout function used in the GNN architecture, and it does not require access to ground-truth target labels. Experiments on real-world graph datasets demonstrate that our method consistently outperforms existing baselines in subgraph importance estimation. Furthermore, we extend our method to identify important nodes within the graph. △ Less

Submitted 12 May, 2026; originally announced May 2026.

Towards LLM-Based Analysis of Virtualization-Obfuscated Code through Automated Data Generation

Authors: Sangjun An, Hyeyeon Park, Yejin Son, Seoksu Lee, Eun-Sun Cho

Abstract: Virtualization-based obfuscation produces extremely large and structurally complex binaries, posing challenges for LLM-based analysis due to input size limits and the need for large-scale labeled data. We address this by focusing on structural rather than full semantic analysis. Obfuscated binaries are decomposed into the largest semantically coherent units that fit within LLM constraints and are… ▽ More Virtualization-based obfuscation produces extremely large and structurally complex binaries, posing challenges for LLM-based analysis due to input size limits and the need for large-scale labeled data. We address this by focusing on structural rather than full semantic analysis. Obfuscated binaries are decomposed into the largest semantically coherent units that fit within LLM constraints and are labeled according to their structural roles. We implement a static analysis framework to automate labeling and enable large-scale dataset generation. Our prototype shows strong performance on real-world virtualization obfuscators. △ Less

Submitted 11 May, 2026; originally announced May 2026.

IAM: Identity-Aware Human Motion and Shape Joint Generation

Authors: Wenqi Jia, Zekun Li, Abhay Mittal, Chengcheng Tang, Chuan Guo, Lezi Wang, James Matthew Rehg, Lingling Tao, Size An

Abstract: Recent advances in text-driven human motion generation enable models to synthesize realistic motion sequences from natural language descriptions. However, most existing approaches assume identity-neutral motion and generate movements using a canonical body representation, ignoring the strong influence of body morphology on motion dynamics. In practice, attributes such as body proportions, mass dis… ▽ More Recent advances in text-driven human motion generation enable models to synthesize realistic motion sequences from natural language descriptions. However, most existing approaches assume identity-neutral motion and generate movements using a canonical body representation, ignoring the strong influence of body morphology on motion dynamics. In practice, attributes such as body proportions, mass distribution, and age significantly affect how actions are performed, and neglecting this coupling often leads to physically inconsistent motions. We propose an identity-aware motion generation framework that explicitly models the relationship between body morphology and motion dynamics. Instead of relying on explicit geometric measurements, identity is represented using multimodal signals, including natural language descriptions and visual cues. We further introduce a joint motion-shape generation paradigm that simultaneously synthesizes motion sequences and body shape parameters, allowing identity cues to directly modulate motion dynamics. Extensive experiments on motion capture datasets and large-scale in-the-wild videos demonstrate improved motion realism and motion-identity consistency while maintaining high motion quality. Project page: https://vjwq.github.io/IAM △ Less

Submitted 27 April, 2026; originally announced April 2026.

A Systematic Approach for Large Language Models Debugging

Authors: Basel Shbita, Anna Lisa Gentile, Bing Zhang, Sungeun An, Shailja Thakur, Shubhi Asthana, Yi Zhou, Saptha Surendran, Farhan Ahmed, Rohan Kulkarni, Yuya Jeremy Ong, Chad DeLuca, Hima Patel

Abstract: Large language models (LLMs) have become central to modern AI workflows, powering applications from open-ended text generation to complex agent-based reasoning. However, debugging these models remains a persistent challenge due to their opaque and probabilistic nature and the difficulty of diagnosing errors across diverse tasks and settings. This paper introduces a systematic approach for LLM debu… ▽ More Large language models (LLMs) have become central to modern AI workflows, powering applications from open-ended text generation to complex agent-based reasoning. However, debugging these models remains a persistent challenge due to their opaque and probabilistic nature and the difficulty of diagnosing errors across diverse tasks and settings. This paper introduces a systematic approach for LLM debugging that treats models as observable systems, providing structured, model-agnostic methods from issue detection to model refinement. By unifying evaluation, interpretability, and error-analysis practices, our approach enables practitioners to iteratively diagnose model weaknesses, refine prompts and model parameters, and adapt data for fine-tuning or assessment, while remaining effective in contexts where standardized benchmarks and evaluation criteria are lacking. We argue that such a structured methodology not only accelerates troubleshooting but also fosters reproducibility, transparency, and scalability in the deployment of LLM-based systems. △ Less

Submitted 24 April, 2026; originally announced April 2026.

STaD: Scaffolded Task Design for Identifying Compositional Skill Gaps in LLMs

Authors: Sungeun An, Swanand Ravindra Kadhe, Shailja Thakur, Chad DeLuca, Hima Patel

Abstract: Benchmarks are often used as a standard to understand LLM capabilities in different domains. However, aggregate benchmark scores provide limited insight into compositional skill gaps of LLMs and how to improve them. To make these weaknesses visible, we propose Scaffolded Task Design (STaD) framework. STaD generates controlled variations of benchmark tasks based on the concept of scaffolding, which… ▽ More Benchmarks are often used as a standard to understand LLM capabilities in different domains. However, aggregate benchmark scores provide limited insight into compositional skill gaps of LLMs and how to improve them. To make these weaknesses visible, we propose Scaffolded Task Design (STaD) framework. STaD generates controlled variations of benchmark tasks based on the concept of scaffolding, which introduces structured, incremental support in a step-by-step manner. Rather than inspecting failures individually, this approach enables systematic and scalable probing of model behavior by identifying the specific reasoning skill compositions they lack. Treating the LLM as a black box, our experiments on six models of varying sizes reveal multiple failure points in three reasoning benchmarks and highlight each model's unique and distinct skill gaps. △ Less

Submitted 21 April, 2026; v1 submitted 20 April, 2026; originally announced April 2026.

Comments: 9 pages, 3 figures, 3 tables, ACL Findings 2026

FRESCO: Benchmarking and Optimizing Re-rankers for Evolving Semantic Conflict in Retrieval-Augmented Generation

Authors: Sohyun An, Hayeon Lee, Shuibenyang Yuan, Chun-cheng Jason Chen, Cho-Jui Hsieh, Vijai Mohan, Alexander Min

Abstract: Retrieval-Augmented Generation (RAG) is a key approach to mitigating the temporal staleness of large language models (LLMs) by grounding responses in up-to-date evidence. Within the RAG pipeline, re-rankers play a pivotal role in selecting the most useful documents from retrieved candidates. However, existing benchmarks predominantly evaluate re-rankers in static settings and do not adequately ass… ▽ More Retrieval-Augmented Generation (RAG) is a key approach to mitigating the temporal staleness of large language models (LLMs) by grounding responses in up-to-date evidence. Within the RAG pipeline, re-rankers play a pivotal role in selecting the most useful documents from retrieved candidates. However, existing benchmarks predominantly evaluate re-rankers in static settings and do not adequately assess performance under evolving information -- a critical gap, as real-world systems often must choose among temporally different pieces of evidence. To address this limitation, we introduce FRESCO (Factual Recency and Evolving Semantic COnflict), a benchmark for evaluating re-rankers in temporally dynamic contexts. By pairing recency-seeking queries with historical Wikipedia revisions, FRESCO tests whether re-rankers can prioritize factually recent evidence while maintaining semantic relevance. Our evaluation reveals a consistent failure mode across existing re-rankers: a strong bias toward older, semantically rich documents, even when they are factually obsolete. We further investigate an instruction optimization framework to mitigate this issue. By identifying Pareto-optimal instructions that balance Evolving and Non-Evolving Knowledge tasks, we obtain gains of up to 27% on Evolving Knowledge tasks while maintaining competitive performance on Non-Evolving Knowledge tasks. △ Less

Submitted 14 April, 2026; originally announced April 2026.

Cycle-Consistent Search: Question Reconstructability as a Proxy Reward for Search Agent Training

Authors: Sohyun An, Shuibenyang Yuan, Hayeon Lee, Cho-Jui Hsieh, Alexander Min

Abstract: Reinforcement Learning (RL) has shown strong potential for optimizing search agents in complex information retrieval tasks. However, existing approaches predominantly rely on gold supervision, such as ground-truth answers, which is difficult to scale. To address this limitation, we propose Cycle-Consistent Search (CCS), a gold-supervision-free framework for training search agents, inspired by cycl… ▽ More Reinforcement Learning (RL) has shown strong potential for optimizing search agents in complex information retrieval tasks. However, existing approaches predominantly rely on gold supervision, such as ground-truth answers, which is difficult to scale. To address this limitation, we propose Cycle-Consistent Search (CCS), a gold-supervision-free framework for training search agents, inspired by cycle-consistency techniques from unsupervised machine translation and image-to-image translation. Our key hypothesis is that an optimal search trajectory, unlike insufficient or irrelevant ones, serves as a lossless encoding of the question's intent. Consequently, a high-quality trajectory should preserve the information required to accurately reconstruct the original question, thereby inducing a reward signal for policy optimization. However, naive cycle-consistency objectives are vulnerable to information leakage, as reconstruction may rely on superficial lexical cues rather than the underlying search process. To reduce this effect, we apply information bottlenecks, including exclusion of the final response and named entity recognition (NER) masking of search queries. These constraints force reconstruction to rely on retrieved observations together with the structural scaffold, ensuring that the resulting reward signal reflects informational adequacy rather than linguistic redundancy. Experiments on question-answering benchmarks show that CCS achieves performance comparable to supervised baselines while outperforming prior methods that do not rely on gold supervision. These results suggest that CCS provides a scalable training paradigm for training search agents in settings where gold supervision is unavailable. △ Less

Submitted 14 April, 2026; originally announced April 2026.

General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks

Authors: Junlin Liu, Shengnan An, Shuang Zhou, Dan Ma, Shixiong Luo, Ying Xie, Yuan Zhang, Wenling Yuan, Yifan Zhou, Xiaoyu Li, Ziwen Wang, Xuezhi Cao, Xunliang Cai

Abstract: Contemporary large language models (LLMs) have demonstrated remarkable reasoning capabilities, particularly in specialized domains like mathematics and physics. However, their ability to generalize these reasoning skills to more general and broader contexts--often termed general reasoning--remains under-explored. Unlike domain-specific reasoning, general reasoning relies less on expert knowledge b… ▽ More Contemporary large language models (LLMs) have demonstrated remarkable reasoning capabilities, particularly in specialized domains like mathematics and physics. However, their ability to generalize these reasoning skills to more general and broader contexts--often termed general reasoning--remains under-explored. Unlike domain-specific reasoning, general reasoning relies less on expert knowledge but still presents formidable reasoning challenges, such as complex constraints, nested logical branches, and semantic interference. To address this gap, we introduce General365, a benchmark specifically designed to assess general reasoning in LLMs. By restricting background knowledge to a K-12 level, General365 explicitly decouples reasoning from specialized expertise. The benchmark comprises 365 seed problems and 1,095 variant problems across eight categories, ensuring both high difficulty and diversity. Evaluations across 26 leading LLMs reveal that even the top-performing model achieves only 62.8% accuracy, in stark contrast to the near-perfect performances of LLMs in math and physics benchmarks. These results suggest that the reasoning abilities of current LLMs are heavily domain-dependent, leaving significant room for improvement in broader applications. We envision General365 as a catalyst for advancing LLM reasoning beyond domain-specific tasks toward robust, general-purpose real-world scenarios. Code, Dataset, and Leaderboard: https://general365.github.io △ Less

Submitted 13 April, 2026; originally announced April 2026.

Comments: 17 pages, 9 figures

Problem Reductions at Scale: Agentic Integration of Computationally Hard Problems

Authors: Xi-Wei Pan, Shi-Wen An, Jin-Guo Liu

Abstract: Solving an NP-hard optimization problem often requires reformulating it for a specific solver -- quantum hardware, a commercial optimizer, or a domain heuristic. A tool for polynomial-time reductions between hard problems would let practitioners route any supported problem to any supported solver through a single interface. Building such a library at scale, however, has remained out of reach. We s… ▽ More Solving an NP-hard optimization problem often requires reformulating it for a specific solver -- quantum hardware, a commercial optimizer, or a domain heuristic. A tool for polynomial-time reductions between hard problems would let practitioners route any supported problem to any supported solver through a single interface. Building such a library at scale, however, has remained out of reach. We show that harness engineering, the practice of designing constraints, verification systems, and feedback loops that channel AI coding agents, can overcome this barrier. Our harness combines a no-code contribution route for domain experts, a multilayer verification stack ranging from type-level checks to agentic feature tests (AI agents role-playing as end users), and a fully automated implementation-review-integration pipeline. In about three months, we built a command-line tool backed by a library of 100+ problem types and 200+ reduction rules in over 170k lines of Rust. The result suggests that a well-engineered harness lets agents build well-tested software at a scale and pace beyond prior reduction-library efforts. Because the reduction graph composes transitively, a new solver registered for any single problem type instantly becomes available to every problem connected by a reduction path. The source code is available at https://github.com/CodingThrust/problem-reductions. △ Less

Submitted 7 May, 2026; v1 submitted 13 April, 2026; originally announced April 2026.

Comments: The source code is available at https://github.com/CodingThrust/problem-reductions

CRIT: Graph-Based Automatic Data Synthesis to Enhance Cross-Modal Multi-Hop Reasoning

Authors: Junyoung Sung, Seungwoo Lyu, Minjun Kim, Sumin An, Arsha Nagrani, Paul Hongsuck Seo

Abstract: Real-world reasoning often requires combining information across modalities, connecting textual context with visual cues in a multi-hop process. Yet, most multimodal benchmarks fail to capture this ability: they typically rely on single images or set of images, where answers can be inferred from a single modality alone. This limitation is mirrored in the training data, where interleaved image-text… ▽ More Real-world reasoning often requires combining information across modalities, connecting textual context with visual cues in a multi-hop process. Yet, most multimodal benchmarks fail to capture this ability: they typically rely on single images or set of images, where answers can be inferred from a single modality alone. This limitation is mirrored in the training data, where interleaved image-text content rarely enforces complementary, multi-hop reasoning. As a result, Vision-Language Models (VLMs) frequently hallucinate and produce reasoning traces poorly grounded in visual evidence. To address this gap, we introduce CRIT, a new dataset and benchmark built with a graph-based automatic pipeline for generating complex cross-modal reasoning tasks. CRIT consists of diverse domains ranging from natural images, videos, and text-rich sources, and includes a manually verified test set for reliable evaluation. Experiments on this benchmark reveal that even state-of-the-art models struggle on such reasoning tasks. Models trained on CRIT show significant gains in cross-modal multi-hop reasoning, including strong improvements on SPIQA and other standard multimodal benchmarks. △ Less

Submitted 2 April, 2026; originally announced April 2026.

Comments: Accepted to CVPR 2026

SHOW3D: Capturing Scenes of 3D Hands and Objects in the Wild

Authors: Patrick Rim, Kevin Harris, Braden Copple, Shangchen Han, Xu Xie, Ivan Shugurov, Sizhe An, He Wen, Alex Wong, Tomas Hodan, Kun He

Abstract: Accurate 3D understanding of human hands and objects during manipulation remains a significant challenge for egocentric computer vision. Existing hand-object interaction datasets are predominantly captured in controlled studio settings, which limits both environmental diversity and the ability of models trained on such data to generalize to real-world scenarios. To address this challenge, we intro… ▽ More Accurate 3D understanding of human hands and objects during manipulation remains a significant challenge for egocentric computer vision. Existing hand-object interaction datasets are predominantly captured in controlled studio settings, which limits both environmental diversity and the ability of models trained on such data to generalize to real-world scenarios. To address this challenge, we introduce a novel marker-less multi-camera system that allows for nearly unconstrained mobility in genuinely in-the-wild conditions, while still having the ability to generate precise 3D annotations of hands and objects. The capture system consists of a lightweight, back-mounted, multi-camera rig that is synchronized and calibrated with a user-worn VR headset. For 3D ground-truth annotation of hands and objects, we develop an ego-exo tracking pipeline and rigorously evaluate its quality. Finally, we present SHOW3D, the first large-scale dataset with 3D annotations that show hands interacting with objects in diverse real-world environments, including outdoor settings. Our approach significantly reduces the fundamental trade-off between environmental realism and accuracy of 3D annotations, which we validate with experiments on several downstream tasks. show3d-dataset.github.io △ Less

Submitted 30 March, 2026; originally announced March 2026.

Comments: CVPR 2026

A Cross-Scale Decoder with Token Refinement for Off-Road Semantic Segmentation

Authors: Seongkyu Choi Jhonghyun An

Abstract: Off-road semantic segmentation is fundamentally challenged by irregular terrain, vegetation clutter, and inherent annotation ambiguity. Unlike urban scenes with crisp object boundaries, off-road environments exhibit strong class-level similarity among terrain categories, resulting in thick and uncertain transition regions that degrade boundary coherence and destabilize training. Rare or thin struc… ▽ More Off-road semantic segmentation is fundamentally challenged by irregular terrain, vegetation clutter, and inherent annotation ambiguity. Unlike urban scenes with crisp object boundaries, off-road environments exhibit strong class-level similarity among terrain categories, resulting in thick and uncertain transition regions that degrade boundary coherence and destabilize training. Rare or thin structures, such as narrow traversable gaps or isolated obstacles, further receive sparse and unreliable supervision and are easily overwhelmed by dominant background textures. Existing decoder designs either rely on low-scale bottlenecks that oversmooth fine structural details, or repeatedly fuse high-detail features, which tends to amplify annotation noise and incur substantial computational cost. We present a cross-scale decoder that explicitly addresses these challenges through three complementary mechanisms. First, a global--local token refinement module consolidates semantic context on a compact bottleneck lattice, guided by boundary-aware regularization to remain robust under ambiguous supervision. Second, a gated detail bridge selectively injects fine-scale structural cues only once through cross-scale attention, preserving boundary and texture information while avoiding noise accumulation. Third, an uncertainty-guided class-aware point refinement selectively updates the least reliable pixels, improving rare and ambiguous structures with minimal computational overhead. The resulting framework achieves noise-robust and boundary-preserving segmentation tailored to off-road environments, recovering fine structural details while maintaining deployment-friendly efficiency. Experimental results on standard off-road benchmarks demonstrate consistent improvements over prior approaches without resorting to heavy dense feature fusion. △ Less

Submitted 29 March, 2026; originally announced March 2026.

GlowQ: Group-Shared LOw-Rank Approximation for Quantized LLMs

Authors: Selim An, Il hong Suh, Yeseong Kim

Abstract: Quantization techniques such as BitsAndBytes, AWQ, and GPTQ are widely used as a standard method in deploying large language models but often degrades accuracy when using low-bit representations, e.g., 4 bits. Low-rank correction methods (e.g., LQER, QERA, ASER) has been proposed to mitigate this issue, however, they restore all layers and insert error-correction modules into every decoder block,… ▽ More Quantization techniques such as BitsAndBytes, AWQ, and GPTQ are widely used as a standard method in deploying large language models but often degrades accuracy when using low-bit representations, e.g., 4 bits. Low-rank correction methods (e.g., LQER, QERA, ASER) has been proposed to mitigate this issue, however, they restore all layers and insert error-correction modules into every decoder block, which increases latency and memory overhead. To address this limitation, we propose GlowQ, a group-shared low-rank approximation for quantized LLMs that caches a single shared right factor per input-sharing group and restores only the groups or layers that yield the highest accuracy benefit. GlowQ computes the high-precision projection once per input-sharing group and reuses it across its modules, reducing parameter and memory overhead, and retaining the expressivity of layer-specific corrections. We also propose a selective variant, GlowQ-S, that applies the cached shared module only where it provides the largest benefit. Compared with strong baselines, our approach reduces TTFB by (5.6%) and increases throughput by (9.6%) on average, while reducing perplexity on WikiText-2 by (0.17%) and increasing downstream accuracy by 0.42 percentage points. The selective model GlowQ-S further reduces latency, cutting TTFB by (23.4%) and increasing throughput by (37.4%), while maintaining accuracy within 0.2 percentage points on average. Code is available at https://github.com/ahnselim/GlowQ. △ Less

Submitted 30 April, 2026; v1 submitted 26 March, 2026; originally announced March 2026.

T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search

Authors: Hyomin Lee, Sangwoo Park, Yumin Choi, Sohyun An, Seanie Lee, Sung Ju Hwang

Abstract: While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models (LLMs), such approaches fail to capture agent-specific vulnerabilities that emerge through multi-step tool execution, particularly in rapidly growing ecosystems such as the Model Context Protocol (MCP). To address this gap, we propose a trajectory-aware evolutionary search method, T-MAP, which… ▽ More While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models (LLMs), such approaches fail to capture agent-specific vulnerabilities that emerge through multi-step tool execution, particularly in rapidly growing ecosystems such as the Model Context Protocol (MCP). To address this gap, we propose a trajectory-aware evolutionary search method, T-MAP, which leverages execution trajectories to guide the discovery of adversarial prompts. Our approach enables the automatic generation of attacks that not only bypass safety guardrails but also reliably realize harmful objectives through actual tool interactions. Empirical evaluations across diverse MCP environments demonstrate that T-MAP substantially outperforms baselines in attack realization rate (ARR) and remains effective against frontier models, including GPT-5.2, Gemini-3-Pro, Qwen3.5, and GLM-5, thereby revealing previously underexplored vulnerabilities in autonomous LLM agents. △ Less

Submitted 21 March, 2026; originally announced March 2026.

LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning

Authors: Jianing Wang, Jianfei Zhang, Qi Guo, Linsen Guo, Rumei Li, Chao Zhang, Chong Peng, Cunguang Wang, Dengchang Zhao, Jiarong Shi, Jingang Wang, Liulin Feng, Mengxia Shen, Qi Li, Shengnan An, Shun Wang, Wei Shi, Xiangyu Xi, Xiaoyu Li, Xuezhi Cao, Yi Lu, Yunke Zhao, Zhengyu Chen, Zhimin Lin, Wei Wang , et al. (2 additional authors not shown)

Abstract: We introduce LongCat-Flash-Prover, a flagship 560-billion-parameter open-source Mixture-of- Experts (MoE) model that advances Native Formal Reasoning in Lean4 through agentic tool-integrated reasoning (TIR). We decompose the native formal reasoning task into three independent formal capabilities, i.e., auto-formalization, sketching, and proving. To facilitate these capabilities, we propose a Hybri… ▽ More We introduce LongCat-Flash-Prover, a flagship 560-billion-parameter open-source Mixture-of- Experts (MoE) model that advances Native Formal Reasoning in Lean4 through agentic tool-integrated reasoning (TIR). We decompose the native formal reasoning task into three independent formal capabilities, i.e., auto-formalization, sketching, and proving. To facilitate these capabilities, we propose a Hybrid-Experts Iteration Framework to expand high-quality task trajectories, including generating a formal statement based on a given informal problem, producing a whole-proof directly from the statement, or a lemma-style sketch. During agentic RL, we present a Hierarchical Importance Sampling Policy Optimization (HisPO) algorithm, which aims to stabilize the MoE model training on such long-horizon tasks. It employs a gradient masking strategy that accounts for the policy staleness and the inherent train-inference engine discrepancies at both sequence and token levels. Additionally, we also incorporate theorem consistency and legality detection mechanisms to eliminate reward hacking issues. Extensive evaluations show that our LongCat-Flash-Prover sets a new state-of-the-art for open-weights models in both auto-formalization and theorem proving. Demonstrating remarkable sample efficiency, it achieves a 97.1% pass rate on MiniF2F-Test using only 72 inference budget per problem. On more challenging benchmarks, it solves 70.8% of ProverBench and 41.5% of PutnamBench with no more than 220 attempts per problem, significantly outperforming existing open-weights baselines. △ Less

Submitted 22 March, 2026; originally announced March 2026.

Comments: 43 pages, 5 figures

UniSAFE: A Comprehensive Benchmark for Safety Evaluation of Unified Multimodal Models

Authors: Segyu Lee, Boryeong Cho, Hojung Jung, Seokhyun An, Juhyeong Kim, Jaehyun Kwak, Yongjin Yang, Sangwon Jang, Youngrok Park, Wonjun Chang, Se-Young Yun

Abstract: Unified Multimodal Models (UMMs) offer powerful cross-modality capabilities but introduce new safety risks not observed in single-task models. Despite their emergence, existing safety benchmarks remain fragmented across tasks and modalities, limiting the comprehensive evaluation of complex system-level vulnerabilities. To address this gap, we introduce UniSAFE, the first comprehensive benchmark fo… ▽ More Unified Multimodal Models (UMMs) offer powerful cross-modality capabilities but introduce new safety risks not observed in single-task models. Despite their emergence, existing safety benchmarks remain fragmented across tasks and modalities, limiting the comprehensive evaluation of complex system-level vulnerabilities. To address this gap, we introduce UniSAFE, the first comprehensive benchmark for system-level safety evaluation of UMMs across 7 I/O modality combinations, spanning conventional tasks and novel multimodal-context image generation settings. UniSAFE is built with a shared-target design that projects common risk scenarios across task-specific I/O configurations, enabling controlled cross-task comparisons of safety failures. Comprising 6,802 curated instances, we use UniSAFE to evaluate 15 state-of-the-art UMMs, both proprietary and open-source. Our results reveal critical vulnerabilities across current UMMs, including elevated safety violations in multi-image composition and multi-turn settings, with image-output tasks consistently more vulnerable than text-output tasks. These findings highlight the need for stronger system-level safety alignment for UMMs. Our code and data are publicly available at https://github.com/segyulee/UniSAFE △ Less

Submitted 18 March, 2026; originally announced March 2026.

Comments: Equal contribution by first three authors, 55 pages

UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors

Authors: Xiaoyan Cong, Zekun Li, Zhiyang Dou, Hongyu Li, Omid Taheri, Chuan Guo, Abhay Mittal, Sizhe An, Taku Komura, Wojciech Matusik, Michael J. Black, Srinath Sridhar

Abstract: Large-scale foundation models (LFMs) have recently made impressive progress in text-to-motion generation by learning strong generative priors from massive 3D human motion datasets and paired text descriptions. However, how to effectively and efficiently leverage such single-purpose motion LFMs, i.e., text-to-motion synthesis, in more diverse cross-modal and in-context motion generation downstream… ▽ More Large-scale foundation models (LFMs) have recently made impressive progress in text-to-motion generation by learning strong generative priors from massive 3D human motion datasets and paired text descriptions. However, how to effectively and efficiently leverage such single-purpose motion LFMs, i.e., text-to-motion synthesis, in more diverse cross-modal and in-context motion generation downstream tasks remains largely unclear. Prior work typically adapts pretrained generative priors to individual downstream tasks in a task-specific manner. In contrast, our goal is to unlock such priors to support a broad spectrum of downstream motion generation tasks within a single unified framework. To bridge this gap, we present UMO, a simple yet general unified formulation that casts diverse downstream tasks into compositions of atomic per-frame operations, enabling in-context adaptation to unlock the generative priors of pretrained DiT-based motion LFMs. Specifically, UMO introduces three learnable frame-level meta-operation embeddings to specify per-frame intent and employs lightweight temporal fusion to inject in-context cues into the pretrained backbone, with negligible runtime overhead compared to the base model. With this design, UMO finetunes the pretrained model, originally limited to text-to-motion generation, to support diverse previously unsupported tasks, including temporal inpainting, text-guided motion editing, text-serialized geometric constraints, and multi-identity reaction generation. Experiments demonstrate that UMO consistently outperforms task-specific and training-free baselines across a wide range of benchmarks, despite using a single unified model. Code and model will be publicly available. Project Page: https://oliver-cong02.github.io/UMO.github.io/ △ Less

Submitted 16 March, 2026; originally announced March 2026.

Comments: Project Page: https://oliver-cong02.github.io/UMO.github.io/

GenState-AI: State-Aware Dataset for Text-to-Video Retrieval on AI-Generated Videos

Authors: Minghan Li, Tongna Chen, Tianrui Lv, Yishuai Zhang, Suchao An, Guodong Zhou

Abstract: Existing text-to-video retrieval benchmarks are dominated by real-world footage where much of the semantics can be inferred from a single frame, leaving temporal reasoning and explicit end-state grounding under-evaluated. We introduce GenState-AI, an AI-generated benchmark centered on controlled state transitions, where each query is paired with a main video, a temporal hard negative that differs… ▽ More Existing text-to-video retrieval benchmarks are dominated by real-world footage where much of the semantics can be inferred from a single frame, leaving temporal reasoning and explicit end-state grounding under-evaluated. We introduce GenState-AI, an AI-generated benchmark centered on controlled state transitions, where each query is paired with a main video, a temporal hard negative that differs only in the decisive end-state, and a semantic hard negative with content substitution, enabling fine-grained diagnosis of temporal vs. semantic confusions beyond appearance matching. Using Wan2.2-TI2V-5B, we generate short clips whose meaning depends on precise changes in position, quantity, and object relations, providing controllable evaluation conditions for state-aware retrieval. We evaluate two representative MLLM-based baselines, and observe consistent and interpretable failure patterns: both frequently confuse the main video with the temporal hard negative and over-prefer temporally plausible but end-state-incorrect clips, indicating insufficient grounding to decisive end-state evidence, while being comparatively less sensitive to semantic substitutions. We further introduce triplet-based diagnostic analyses, including relative-order statistics and breakdowns across transition categories, to make temporal vs. semantic failure sources explicit. GenState-AI provides a focused testbed for state-aware, temporally and semantically sensitive text-to-video retrieval, and will be released on huggingface.co. △ Less

Submitted 15 March, 2026; originally announced March 2026.

Deep Tabular Research via Continual Experience-Driven Execution

Authors: Junnan Dong, Chuang Zhou, Zheng Yuan, Yifei Yu, Qiufeng Wang, Yinghui Li, Siyu An, Di Yin, Xing Sun, Feiyue Huang

Abstract: Large language models often struggle with complex long-horizon analytical tasks over unstructured tables, which typically feature hierarchical and bidirectional headers and non-canonical layouts. We formalize this challenge as Deep Tabular Research (DTR), requiring multi-step reasoning over interdependent table regions. To address DTR, we propose a novel agentic framework that treats tabular reaso… ▽ More Large language models often struggle with complex long-horizon analytical tasks over unstructured tables, which typically feature hierarchical and bidirectional headers and non-canonical layouts. We formalize this challenge as Deep Tabular Research (DTR), requiring multi-step reasoning over interdependent table regions. To address DTR, we propose a novel agentic framework that treats tabular reasoning as a closed-loop decision-making process. We carefully design a coupled query and table comprehension for path decision making and operational execution. Specifically, (i) DTR first constructs a hierarchical meta graph to capture bidirectional semantics, mapping natural language queries into an operation-level search space; (ii) To navigate this space, we introduce an expectation-aware selection policy that prioritizes high-utility execution paths; (iii) Crucially, historical execution outcomes are synthesized into a siamese structured memory, i.e., parameterized updates and abstracted texts, enabling continual refinement. Extensive experiments on challenging unstructured tabular benchmarks verify the effectiveness and highlight the necessity of separating strategic planning from low-level execution for long-horizon tabular reasoning. △ Less

Submitted 11 March, 2026; v1 submitted 9 March, 2026; originally announced March 2026.

Comments: 23 pages, 6 tables, 6 figures

QATMA: Quantization-Aware Training with Multimodal Alignment for Open-Vocabulary Object Detection

Authors: Jinyeong Park, Donghwa Kang, Seunghwan An, Insoo Kim, Brent ByungHoon Kang, Hyeongboo Baek, Jibum Kim

Abstract: Quantizing open-vocabulary object detection (OVOD) models reduces their memory and computational costs, but extremely low-bit quantization severely degrades both cross-modal (region-text) and intra-modal (region-region) alignments. This multimodal degradation is a unique challenge that prior quantization methods for closed-vocabulary detectors fail to resolve. To overcome this, we propose Quantiza… ▽ More Quantizing open-vocabulary object detection (OVOD) models reduces their memory and computational costs, but extremely low-bit quantization severely degrades both cross-modal (region-text) and intra-modal (region-region) alignments. This multimodal degradation is a unique challenge that prior quantization methods for closed-vocabulary detectors fail to resolve. To overcome this, we propose Quantization-Aware Training with Multimodal Alignment (QATMA), the first multimodal-aware and architecture-agnostic QAT framework tailored for OVOD. QATMA integrates two key components: (i) Curriculum QAT, which partitions the detector by functional roles and progressively expands the quantization scope to suppress error accumulation and ensure stable optimization; and (ii) Text-anchored Pairwise Similarity Distillation, which transfers both region-text and region-region alignments from a full-precision teacher model via pairwise cosine similarities in the joint embedding space. Experimental results on LVIS and COCO zero-shot benchmarks demonstrate that QATMA significantly outperforms existing QAT baselines under extremely low-bit settings, achieving gains of up to 4.3 and 7.6 AP, respectively. △ Less

Submitted 23 July, 2026; v1 submitted 6 March, 2026; originally announced March 2026.

Scrambler: Mixed Boolean Arithmetic Obfuscation Tool Using E-graph and Equality Expansion

Authors: Seoksu Lee, Sangjun An, Eun-Sun Cho

Abstract: We propose Scrambler, and e-graph-based MBA obfuscation tool using Equality Expansion to efficiently generate complex and diverse expressions with equivalence guaranteed by construction. Experiments show Scrambler improves existing tools in expressiveness and complexity. We propose Scrambler, and e-graph-based MBA obfuscation tool using Equality Expansion to efficiently generate complex and diverse expressions with equivalence guaranteed by construction. Experiments show Scrambler improves existing tools in expressiveness and complexity. △ Less

Submitted 6 March, 2026; v1 submitted 3 March, 2026; originally announced March 2026.

Comments: 4 pages, 1 figure, 1 table

A generalizable foundation model for intraoperative understanding across surgical procedures

Authors: Kanggil Park, Yongjun Jeon, Soyoung Lim, Seonmin Park, Jongmin Shin, Jung Yong Kim, Sehyeon An, Jinsoo Rhu, Jongman Kim, Gyu-Seong Choi, Namkee Oh, Kyu-Hwan Jung

Abstract: In minimally invasive surgery, clinical decisions depend on real-time visual interpretation, yet intraoperative perception varies substantially across surgeons and procedures. This variability limits consistent assessment, training, and the development of reliable artificial intelligence systems, as most surgical AI models are designed for narrowly defined tasks and do not generalize across proced… ▽ More In minimally invasive surgery, clinical decisions depend on real-time visual interpretation, yet intraoperative perception varies substantially across surgeons and procedures. This variability limits consistent assessment, training, and the development of reliable artificial intelligence systems, as most surgical AI models are designed for narrowly defined tasks and do not generalize across procedures or institutions. Here we introduce ZEN, a generalizable foundation model for intraoperative surgical video understanding trained on more than 4 million frames from over 21 procedures using a self-supervised multi-teacher distillation framework. We curated a large and diverse dataset and systematically evaluated multiple representation learning strategies within a unified benchmark. Across 20 downstream tasks and full fine-tuning, frozen-backbone, few-shot and zero-shot settings, ZEN consistently outperforms existing surgical foundation models and demonstrates robust cross-procedure generalization. These results suggest a step toward unified representations for surgical scene understanding and support future applications in intraoperative assistance and surgical training assessment. △ Less

Submitted 14 February, 2026; originally announced February 2026.

LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens

Authors: Zekun Li, Sizhe An, Chengcheng Tang, Chuan Guo, Ivan Shugurov, Linguang Zhang, Amy Zhao, Srinath Sridhar, Lingling Tao, Abhay Mittal

Abstract: Recent progress in large models has led to significant advances in unified multimodal generation and understanding. However, the development of models that unify motion-language generation and understanding remains largely underexplored. Existing approaches often fine-tune large language models (LLMs) on paired motion-text data, which can result in catastrophic forgetting of linguistic capabilitie… ▽ More Recent progress in large models has led to significant advances in unified multimodal generation and understanding. However, the development of models that unify motion-language generation and understanding remains largely underexplored. Existing approaches often fine-tune large language models (LLMs) on paired motion-text data, which can result in catastrophic forgetting of linguistic capabilities due to the limited scale of available text-motion pairs. Furthermore, prior methods typically convert motion into discrete representations via quantization to integrate with language models, introducing substantial jitter artifacts from discrete tokenization. To address these challenges, we propose LLaMo, a unified framework that extends pretrained LLMs through a modality-specific Mixture-of-Transformers (MoT) architecture. This design inherently preserves the language understanding of the base model while enabling scalable multimodal adaptation. We encode human motion into a causal continuous latent space and maintain the next-token prediction paradigm in the decoder-only backbone through a lightweight flow-matching head, allowing for streaming motion generation in real-time (>30 FPS). Leveraging the comprehensive language understanding of pretrained LLMs and large-scale motion-text pretraining, our experiments demonstrate that LLaMo achieves high-fidelity text-to-motion generation and motion-to-text captioning in general settings, especially zero-shot motion generation, marking a significant step towards a general unified motion-language large model. △ Less

Submitted 16 April, 2026; v1 submitted 12 February, 2026; originally announced February 2026.

Comments: Project page: https://kunkun0w0.github.io/project/LLaMo/

TG-Field: Geometry-Aware Radiative Gaussian Fields for Tomographic Reconstruction

Authors: Yuxiang Zhong, Jun Wei, Chaoqi Chen, Senyou An, Hui Huang

Abstract: 3D Gaussian Splatting (3DGS) has revolutionized 3D scene representation with superior efficiency and quality. While recent adaptations for computed tomography (CT) show promise, they struggle with severe artifacts under highly sparse-view projections and dynamic motions. To address these challenges, we propose Tomographic Geometry Field (TG-Field), a geometry-aware Gaussian deformation framework t… ▽ More 3D Gaussian Splatting (3DGS) has revolutionized 3D scene representation with superior efficiency and quality. While recent adaptations for computed tomography (CT) show promise, they struggle with severe artifacts under highly sparse-view projections and dynamic motions. To address these challenges, we propose Tomographic Geometry Field (TG-Field), a geometry-aware Gaussian deformation framework tailored for both static and dynamic CT reconstruction. A multi-resolution hash encoder is employed to capture local spatial priors, regularizing primitive parameters under ultra-sparse settings. We further extend the framework to dynamic reconstruction by introducing time-conditioned representations and a spatiotemporal attention block to adaptively aggregate features, thereby resolving spatiotemporal ambiguities and enforcing temporal coherence. In addition, a motion-flow network models fine-grained respiratory motion to track local anatomical deformations. Extensive experiments on synthetic and real-world datasets demonstrate that TG-Field consistently outperforms existing methods, achieving state-of-the-art reconstruction accuracy under highly sparse-view conditions. △ Less

Submitted 12 February, 2026; originally announced February 2026.

Comments: Accepted to AAAI 2026. Project page: https://vcc.tech/research/2026/TG-Field

GFlowPO: Generative Flow Network as a Language Model Prompt Optimizer

Authors: Junmo Cho, Suhan Kim, Sangjune An, Minsu Kim, Dong Bok Lee, Heejun Lee, Sung Ju Hwang, Hae Beom Lee

Abstract: Finding effective prompts for language models (LMs) is critical yet notoriously difficult: the prompt space is combinatorially large, rewards are sparse due to expensive target-LM evaluation. Yet, existing RL-based prompt optimizers often rely on on-policy updates and a meta-prompt sampled from a fixed distribution, leading to poor sample efficiency. We propose GFlowPO, a probabilistic prompt opti… ▽ More Finding effective prompts for language models (LMs) is critical yet notoriously difficult: the prompt space is combinatorially large, rewards are sparse due to expensive target-LM evaluation. Yet, existing RL-based prompt optimizers often rely on on-policy updates and a meta-prompt sampled from a fixed distribution, leading to poor sample efficiency. We propose GFlowPO, a probabilistic prompt optimization framework that casts prompt search as a posterior inference problem over latent prompts regularized by a meta-prompted reference-LM prior. In the first step, we fine-tune a lightweight prompt-LM with an off-policy Generative Flow Network (GFlowNet) objective, using a replay-based training policy that reuses past prompt evaluations to enable sample-efficient exploration. In the second step, we introduce Dynamic Memory Update (DMU), a training-free mechanism that updates the meta-prompt by injecting both (i) diverse prompts from a replay buffer and (ii) top-performing prompts from a small priority queue, thereby progressively concentrating the search process on high-reward regions. Across few-shot text classification, instruction induction benchmarks, and question answering tasks, GFlowPO consistently outperforms recent discrete prompt optimization baselines. △ Less

Submitted 3 February, 2026; originally announced February 2026.

GraFine: Retrieval-Time Refinement for Efficient Graph RAG over Corpus Graphs

Authors: Seonho An, Chaejeong Hyun, Min-Soo Kim

Abstract: Graph RAG on corpus graphs enhances retrieval by leveraging intermediate node content as contextual clues to uncover unretrieved oracle nodes. However, existing methods suffer from two critical blind spots, namely semantically blind graph expansion and topology blind pruning, or else rely on prohibitively slow retrieval and generation interleaving. To address this, we formalize these limitations t… ▽ More Graph RAG on corpus graphs enhances retrieval by leveraging intermediate node content as contextual clues to uncover unretrieved oracle nodes. However, existing methods suffer from two critical blind spots, namely semantically blind graph expansion and topology blind pruning, or else rely on prohibitively slow retrieval and generation interleaving. To address this, we formalize these limitations through an operational taxonomy and propose a retriever design that couples semantics-aware adding with graph-aware pruning under efficiency constraints. We instantiate this design as GraFine, which alternates between two refinement stages: Semantic Proximity eXpansion (SPX) for semantics-aware node addition, and a Graph Smoothing Reranker (GSR) for graph-aware pruning. Experiments on reference networks and text-rich knowledge graphs show that GraFine improves retrieval accuracy and generation quality while maintaining time-efficiency. Furthermore, we introduce Topological Recall (TR), a metric that quantifies the topological proximity between retrieved and oracle nodes. Our analysis using TR confirms that GraFine more effectively steers refinement toward undiscovered oracle nodes by leveraging intermediate contextual clues. Our code is available at this link: https://github.com/asmath472/GraFine. △ Less

Submitted 11 August, 2026; v1 submitted 26 January, 2026; originally announced January 2026.

Comments: CIKM 2026

ACM Class: H.3.3; I.2.7

LongCat-Flash-Thinking-2601 Technical Report

Authors: Meituan LongCat Team, Anchun Gui, Bei Li, Bingyang Tao, Bole Zhou, Borun Chen, Chao Zhang, Chao Zhang, Chen Gao, Chen Zhang, Chengcheng Han, Chenhui Yang, Chuyu Zhang, Cong Chen, Cunguang Wang, Daoru Pan, Defei Bu, Dengchang Zhao, Di Xiu, Dishan Liu, Dongyu Ru, Dunwei Tu, Fan Wu, Fengcheng Yuan, Fengcun Li , et al. (141 additional authors not shown)

Abstract: We introduce LongCat-Flash-Thinking-2601, a 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model with superior agentic reasoning capability. LongCat-Flash-Thinking-2601 achieves state-of-the-art performance among open-source models on a wide range of agentic benchmarks, including agentic search, agentic tool use, and tool-integrated reasoning. Beyond benchmark performance, th… ▽ More We introduce LongCat-Flash-Thinking-2601, a 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model with superior agentic reasoning capability. LongCat-Flash-Thinking-2601 achieves state-of-the-art performance among open-source models on a wide range of agentic benchmarks, including agentic search, agentic tool use, and tool-integrated reasoning. Beyond benchmark performance, the model demonstrates strong generalization to complex tool interactions and robust behavior under noisy real-world environments. Its advanced capability stems from a unified training framework that combines domain-parallel expert training with subsequent fusion, together with an end-to-end co-design of data construction, environments, algorithms, and infrastructure spanning from pre-training to post-training. In particular, the model's strong generalization capability in complex tool-use are driven by our in-depth exploration of environment scaling and principled task construction. To optimize long-tailed, skewed generation and multi-turn agentic interactions, and to enable stable training across over 10,000 environments spanning more than 20 domains, we systematically extend our asynchronous reinforcement learning framework, DORA, for stable and efficient large-scale multi-environment training. Furthermore, recognizing that real-world tasks are inherently noisy, we conduct a systematic analysis and decomposition of real-world noise patterns, and design targeted training procedures to explicitly incorporate such imperfections into the training process, resulting in improved robustness for real-world applications. To further enhance performance on complex reasoning tasks, we introduce a Heavy Thinking mode that enables effective test-time scaling by jointly expanding reasoning depth and width through intensive parallel thinking. △ Less

Submitted 1 February, 2026; v1 submitted 23 January, 2026; originally announced January 2026.

Static Detection of Core Structures in Tigress Virtualization-Based Obfuscation Using an LLVM Pass

Authors: Sangjun An, Seoksu Lee, Eun-Sun Cho

Abstract: Malware often uses obfuscation to hinder security analysis. Among these techniques, virtualization-based obfuscation is particularly strong because it protects programs by translating original instructions into attacker-defined virtual machine (VM) bytecode, producing long and complex code that is difficult to analyze and deobfuscate. This paper aims to identify the structural components of virtua… ▽ More Malware often uses obfuscation to hinder security analysis. Among these techniques, virtualization-based obfuscation is particularly strong because it protects programs by translating original instructions into attacker-defined virtual machine (VM) bytecode, producing long and complex code that is difficult to analyze and deobfuscate. This paper aims to identify the structural components of virtualization-based obfuscation through static analysis. By examining the execution model of obfuscated code, we define and detect the key elements required for deobfuscation-namely the dispatch routine, handler blocks, and the VM region-using LLVM IR. Experimental results show that, in the absence of compiler optimizations, the proposed LLVM Pass successfully detects all core structures across major virtualization options, including switch, direct, and indirect modes. △ Less

Submitted 22 January, 2026; v1 submitted 19 January, 2026; originally announced January 2026.

Comments: 7 pages, 7figures, An extended version of this work has been submitted to the Journal of KIISC

NC-Bench: An LLM Benchmark for Evaluating Conversational Competence

Authors: Robert J. Moore, Sungeun An, Farhan Ahmed, Jay Pankaj Gala

Abstract: The Natural Conversation Benchmark (NC-Bench) introduces a new approach to evaluating the general conversational competence of large language models (LLMs). Unlike prior benchmarks that focus on the content of model behavior, NC-Bench focuses on the form and structure of natural conversation. Grounded in the IBM Natural Conversation Framework (NCF), NC-Bench comprises three distinct sets: (1) the… ▽ More The Natural Conversation Benchmark (NC-Bench) introduces a new approach to evaluating the general conversational competence of large language models (LLMs). Unlike prior benchmarks that focus on the content of model behavior, NC-Bench focuses on the form and structure of natural conversation. Grounded in the IBM Natural Conversation Framework (NCF), NC-Bench comprises three distinct sets: (1) the basic set evaluates fundamental sequence management practices, such as answering inquiries, repairing responses, and closing conversational pairs; (2) the retrieval-augmented generation (RAG) set applies the same sequence management patterns as the first set but incorporates information-seeking via RAG; (3) the complex request set extends to requests involving more intricate sequence management patterns. Each set tests a model's ability to produce contextually appropriate conversational actions in response to characteristic interaction patterns. Initial evaluations across six open-source models and 14 interaction patterns show that models perform well on basic answering tasks, struggle more with repair tasks (especially repeat), have mixed performance on closing sequences, and find complex multi-turn requests most challenging. By operationalizing fundamental principles of human conversation, NC-Bench provides a lightweight, extensible, and theory-grounded framework for assessing and improving the conversational abilities of LLMs beyond topical or task-specific benchmarks. △ Less

Submitted 7 March, 2026; v1 submitted 9 January, 2026; originally announced January 2026.

Comments: 8 pages, 1 figure, 2 tables

Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models

Authors: Junru Lu, Jiarui Qin, Lingfeng Qiao, Yinghui Li, Xinyi Dai, Bo Ke, Jianfeng He, Ruizhi Qiao, Di Yin, Xing Sun, Yunsheng Wu, Yinsong Liu, Shuangyin Liu, Mingkong Tang, Haodong Lin, Jiayi Kuang, Fanxu Meng, Xiaojuan Tang, Yunjia Xi, Junjie Huang, Haotong Yang, Zhenyi Shen, Yangning Li, Qianwen Zhang, Yifei Yu , et al. (13 additional authors not shown)

Abstract: We introduce Youtu-LLM, a lightweight yet powerful language model that harmonizes high computational efficiency with native agentic intelligence. Unlike typical small models that rely on distillation, Youtu-LLM (1.96B) is pre-trained from scratch to systematically cultivate reasoning and planning capabilities. The key technical advancements are as follows: (1) Compact Architecture with Long-Contex… ▽ More We introduce Youtu-LLM, a lightweight yet powerful language model that harmonizes high computational efficiency with native agentic intelligence. Unlike typical small models that rely on distillation, Youtu-LLM (1.96B) is pre-trained from scratch to systematically cultivate reasoning and planning capabilities. The key technical advancements are as follows: (1) Compact Architecture with Long-Context Support: Built on a dense Multi-Latent Attention (MLA) architecture with a novel STEM-oriented vocabulary, Youtu-LLM supports a 128k context window. This design enables robust long-context reasoning and state tracking within a minimal memory footprint, making it ideal for long-horizon agent and reasoning tasks. (2) Principled "Commonsense-STEM-Agent" Curriculum: We curated a massive corpus of approximately 11T tokens and implemented a multi-stage training strategy. By progressively shifting the pre-training data distribution from general commonsense to complex STEM and agentic tasks, we ensure the model acquires deep cognitive abilities rather than superficial alignment. (3) Scalable Agentic Mid-training: Specifically for the agentic mid-training, we employ diverse data construction schemes to synthesize rich and varied trajectories across math, coding, and tool-use domains. This high-quality data enables the model to internalize planning and reflection behaviors effectively. Extensive evaluations show that Youtu-LLM sets a new state-of-the-art for sub-2B LLMs. On general benchmarks, it achieves competitive performance against larger models, while on agent-specific tasks, it significantly surpasses existing SOTA baselines, demonstrating that lightweight models can possess strong intrinsic agentic capabilities. △ Less

Submitted 4 January, 2026; v1 submitted 30 December, 2025; originally announced December 2025.

Comments: 57 pages, 26 figures

LogosQ: A High-Performance and Type-Safe Quantum Computing Library in Rust

Authors: Shiwen An, Jiayi Wang, Konstantinos Slavakis

Abstract: Developing robust and high performance quantum software is challenging due to the dynamic nature of existing Python-based frameworks, which often suffer from runtime errors and scalability bottlenecks. In this work, we present LogosQ, a high performance backend agnostic quantum computing library implemented in Rust that enforces correctness through compile time type safety. Unlike existing tools,… ▽ More Developing robust and high performance quantum software is challenging due to the dynamic nature of existing Python-based frameworks, which often suffer from runtime errors and scalability bottlenecks. In this work, we present LogosQ, a high performance backend agnostic quantum computing library implemented in Rust that enforces correctness through compile time type safety. Unlike existing tools, LogosQ leverages Rust static analysis to eliminate entire classes of runtime errors, particularly in parameter-shift rule gradient computations for variational algorithms. We introduce novel optimization techniques, including direct state-vector manipulation, adaptive parallel processing, and an FFT optimized Quantum Fourier Transform, which collectively deliver speedups of up to 900 times for state preparation (QFT) and 2 to 5 times for variational workloads over Python frameworks (PennyLane, Qiskit), 6 to 22 times over Julia implementations (Yao), and competitive performance with Q sharp. Beyond performance, we validate numerical stability through variational quantum eigensolver (VQE) experiments on molecular hydrogen and XYZ Heisenberg models, achieving chemical accuracy even in edge cases where other libraries fail. By combining the safety of systems programming with advanced circuit optimization, LogosQ establishes a new standard for reliable and efficient quantum simulation. △ Less

Submitted 30 December, 2025; v1 submitted 28 December, 2025; originally announced December 2025.

Comments: https://github.com/zazabap/LogosQ https://github.com/zazabap/LogosQBenchmarks https://crates.io/crates/logosq https://logosqbook.vercel.app/

Towards Fine-Tuning-Based Site Calibration for Knowledge-Guided Machine Learning: A Summary of Results

Authors: Ruolei Zeng, Arun Sharma, Shuai An, Mingzhou Yang, Shengya Zhang, Licheng Liu, David Mulla, Shashi Shekhar

Abstract: Accurate and cost-effective quantification of the agroecosystem carbon cycle at decision-relevant scales is essential for climate mitigation and sustainable agriculture. However, both transfer learning and the exploitation of spatial variability in this field are challenging, as they involve heterogeneous data and complex cross-scale dependencies. Conventional approaches often rely on location-ind… ▽ More Accurate and cost-effective quantification of the agroecosystem carbon cycle at decision-relevant scales is essential for climate mitigation and sustainable agriculture. However, both transfer learning and the exploitation of spatial variability in this field are challenging, as they involve heterogeneous data and complex cross-scale dependencies. Conventional approaches often rely on location-independent parameterizations and independent training, underutilizing transfer learning and spatial heterogeneity in the inputs, and limiting their applicability in regions with substantial variability. We propose FTBSC-KGML (Fine-Tuning-Based Site Calibration-Knowledge-Guided Machine Learning), a pretraining- and fine-tuning-based, spatial-variability-aware, and knowledge-guided machine learning framework that augments KGML-ag with a pretraining-fine-tuning process and site-specific parameters. Using a pretraining-fine-tuning process with remote-sensing GPP, climate, and soil covariates collected across multiple midwestern sites, FTBSC-KGML estimates land emissions while leveraging transfer learning and spatial heterogeneity. A key component is a spatial-heterogeneity-aware transfer-learning scheme, which is a globally pretrained model that is fine-tuned at each state or site to learn place-aware representations, thereby improving local accuracy under limited data without sacrificing interpretability. Empirically, FTBSC-KGML achieves lower validation error and greater consistency in explanatory power than a purely global model, thereby better capturing spatial variability across states. This work extends the prior SDSA-KGML framework. △ Less

Submitted 17 December, 2025; originally announced December 2025.