Showing 1–50 of 713 results for author: Hwang, J

PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents

Authors: Seongjae Kang, Taehyung Yu, Sung Ju Hwang

Abstract: Customer-service LLM agents must follow organizational policy when acting on a user's behalf. Compliance failures arise from either forbidden actions, such as granting an ineligible change, or omitted procedural requirements, such as identification or confirmation. Runtime safeguards can intervene on risky actions, but action-local checks do not guide an agent through a multi-step procedure. Workf… ▽ More Customer-service LLM agents must follow organizational policy when acting on a user's behalf. Compliance failures arise from either forbidden actions, such as granting an ineligible change, or omitted procedural requirements, such as identification or confirmation. Runtime safeguards can intervene on risky actions, but action-local checks do not guide an agent through a multi-step procedure. Workflow-following systems support prescribed process execution, but primarily target workflow completion rather than safeguarding agent behavior. PolicyGuide instead compiles each domain policy into a workflow graph and invokes a proactive verifier at user-turn boundaries. From persisted graph state, the verifier reconciles open requests and returns step-specific remediation along a policy-compliant path. Across the $τ^2$-bench airline, retail, and telecom domains with a GPT-5.4 agent and verifier, PolicyGuide raises mean $\mathrm{Pass}^4$ from $0.42$ to $0.62$, with the largest gain on telecom ($0.19$ to $0.61$), the most workflow-structured domain. The same workflows transfer to Claude Sonnet 4.6 and Gemini 2.5 Pro agents. Complementary evaluations find the lowest observed attack-success rate under adversarial users and the strongest procedural compliance in an author-designed workflow-level validation. △ Less

Submitted 20 August, 2026; originally announced August 2026.

Comments: 26 pages, 15 figures, including appendices

ACM Class: I.2.11; I.2.7

Memory Tree Guided Key Frame Querying for Efficient 3D Question Answering

Authors: Hsiang-Wei Huang, Fu-Chen Chen, Li-Wu Tsao, Cheng-Han Lee, Che-Chun Su, Lu Xia, Ronghui Peng, Jenq-Neng Hwang, Min Sun, Cheng-Hao Kuo

Abstract: Answering questions accurately and efficiently in embodied scenarios presents significant challenges due to limited computational and memory resources for Vision Language Model (VLM) inference. Existing methods adopt visual search key frame retrieval method to select critical question-related key frames for VLM input. However, visual search methods are inefficient because they require visual searc… ▽ More Answering questions accurately and efficiently in embodied scenarios presents significant challenges due to limited computational and memory resources for Vision Language Model (VLM) inference. Existing methods adopt visual search key frame retrieval method to select critical question-related key frames for VLM input. However, visual search methods are inefficient because they require visual search among thousands of video frames for each individual user query. In this work, we propose a memory tree guided key frame selection paradigm for efficient 3D question answering in embodied scenarios. Our method leverages a compact and reusable 3D scene representation, termed MemTree3D, which supports real-time online construction leveraging camera 6-DoF poses. MemTree3D captures multi-level 3D scene information, enabling a Large Language Model to efficiently query and retrieve question-relevant key frames through our scoring-based frame selection without reprocessing the entire video stream. On OpenEQA, our method improves the LLM-Match of GPT-4o by 17.4%, LLaVA-OneVision-7B by 5.8%, outperforms existing visual search methods. Our code is available at https://github.com/hsiangwei0903/MemTree3D △ Less

Submitted 18 August, 2026; originally announced August 2026.

Comments: ECCV 2026

Through Van Gogh's Eyes: Global Style Transfer with Diffusion Model

Authors: Jeongha Lee, Yujin Kim, Ghazanfar Ali, Suhyun Kim, Jae-In Hwang

Abstract: Artistic image synthesis aims to recreate the expressive visual identity of a target artist, yet existing methods often fail to capture an artist's global style. Conventional style transfer methods transfer the style of one or a few reference artworks to a content image in a One-to-One manner, making them effective for artwork-level stylization but limited in representing the broader stylistic dis… ▽ More Artistic image synthesis aims to recreate the expressive visual identity of a target artist, yet existing methods often fail to capture an artist's global style. Conventional style transfer methods transfer the style of one or a few reference artworks to a content image in a One-to-One manner, making them effective for artwork-level stylization but limited in representing the broader stylistic distribution of an artist. Text-to-image diffusion models conditioned on artist names, such as '~ in Van Gogh style', offer greater flexibility, but they often suffer from text-induced bias and reproduce patterns from only a few iconic works. To address these limitations, we introduce Global Style Transfer (GST), an artistic image synthesis paradigm, in a Many-to-One manner, that aggregates multiple artworks from a target artist and transfers their shared global style to a single content image. For GST, we propose Global Style Guidance (GSG), which learns a residual global style offset in the intermediate feature space, or h-space, of a diffusion model under a fixed prompt. By learning artist-level style semantics purely from visual statistics, GSG mitigates text-dependent artistic bias. We further propose Content Alignment Guidance (CAG), a training-free perceptual guidance mechanism that preserves the semantic structure of the content image while allowing artist-specific geometric deformation. Experiments on WikiArt demonstrate that GST achieves superior stylistic fidelity, content preservation, and output diversity compared to existing style transfer and diffusion-based artistic synthesis methods. △ Less

Submitted 12 August, 2026; v1 submitted 11 August, 2026; originally announced August 2026.

Comments: Published at ECCV 2026

A 5/4 bound for graphic $s$-$t$ path TSP on subcubic graphs

Authors: Junho Hwang

Abstract: We study the graphic $s$-$t$ path TSP on subcubic graphs (maximum degree 3): given two vertices $s,t$, find a shortest walk from $s$ to $t$ that visits every vertex. Our main result is that the optimal $5/4$ coefficient is attained for every terminal pair -- including the difficult case where deleting both $s$ and $t$ disconnects the graph. Concretely, every pair of distinct vertices $s,t$ in a si… ▽ More We study the graphic $s$-$t$ path TSP on subcubic graphs (maximum degree 3): given two vertices $s,t$, find a shortest walk from $s$ to $t$ that visits every vertex. Our main result is that the optimal $5/4$ coefficient is attained for every terminal pair -- including the difficult case where deleting both $s$ and $t$ disconnects the graph. Concretely, every pair of distinct vertices $s,t$ in a simple 2-connected subcubic graph $G$ admits a spanning $s$-$t$ walk of length at most $\lfloor(5n+n_2(G))/4\rfloor-1$, where $n=|V(G)|$ and $n_2(G)$ is the number of degree-2 vertices; the asymptotic coefficient $5/4$ cannot be improved, and a simple $O(n^2)$ algorithm finds a walk of length at most $\lfloor(5n+n_2(G))/4\rfloor$. An edge-rooted even-cover theorem of Wigal, Yoo, and Yu, combined with a short conversion lemma proved here, gives a bound of this form only when $s$ and $t$ are the two endpoints of a given edge; we remove that adjacency restriction. For cubic graphs ($n_2(G)=0$) the bound reads $\lfloor 5n/4\rfloor-1$, to our knowledge the first $5/4$ bound for cubic path TSP proved directly rather than through the general path-to-tour reduction. △ Less

Submitted 11 August, 2026; originally announced August 2026.

Comments: 12 pages, 2 figures. To appear in the proceedings of WAOA 2026 (Springer LNCS)

MSC Class: 68W25; 05C38; 05C85; 90C27 ACM Class: F.2.2; G.2.2

Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory

Authors: Taeil Kim, Kangsan Kim, Sung Ju Hwang

Abstract: Memory systems have shown promise for improving agent performance, but their potential remains largely unexplored for small language models, which struggle to generate sufficient successful trajectories on their own. We propose Agent Memory Distillation (AMD), a training-free framework that transfers structured knowledge from a large teacher agent to a small student agent through hierarchical memo… ▽ More Memory systems have shown promise for improving agent performance, but their potential remains largely unexplored for small language models, which struggle to generate sufficient successful trajectories on their own. We propose Agent Memory Distillation (AMD), a training-free framework that transfers structured knowledge from a large teacher agent to a small student agent through hierarchical memory. AMD constructs three complementary memory types from successful teacher trajectories: Workflow memory encodes task-level strategies, Subtask memory provides concrete behavioral examples at an intermediate granularity, and Function memory captures per-function calling conventions and common pitfalls. Workflow and Subtask memories are injected proactively at the start of each task, while Function memory is retrieved reactively upon tool-calling errors. We evaluate AMD on three tool-use benchmarks using four student models (4B-8B parameters) with GPT-5-mini as the teacher, achieving average accuracy gains of 27.2%p, 11.2%p, and 3.4%p on AppWorld, BFCL V3, and ToolSandbox, while consistently outperforming existing memory-based baselines. Further analysis shows that Subtask memory contributes the largest gains, teacher effectiveness depends on both teacher capability and student compatibility, and 4B-sized students benefit most from AMD. △ Less

Submitted 7 August, 2026; originally announced August 2026.

Comments: Under review

On-Policy Delta Distillation for Multilingual Math Reasoning

Authors: Byeongho Heo, Jaehui Hwang, Sangdoo Yun, Dongyoon Han

Abstract: On-Policy Distillation (OPD) is emerging as a promising alternative to reinforcement learning for LLM post-training, yet its effectiveness in multilingual settings remains underexplored. We study OPD and its advanced variant, On-Policy Delta Distillation (OPD$^2$), for mathematical reasoning in English, Korean, and Japanese. OPD$^2$ improves OPD by using the probability gap between a post-trained… ▽ More On-Policy Distillation (OPD) is emerging as a promising alternative to reinforcement learning for LLM post-training, yet its effectiveness in multilingual settings remains underexplored. We study OPD and its advanced variant, On-Policy Delta Distillation (OPD$^2$), for mathematical reasoning in English, Korean, and Japanese. OPD$^2$ improves OPD by using the probability gap between a post-trained teacher and its base model as the learning signal. Experiments with Qwen3 show that OPD$^2$ consistently outperforms the original OPD, with particularly strong improvements in Korean and Japanese, and generally narrows the English-Korean performance gap. We further find that English-only OPD can also increase performance for Korean and Japanese, but often shifts the responses toward English, highlighting the importance of multilingual data to preserving target-language responses. △ Less

Submitted 6 August, 2026; originally announced August 2026.

Comments: 9 pages, 3 figures, 10 tables

K-EXAONE 2.0 Technical Report

Authors: Eunbi Choi, Kibong Choi, Sehyun Chun, Seokhee Hong, Junwon Hwang, Hyojin Jeon, Ahra Jo, Hyunjik Jo, Yeonsik Jo, Minhyeok Jung, Doyoung Kim, Heegyu Kim, Joonkee Kim, Seonghwan Kim, Soyeon Kim, Sunkyoung Kim, Yireun Kim, Yongil Kim, Byungoh Ko, Changhun Lee, Dohaeng Lee, Haeju Lee, Jinsik Lee, Kyungmin Lee, Minwoo Lee , et al. (52 additional authors not shown)

Abstract: This technical report presents K-EXAONE 2.0, an open-weight multilingual foundation model developed by LG AI Research as a step in our effort toward global frontier-scale foundation models. Rather than training from scratch, we upcycle K-EXAONE and expand its architecture, yielding a Mixture-of-Experts (MoE) model with 750B total parameters and approximately 37B activated per token---more than thr… ▽ More This technical report presents K-EXAONE 2.0, an open-weight multilingual foundation model developed by LG AI Research as a step in our effort toward global frontier-scale foundation models. Rather than training from scratch, we upcycle K-EXAONE and expand its architecture, yielding a Mixture-of-Experts (MoE) model with 750B total parameters and approximately 37B activated per token---more than three times the capacity of its predecessor. K-EXAONE 2.0 supports context lengths of up to 256K tokens and expands multilingual coverage from six to ten languages. Its training pipeline combines continual pre-training, difficulty-focused mid-training, and post-training to strengthen reasoning, agentic coding, multilingual capability, and safety grounded in Korean sociocultural contexts. Across nine evaluation categories selected to reflect the conditions of practical use, K-EXAONE 2.0 improves over K-EXAONE and remains competitive with open-weight models, showing its largest gains in agentic coding and long-context understanding and its clearest strengths in long-context retrieval and safety. Released under the Apache 2.0 license, K-EXAONE 2.0 enables the wider AI ecosystem to evaluate, deploy, adapt, and build upon it, while marking the beginning---rather than the endpoint---of our challenge toward the global frontier. △ Less

Submitted 5 August, 2026; originally announced August 2026.

Learning from Adversity: Semantic-Aware Mask Refinement through Adversarial Perturbation

Authors: Beomyoung Kim, Sung Ju Hwang

Abstract: Despite significant advances in image segmentation, even state-of-the-art models produce masks with imperfect boundaries, semantic inconsistencies, and structural errors. Mask refinement addresses these limitations, yet current approaches rely on simplistic synthetic noise that fails to capture the complex error patterns of real segmentation models. We introduce Phoenix, a novel framework that lev… ▽ More Despite significant advances in image segmentation, even state-of-the-art models produce masks with imperfect boundaries, semantic inconsistencies, and structural errors. Mask refinement addresses these limitations, yet current approaches rely on simplistic synthetic noise that fails to capture the complex error patterns of real segmentation models. We introduce Phoenix, a novel framework that leverages adversarial learning to generate semantically meaningful noise patterns and contrastive learning to model refinement relationships. Our approach consists of two key innovations: (1) Adversarial Mask Perturbation, which employs embedding attacks to create semantic-aware noise that mimics real segmentation errors, and (2) Contrastive Mask Refinement Learning, which establishes a tri-directional framework that ensures feature consistency within semantic regions while maintaining separation between classes. Experiments demonstrate that Phoenix significantly outperforms existing methods across diverse tasks, while consistently enhancing state-of-the-art segmentation models with substantial improvements. Our code and project page are publicly available at https://phoenix-eccv26.github.io. △ Less

Submitted 31 July, 2026; originally announced July 2026.

Comments: ECCV 2026

Convolutional Neural Shading for High-Quality 3D Reconstruction from Multi-View Images

Authors: Juheon Hwang, Taewan Kim, Heeseok Oh, Jiwoo Kang

Abstract: We propose a convolutional neural shading (CNS), a novel pipeline to reconstruct high-quality 3D shapes from multi-view images. Several recent studies have used neural radiance fields and other neural differentiable rendering methods to understand 3D geometry. However, these approaches rely on single-point geometric information, such as positions and normals of the surface, leading to a lack of de… ▽ More We propose a convolutional neural shading (CNS), a novel pipeline to reconstruct high-quality 3D shapes from multi-view images. Several recent studies have used neural radiance fields and other neural differentiable rendering methods to understand 3D geometry. However, these approaches rely on single-point geometric information, such as positions and normals of the surface, leading to a lack of detailed local geometry. Our approach addresses the inherent limitations of single-point information by leveraging a neural shader to capture variations even in dark and textureless regions with a convolutional neural shader, resulting in far more accurate geometry predictions. Additionally, our method mitigates surface irregularities at image boundaries by introducing a fine-detail displacement network, which utilizes spatial information of surface geometry and learns fine displacement details by correlating neighboring values in the rendering coordinates. Through extensive experiments, our proposed method has demonstrated significant quality improvements in the reconstructed shapes and rendered images over current state-of-the-art methods. △ Less

Submitted 30 July, 2026; originally announced July 2026.

Journal ref: Multimedia Systems, vol. 31, no. 4, pp. 296, July 2025

Collaborative Feature Aggregation for Face Super-Resolution and Robust Re-Identification

Authors: Juheon Hwang, Taewan Kim, Jiwoo Kang

Abstract: We propose a novel collaborative approach for face super-resolution (SR) and robust person re-identification from sequential or multi-view facial images. Traditional SR methods often suffer from blurring and distortion in faces recovered from poor-quality images due to low resolution. Image- and video-based facial SR methods using facial landmarks or segmentation also have similar challenges. To o… ▽ More We propose a novel collaborative approach for face super-resolution (SR) and robust person re-identification from sequential or multi-view facial images. Traditional SR methods often suffer from blurring and distortion in faces recovered from poor-quality images due to low resolution. Image- and video-based facial SR methods using facial landmarks or segmentation also have similar challenges. To overcome these limitations, we leverage multiple correlated facial observations, across time or viewpoints, by introducing a transformer-based collaborative feature aggregation method that unifies identity features from multi-sequence or multi-view data. This allows faces in multiple sequences of an individual to contribute to accurately estimating common facial features. Furthermore, we propose a cascade SR network to progressively restore the high-resolution image of the target's face with gradual facial feature unification. The unified identity representation is further utilized in person re-identification scenarios, enabling accurate matching even under severe image degradation. The exhaustive experimental results and comparisons show that our method outperforms other state-of-the-art methods, demonstrating consistent improvements in both face super-resolution and re-identification performance. Our work highlights the effectiveness of joint identity reconstruction and progressive image restoration from multiple facial inputs in enhancing downstream visual recognition tasks. △ Less

Submitted 30 July, 2026; originally announced July 2026.

Journal ref: Multimedia Systems, vol. 31, no. 5, pp. 341, Aug. 2025

ReCo: Reweighting GRPO Against Distributional Concentration

Authors: Junoh Park, Junseo Hwang, Wonguk Cho, Taesup Kim

Abstract: Group Relative Policy Optimization (GRPO) has become a standard reinforcement learning method for post-training language models. Recent work shows that GRPO can reduce the base model's reasoning capacity and underperform it in Pass@k when k is large, indicating reduced coverage of reasoning paths. We find that this reduction is associated with GRPO concentrating on responses that the base model al… ▽ More Group Relative Policy Optimization (GRPO) has become a standard reinforcement learning method for post-training language models. Recent work shows that GRPO can reduce the base model's reasoning capacity and underperform it in Pass@k when k is large, indicating reduced coverage of reasoning paths. We find that this reduction is associated with GRPO concentrating on responses that the base model already generates with high probability. We trace this concentration to two mechanisms in the GRPO update. At the response level, high-probability responses dominate the group gradient through repeated occurrence. At the token level, GRPO's importance ratio scales gradients, further reinforcing tokens that become more likely under the current policy. We propose ReCo, a reweighting method that addresses both effects. Response contributions are normalized by their expected occurrence within the rollout group, and the token-level importance ratio is replaced with a variance-based ratio that gives larger update scale to non-saturated decision points where alternative token choices remain plausible. Across Qwen2.5-Math-1.5B/7B and Llama-3.1-8B-Instruct on five mathematical reasoning benchmarks, ReCo improves Pass@k for large values of k and is comparable to GRPO for small values of k. △ Less

Submitted 29 July, 2026; originally announced July 2026.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding

Authors: Junsung Hwang

Abstract: Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read in full at every decode step. Attention keys are locally low-rank though globally high-rank: shared low-rank bases discard page-specific directions that a page's own compact basis retains. LOCKS gives every page its own spectral summary (resident, about a tenth the cache's size), reconstructs w… ▽ More Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read in full at every decode step. Attention keys are locally low-rank though globally high-rank: shared low-rank bases discard page-specific directions that a page's own compact basis retains. LOCKS gives every page its own spectral summary (resident, about a tenth the cache's size), reconstructs within-page logits, estimates each page's attention mass by log-sum-exp, and attends only the top pages; selection itself reads no candidate keys or values. Selecting on this summary alone stays within about a point of the full cache on long-document QA (LongBench-v1), tracks the read-every-key oracle on retrieval-dense RULER down to the smallest budgets, and shows its largest margins on long-form reasoning (AIME26, MATH-500), where baseline selectors collapse. At its shipped $2048$-token budget LOCKS matches FullKV aggregate quality at $100$K$+$ context while attending about $2\%$ of the tokens, and halves per-token decode latency ($2.0\times$ at $1$M tokens) against dense attention. LOCKS ships as a drop-in plugin for unmodified vLLM, with batched decode running in full CUDA graphs. △ Less

Submitted 27 July, 2026; originally announced July 2026.

On-Policy Delta Distillation

Authors: Byeongho Heo, Jaehui Hwang, Sangdoo Yun, Dongyoon Han

Abstract: On-policy distillation is an alternative post-training method in reinforcement learning that alleviates the constraints imposed by reward models by providing token-level supervision from a teacher model. Although on-policy distillation has been studied and applied across various settings, its fundamental design remains underexplored. In this paper, we introduce a new distillation reward, termed th… ▽ More On-policy distillation is an alternative post-training method in reinforcement learning that alleviates the constraints imposed by reward models by providing token-level supervision from a teacher model. Although on-policy distillation has been studied and applied across various settings, its fundamental design remains underexplored. In this paper, we introduce a new distillation reward, termed the delta signal, instead of directly imitating the teacher's output distribution. The delta signal is defined as the difference between the teacher model and its base model prior to instruction tuning for reasoning capability. It therefore captures the changes induced by reasoning tuning and provides a more direct signal for transferring reasoning capabilities. Using extensive empirical evidence, we show that the delta signal substantially improves on-policy distillation and refer to the new distillation method as On-Policy Delta Distillation (OPD$^2$). Experiments across mathematics, science, and code-reasoning benchmarks demonstrate that OPD$^2$ consistently outperforms conventional on-policy distillation, enabling reasoning LLMs to achieve strong performance with only a short post-training period. Code will be available at https://github.com/naver-ai/opd2 △ Less

Submitted 16 July, 2026; originally announced July 2026.

Comments: 19 pages, 4 figures, 12 tables

Controlling Motion Transfer in Diffusion Transformers via Attention Heads

Authors: Sunyoung Jung, Jiwoo Park, Yoonseok Choi, Kyobin Choo, Ming-Hsuan Yang, Seong Jae Hwang

Abstract: Diffusion Transformers (DiTs) have advanced video generation with high-quality, temporally coherent results. However, extending them to motion transfer, which requires following reference motion while aligning with a target prompt, remains challenging due to limited understanding of motion and structure representations within DiTs. We analyze video DiTs at the attention-head level and identify dis… ▽ More Diffusion Transformers (DiTs) have advanced video generation with high-quality, temporally coherent results. However, extending them to motion transfer, which requires following reference motion while aligning with a target prompt, remains challenging due to limited understanding of motion and structure representations within DiTs. We analyze video DiTs at the attention-head level and identify distinct heads specialized for motion and spatial structure. Based on this insight, we propose a head-aware controllable motion transfer framework that requires no parameter updates. Our method refines motion cues from motion-specialized heads via semantic correspondence guidance and preserves structure through selective feature injection. This head-level control not only enables accurate motion transfer but also provides an interpretable foundation for controllable video generation with DiTs. △ Less

Submitted 13 July, 2026; originally announced July 2026.

Comments: Accepted to ECCV 2026, Project page: https://sunyj-hxppy.github.io/halo/

Semantic Hardness Is Not Visual Hardness: Sign-Aware Hard Negative Mining for Sign Language Retrieval

Authors: Junmyeong Lee, Chan Hur, ChangSu Choi, Sukmin Cho, Fitsum Gaim, Eui Jun Hwang, Hoyun Song, KyungTae Lim

Abstract: Sign Language Retrieval (SLRet) enables efficient access to sign language content but remains fragile in fine-grained scenarios where visually similar signs must be distinguished. We show that this limitation does not stem from model capacity, but from ineffective hard negative supervision. Specifically, we formulate fine-grained retrieval failures as a negative distribution mismatch: semantically… ▽ More Sign Language Retrieval (SLRet) enables efficient access to sign language content but remains fragile in fine-grained scenarios where visually similar signs must be distinguished. We show that this limitation does not stem from model capacity, but from ineffective hard negative supervision. Specifically, we formulate fine-grained retrieval failures as a negative distribution mismatch: semantically distinct yet visually confusable signs are rarely treated as hard negatives, while existing text-based mining strategies fail to capture such visual ambiguity. To address this issue, we propose Sign-Aware Hard Negative Mining (SAN), which constructs hard negatives based on visual confusability in the sign embedding space rather than linguistic similarity. Experiments on PHOENIX-2014T demonstrate that SAN substantially improves fine-grained retrieval performance while preserving coarse-grained accuracy, highlighting the importance of aligning negative supervision with visual ambiguity in sign language retrieval. △ Less

Submitted 10 July, 2026; originally announced July 2026.

Comments: Accepted to ACL 2026 main

Journal ref: Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026, pages 28262-28277

Real-Time LiDAR Gaussian Splatting SLAM

Authors: Seungjun Tak, Yewon Jeon, Jaeik Hwang, SukMin Hwang, Seongbo Ha, Hyeonwoo Yu

Abstract: We present a real-time LiDAR-based framework for Gaussian Splatting SLAM that tightly couples fast G-ICP registration with spherical rasterization-based dense mapping for large-scale sequences. Leveraging LiDAR geometry rather than appearance, we reuse tracking-estimated local covariances to initialize Gaussians with range-aware scales and to derive surface normals for geometry-aware map optimizat… ▽ More We present a real-time LiDAR-based framework for Gaussian Splatting SLAM that tightly couples fast G-ICP registration with spherical rasterization-based dense mapping for large-scale sequences. Leveraging LiDAR geometry rather than appearance, we reuse tracking-estimated local covariances to initialize Gaussians with range-aware scales and to derive surface normals for geometry-aware map optimization. We further introduce a covariance-derived geometry score that measures local complexity and drives pruning in planar regions and selective densification in structurally rich areas, while optimized Gaussians and LiDAR-specific confidence cues are fed back to improve tracking robustness. On the Newer College dataset, our method achieves an F-score of 86.78\% using purely online trajectories at real-time speed ($>$20 FPS), and additional experiments on other datasets confirm its stability and scalability. △ Less

Submitted 5 July, 2026; originally announced July 2026.

Comments: 18 pages, 5 figures

MSC Class: 68T40

OmniDS: Dual-Stream Context Fusion for Omnidirectional Depth from Fisheye Cameras

Authors: Chaesong Park, Jihyeon Hwang, Muyeol Sung, Jongwoo Lim

Abstract: Omnidirectional depth estimation from multi-fisheye camera rigs is complicated by visibility conflicts: wide baselines cause different cameras to observe different portions, or even different faces, of the same object, so aggregating their features into a unified equirectangular (ERP) representation under fixed projection produces ambiguous matching evidence near occlusion boundaries and thin stru… ▽ More Omnidirectional depth estimation from multi-fisheye camera rigs is complicated by visibility conflicts: wide baselines cause different cameras to observe different portions, or even different faces, of the same object, so aggregating their features into a unified equirectangular (ERP) representation under fixed projection produces ambiguous matching evidence near occlusion boundaries and thin structures. Although existing methods mitigate this by down-weighting unreliable views, they do not resolve the underlying discrepancy because context formation and cross-view fusion remain tied to rigid fisheye-to-ERP sampling. We present OmniDS, an iterative depth refinement framework that replaces rigid aggregation by combining dynamic context fusion with consensus-aware multi-view similarity. A dual-stream encoder pairs a lightweight CNN for geometric detail with a frozen DINOv3 for semantic priors; their features are reprojected into ERP space at each refinement step via learned view weighting and deformable cross-attention with geometric distortion bias. In parallel, a multi-view consensus volume captures global cross-camera agreement through group-wise correlation and feature variance, regularized by a 3D U-Net. For efficient deployment, we distill the dual-stream representation into a single MobileNet-based encoder. OmniDS achieves state-of-the-art performance on the OmniThings, OmniHouse, and Sunny benchmarks while maintaining competitive inference speed. Project page and codes are available at https://parkchaesong.github.io/omnids. △ Less

Submitted 3 July, 2026; originally announced July 2026.

Comments: 15 pages, 3 figures, 3 tables

QWERTY: Training-Free Motion Control via Query-Warped Video Diffusion Transformers

Authors: Kyobin Choo, Youngmin Kim, Hyunkyung Han, Geunrip Park, Chanyoung Kim, Sunyoung Jung, Seong Jae Hwang

Abstract: Video diffusion transformers (DiTs) generate high-fidelity and temporally coherent videos, yet motion control remains implicit, primarily relying on text prompts. As a result, achieving desired motion often requires extensive prompt engineering and repeated resampling. While fine-tuning models with additional spatial prompts (e.g., bounding boxes or point trajectories) enables explicit control, it… ▽ More Video diffusion transformers (DiTs) generate high-fidelity and temporally coherent videos, yet motion control remains implicit, primarily relying on text prompts. As a result, achieving desired motion often requires extensive prompt engineering and repeated resampling. While fine-tuning models with additional spatial prompts (e.g., bounding boxes or point trajectories) enables explicit control, it demands substantial data curation and computation, and may compromise the generative capabilities of pretrained models. Consequently, training-free motion control using such spatial prompts has been explored in U-Net-based video diffusion models, but remains largely unexplored for DiTs. We introduce QWERTY, a training-free framework that enables flexible motion control in pretrained image-to-video DiTs via user-defined object warping and optical flow. We carefully manipulate the 3D full attention of DiTs by warping the frame-invariant semantic subspace of queries. We find that the noise predicted by the query-warped DiT naturally guides the diffusion trajectory toward the desired motion, and further show that leveraging this noise as self-guidance for latent optimization improves control stability and visual quality. Experiments show that QWERTY achieves the most effective motion control among existing training-free approaches on a recent image-to-video DiT, with performance comparable to fine-tuning-based methods. △ Less

Submitted 2 July, 2026; originally announced July 2026.

Comments: 37 pages, 18 figures, accepted at the European Conference on Computer Vision (ECCV) 2026

ACM Class: I.4.9

PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents

Authors: Seongjae Kang, Taehyung Yu, Sung Ju Hwang

Abstract: LLM agents handle user requests on behalf of organizations through tool calls and must follow the company policies stated in their system prompts. Prior work approaches this as a safeguarding problem -- external checks that block non-compliant agent actions. We argue that policy adherence is a broader problem: real workflows unfold across many turns, require explicit user confirmation and prerequi… ▽ More LLM agents handle user requests on behalf of organizations through tool calls and must follow the company policies stated in their system prompts. Prior work approaches this as a safeguarding problem -- external checks that block non-compliant agent actions. We argue that policy adherence is a broader problem: real workflows unfold across many turns, require explicit user confirmation and prerequisite reads, and hinge on the content of the dialogue rather than on any single argument value. Meeting this bar requires (i) full conversation context, (ii) self-reasoning over the policy and the current dialogue, and (iii) conversation-specific remediation that guides the agent's next turn -- three capabilities that prior safeguard work has often underestimated. We introduce POLICYGUARD, a sub-agent verifier that shares the agent's view of the dialogue, reasons over the policy in context, and provides actionable feedback for the agent's next turn. On tau^2-BENCH airline across three vendors (GPT-5.4, Claude Sonnet 4.6, Gemini 2.5 Pro) with four trials per setting, POLICYGUARD improves PASS4 by +12.0 / +6.0 / +12.0 pp. Per-call analyses show POLICYGUARD achieves higher policy-violation recall while blocking roughly half as often as argument-level guards. △ Less

Submitted 28 June, 2026; originally announced June 2026.

Comments: 20 pages, 8 figures

MacroLens: A Multi-Task Benchmark for Contextual Financial Reasoning under Macroeconomic Scenarios

Authors: Patara Trirat, Jin Myung Kwak, Jay Heo, Heejun Lee, Sung Ju Hwang

Abstract: Financial decision-making is contextual: forecasting prices, valuing companies, and assessing event exposure weigh price history, accounting fundamentals, macroeconomic regime, and contemporaneous text. A benchmark over these four signals is hard to build because finance violates four assumptions of time-series evaluation: text must be gated by its publication date to prevent look-ahead, quarterly… ▽ More Financial decision-making is contextual: forecasting prices, valuing companies, and assessing event exposure weigh price history, accounting fundamentals, macroeconomic regime, and contemporaneous text. A benchmark over these four signals is hard to build because finance violates four assumptions of time-series evaluation: text must be gated by its publication date to prevent look-ahead, quarterly fundamentals are reported with a one- to ninety-day lag, filing text is partly redundant with the numerical statement fields it accompanies, and macroeconomic regimes leak across calendar splits. No public benchmark addresses all four signals jointly. MacroLens covers 4,416 U.S. small- and micro-cap equities over 2021-2026. Seven tasks share one point-in-time panel of prices, 46.8M XBRL accounting facts, 53 macroeconomic series, 295,860 SEC filings, and 215,882 news articles, plus a scenario layer of 1,130 macroeconomic events across 49 types automatically detected and rendered as natural language. Tasks span contextual forecasting, public and private valuation, statement generation from fundamentals and descriptions, scenario-conditioned returns, and real-estate valuation. We evaluate 19 methods across six families spanning naive heuristics through time-series foundation models, fine-tuned LLM-based time-series models, and zero-shot large language models (LLMs), plus a five-step feature-context ablation on two frontier LLMs and a gradient-boosted baseline. MacroLens is released at https://huggingface.co/datasets/DeepAuto-AI/MacroLens. △ Less

Submitted 23 June, 2026; originally announced June 2026.

Comments: 25 pages, 3 figures

Anatomically Consistent TMJ Disc Segmentation via Semantic Anchoring and Clinical Priors

Authors: Dayun Ju, Chanyoung Kim, Sunyoung Jung, Hyo-Jung Jung, Chena Lee, Younjung Park, Seong Jae Hwang

Abstract: Segmenting the temporomandibular joint (TMJ) disc from MRI is essential for accurate diagnosis of internal derangement, yet it remains unreliable in practice due to its small size, low contrast, and morphological variability. Existing methods, primarily adapted from general segmentation architectures, often produce fragmented or anatomically inconsistent masks, leading to unstable measurements of… ▽ More Segmenting the temporomandibular joint (TMJ) disc from MRI is essential for accurate diagnosis of internal derangement, yet it remains unreliable in practice due to its small size, low contrast, and morphological variability. Existing methods, primarily adapted from general segmentation architectures, often produce fragmented or anatomically inconsistent masks, leading to unstable measurements of disc position and shape for downstream diagnosis. To address these challenges, we propose TISC, a TMJ disc segmentation framework that integrates semantic anchoring with clinical metadata-guided boundary refinement. The framework first establishes robust disc localization in the foundation model feature space via a Prototypical Semantic Anchoring (PSA) module that aggregates adjacent-slice MedDINOv3 features and derives a prototype-driven similarity map. It then performs targeted boundary refinement through a Clinical-Metadata Point Refinement (C-MPR) module, with point-wise predictions modulated by Mouth Open Limitation (MOL), a clinical indicator associated with disc displacement without reduction. On a large-scale cohort of 2,488 PD MRI volumes from 1,300 patients, our method achieves up to a 4.96 Dice improvement over strong baselines across diverse architectures, delivering more anatomically coherent and clinically reliable TMJ disc segmentation. △ Less

Submitted 19 June, 2026; originally announced June 2026.

Comments: 10 pages, 3 figures

Contrastive and Adaptive Multi-modal Masked Autoencoder for Spatial Transcriptomics

Authors: Joohyeok Kim, Taejin Jeong, Jinyeong Kim, Seong Jae Hwang

Abstract: The high cost of spatial transcriptomics (ST) has driven extensive studies into predicting gene expression directly from H&E histology images. However, this prediction task faces an inherent limitation, as tissue morphology alone provides insufficient information to fully resolve underlying gene expression. To address this limitation, a recent study leverages partial gene expression to guide the p… ▽ More The high cost of spatial transcriptomics (ST) has driven extensive studies into predicting gene expression directly from H&E histology images. However, this prediction task faces an inherent limitation, as tissue morphology alone provides insufficient information to fully resolve underlying gene expression. To address this limitation, a recent study leverages partial gene expression to guide the prediction process alongside histology images. Building on this paradigm, we approach the prediction task as a spatial imputation problem, employing a Masked Autoencoder (MAE) to utilize a small fraction of gene expression as genetic anchors for inferring whole-slide gene expression profiles. Specifically, we propose a bio-saliency score and a learning-to-rank strategy to adaptively identify the most informative spots within the tissue. Based on these identified spots, our framework selects contiguous regions as genetic anchors to ensure suitability for real-world ST profiling hardware. To effectively leverage these anchors, we design a cross-modal joint encoder that integrates visual and genetic modalities. By aligning the selected anchors with their corresponding visual features via contrastive learning, the encoder generates robust joint representations to accurately predict gene expression across the whole slide. Notably, our framework consistently surpasses existing methods in both histology-only prediction and spatial imputation, achieving superior accuracy even without genetic anchors and further excelling with as little as 10% transcriptomic coverage. Our code is available at https://github.com/Kyyle2114/CAMMST. △ Less

Submitted 19 June, 2026; originally announced June 2026.

B[FM]$^2$: Brain Foundation Model via Flow Matching with SplitUNet

Authors: Jaedong Hwang, Kathleen Zhang, Wei Dai, Konstantinos Kontras, Maarten Vanmarcke, Maarten De Vos, Ila Fiete, Paul Pu Liang

Abstract: EEG foundation models can learn generalizable representations from large-scale EEG corpora to enable single-backbone transfer across diverse clinical and brain-computer interface tasks. Existing models typically discretize the continuous multi-channel EEG waveform into patches or codebook tokens and train a transformer with masked self-supervision. Recognizing that this discretization fragments co… ▽ More EEG foundation models can learn generalizable representations from large-scale EEG corpora to enable single-backbone transfer across diverse clinical and brain-computer interface tasks. Existing models typically discretize the continuous multi-channel EEG waveform into patches or codebook tokens and train a transformer with masked self-supervision. Recognizing that this discretization fragments continuous brain rhythms and obscures fine-grained temporal dynamics, we present B[FM]$^2$(Brain Foundation Model via Flow Matching), whose inductive bias aligns with the data by pretraining directly on the raw signal using continuous-time flow matching without patches, tokenization, or masking. However, multi-channel EEG signals pose an architectural challenge for flow matching: time is densely sampled and highly autocorrelated (thousands of timepoints), while the electrode axis is short (tens of channels) at distinct scalp positions. To address this time-electrode asymmetry, we introduce SplitUNet, a velocity network that factorizes each block into separate 1D temporal and 1D electrode convolutions and downsamples only along time, preserving electrode topology throughout the hierarchy. B[FM]$^2$ sets a new state of the art on 7 of 9 standard downstream EEG classification tasks, using a pretraining budget of only 36,895 segments ($\approx$ 307h), 1-2 orders of magnitude ($\approx$ 30x) less than required by existing EEG foundation models. Further, it generates synthetic EEGs that two board-certified neurologists cannot distinguish from brain data (Cohen's $κ=$ -0.096). https://jd730.github.io/projects/BFM2 △ Less

Submitted 18 June, 2026; originally announced June 2026.

MAGNIFIED: RL Fine-tuning of Multimodal Large Language Models for Motion Planning

Authors: Letian Chen, Yiren Lu, Justin Fu, Yichen Xie, Runsheng Xu, Jyh-Jing Hwang, Ben Sapp, Drago Anguelov

Abstract: Multi-modal Large Language Models (MLLMs) have demonstrated remarkable capabilities in semantic understanding and common sense reasoning, making them promising candidates for solving planning problems in autonomous driving. However, the next-token text prediction objectives traditionally used in pre-training and supervised fine-tuning (SFT) of MLLMs may fall short of fulfilling the planning object… ▽ More Multi-modal Large Language Models (MLLMs) have demonstrated remarkable capabilities in semantic understanding and common sense reasoning, making them promising candidates for solving planning problems in autonomous driving. However, the next-token text prediction objectives traditionally used in pre-training and supervised fine-tuning (SFT) of MLLMs may fall short of fulfilling the planning objectives for autonomous vehicles. The next-token prediction objective merely encourages per-token imitation in text, often irrespective of multi-step consequences and the alignment with crucial planning considerations such as giving space to other road actors. To overcome these limitations, we propose a reinforcement learning fine-tuning (RLFT) approach, MAGNIFIED, that aligns the MLLM-based driving agent with planning objectives by learning from token-level rewards. By mapping a sequence of predicted tokens to corresponding vehicle trajectories and learning from planning rewards, MAGNIFIED optimizes for the true planning objectives rather than focusing solely on token prediction accuracy, enabling the model to refine its understanding of the planning task beyond simple imitation. We validate our approach on the Waymo Open Motion Dataset with a novel setup incorporating rasterized birds-eye views and tokenized trajectories as inputs and planning-oriented outputs. An initial SFT phase establishes a strong baseline in outputting plan trajectories as sequences of X-Y coordinates in text, while subsequent RL fine-tuning substantially enhances planning performance relative to the SFT baseline (demonstrating over a 10.5% reduction in overlap rate and a 38.9% reduction in off-road rate), underscoring the potential of RLFT on MLLMs to achieve vehicle planning that is better aligned with compliant, comfortable, and efficient driving. △ Less

Submitted 2 June, 2026; originally announced June 2026.

Journal ref: ICRA 2026

BCL: Bayesian In-Context Learning Framework for Information Extraction

Authors: Haoliang Liu, Chengkun Cai, Xu Zhao, Han Zhu, Shizhou Huang, Xinglin Zhang, Tao Chen, Jenq-Neng Hwang, Zhang Huaping, Lei Li

Abstract: Existing information extraction (IE) tasks increasingly adopt in-context learning (ICL) with large language models. However, current approaches either show inconsistent performance across model scales or lack systematic optimization and generalizability. Building on this, we propose BCL (Bayesian In-Context Learning Framework for Information Extraction), the first optimization framework that uses… ▽ More Existing information extraction (IE) tasks increasingly adopt in-context learning (ICL) with large language models. However, current approaches either show inconsistent performance across model scales or lack systematic optimization and generalizability. Building on this, we propose BCL (Bayesian In-Context Learning Framework for Information Extraction), the first optimization framework that uses particle filtering with Bayesian updates to systematically refine label representations across IE tasks. Through four steps initialization, observation, weight update, and resampling, BCL generalizes to both sequence labeling and relation classification paradigms. Extensive experiments demonstrate substantial and consistent improvements over existing approaches. △ Less

Submitted 16 June, 2026; originally announced June 2026.

Comments: ACL 2026 Findings

NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment

Authors: Jisung Hwang, Yunhong Min, Jaihoon Kim, I-Chao Shen, Minhyuk Sung

Abstract: We introduce the Noise-Tilted Reverse Kernel (NTRK), a reward-guided diffusion sampler that injects reward gradients through the noise term, leaving the pretrained reverse kernel unchanged and requiring only a single sample per step. Reward-guided sampling at inference time has greatly expanded the versatility of pretrained diffusion models. Yet existing methods face a trade-off. Gradient-based gu… ▽ More We introduce the Noise-Tilted Reverse Kernel (NTRK), a reward-guided diffusion sampler that injects reward gradients through the noise term, leaving the pretrained reverse kernel unchanged and requiring only a single sample per step. Reward-guided sampling at inference time has greatly expanded the versatility of pretrained diffusion models. Yet existing methods face a trade-off. Gradient-based guidance shifts the reverse mean, steering generation but pushing intermediate states outside the region that the model was trained on and degrading quality. Search-based methods preserve quality but gain no gradient signal. No prior method achieves both. NTRK resolves this by keeping the reverse mean fixed and biasing the noise term toward high reward. This is enabled by a whitening operator, the central mechanism behind NTRK, which converts reward gradients into noise-compatible perturbations without losing their guiding signal. Across various reward alignment tasks, NTRK outperforms recent state-of-the-art baselines without losing sample quality. Remarkably, on aesthetic generation, NTRK surpasses the reward of the best baseline at 500 NFEs using only 25 NFEs, a 20 times reduction in compute. △ Less

Submitted 27 June, 2026; v1 submitted 16 June, 2026; originally announced June 2026.

Comments: ECCV 2026

Pseudonym Scheme Based on Hybrid Certificates for Security Credential Management System in Vehicular Communications

Authors: Abel C. H. Chen, F. J. Hwang, Yu-Chih Wei, Chin-Chen Chang, Bon-Yeh Lin

Abstract: In recent years, the Institute of Electrical and Electronics Engineers (IEEE) and the European Telecommunications Standards Institute (ETSI) have developed a series of security communication standards for vehicular communications. These standards include mechanisms such as the Security Credential Management System (SCMS) and Butterfly Key Expansion (BKE) to protect vehicle privacy. However, these… ▽ More In recent years, the Institute of Electrical and Electronics Engineers (IEEE) and the European Telecommunications Standards Institute (ETSI) have developed a series of security communication standards for vehicular communications. These standards include mechanisms such as the Security Credential Management System (SCMS) and Butterfly Key Expansion (BKE) to protect vehicle privacy. However, these standards are mainly based on the Elliptic-Curve Cryptography (ECC), which may be vulnerable to attacks from quantum computing in the future. In response to this potential risk, this study proposes a hybrid certificate that combines the ECC with Post-Quantum Cryptography (PQC). This approach enables infrastructure systems to be built on cryptographic foundations that are more resilient to quantum-based attacks. Furthermore, this study presents a generalized pseudonym scheme that is compatible with various cryptographic algorithms for generating pseudonym certificates. This design aims to eliminate the possibility of inferring any correlation between the public key in a pseudonym certificate and that in an enrollment certificate. This study also conducts a comprehensive performance evaluation of the RSA, ECC, and PQC algorithms, particularly those standardized by the National Institute of Standards and Technology (NIST). The comparison considers factors such as message length and computation time. Based on the findings, this study recommends suitable pseudonym schemes that adopt hybrid certificates for secure and efficient use in vehicular communications. △ Less

Submitted 11 June, 2026; originally announced June 2026.

Journal ref: IEEE Canadian Journal of Electrical and Computer Engineering (2026)

Flex4DHuman: Flexible Multi-view Video Diffusion for 4D Human Reconstruction

Authors: Jen-Hao Cheng, Yipeng Wang, Hao Zhang, Gengshan Yang, Jenq-Neng Hwang

Abstract: We present Flex4DHuman, a multi-view video diffusion model that transforms a monocular or sparse multi-view video of a dynamic subject into synchronized dense multi-view videos using only relative camera-pose conditioning. Unlike prior human-centric methods that rely on skeletons, depth maps, normals, or rendered target-view geometry, Flex4DHuman requires no explicit geometry priors and instead co… ▽ More We present Flex4DHuman, a multi-view video diffusion model that transforms a monocular or sparse multi-view video of a dynamic subject into synchronized dense multi-view videos using only relative camera-pose conditioning. Unlike prior human-centric methods that rely on skeletons, depth maps, normals, or rendered target-view geometry, Flex4DHuman requires no explicit geometry priors and instead conditions generation through relative camera-pose positional encoding. The generated videos can be directly ingested by downstream reconstruction pipelines to create dynamic 4D Gaussian splats. Built on the Wan 2.1 1.3B text-to-video model, Flex4DHuman preserves the backbone architecture and encodes camera and view information through a five-axis positional encoding that extends spatio-temporal RoPE with view indices and continuous SE(3) relative camera geometry. A three-stage curriculum progressively trains the model for pose following, flexible reference-to-target view generation, and temporal rollout. To support temporal rollout, we train with clean historical target-view tokens. We also add multi-view captions to enable test-time text control. Combined with an off-the-shelf 4D Gaussian Splatting stage, our framework lifts monocular static-camera videos into dynamic 4D Gaussian splats. Experiments on DNA-Rendering and ActorsHQ show that Flex4DHuman surpasses prior state-of-the-art methods, while the same formulation generalizes to animal categories after mixed human-animal training. These capabilities make Flex4DHuman a practical step toward scalable 4D content creation from casual monocular videos for simulation, gaming, AR/VR, and video re-shooting. △ Less

Submitted 13 June, 2026; v1 submitted 11 June, 2026; originally announced June 2026.

Comments: Project Page: https://andy-cheng.github.io/Flex4DHuman/

MemRefine: LLM-Guided Compression for Long-Term Agent Memory

Authors: Minjae Kim, Jinheon Baek, Soyeong Jeong, Sung Ju Hwang

Abstract: Large language model (LLM) agents are increasingly expected to operate over long-term interactions, where information from past dialogues must be preserved and recalled to support future tasks. However, as interactions accumulate, the memory store grows without bound and fills with redundant entries that inflate storage cost and degrade retrieval by crowding out the most useful evidence. Furthermo… ▽ More Large language model (LLM) agents are increasingly expected to operate over long-term interactions, where information from past dialogues must be preserved and recalled to support future tasks. However, as interactions accumulate, the memory store grows without bound and fills with redundant entries that inflate storage cost and degrade retrieval by crowding out the most useful evidence. Furthermore, this is especially limiting on resource-constrained platforms with hard memory budgets, motivating us to formulate storage-budgeted memory management, the task of keeping an already constructed memory store within a fixed budget while preserving information useful for future interactions. To this end, we then propose MemRefine, an LLM-guided framework that, since surface similarity poorly reflects factual value, uses similarity only to propose candidate pairs and defers delete, merge, and preserve decisions to an LLM judge based on factual content, iterating until the budget is met. Across multiple memory frameworks and long-term conversation benchmarks, MemRefine consistently meets target budgets while preserving downstream performance and outperforming rule-based baselines under tight budgets. △ Less

Submitted 11 June, 2026; originally announced June 2026.

WebChallenger: A Reliable and Efficient Generalist Web Agent

Authors: Jayoo Hwang, Xiaowen Zhang, Vedant Padwal

Abstract: Autonomous web navigation remains challenging for LLM agents, and the strongest generalist systems rely on proprietary reasoning models whose inference cost is prohibitive for the repetitive tasks where such agents would be most useful. We argue this gap stems not from insufficient model capability but from agent architectures that fail to replicate three human cognitive advantages: selective atte… ▽ More Autonomous web navigation remains challenging for LLM agents, and the strongest generalist systems rely on proprietary reasoning models whose inference cost is prohibitive for the repetitive tasks where such agents would be most useful. We argue this gap stems not from insufficient model capability but from agent architectures that fail to replicate three human cognitive advantages: selective attention to relevant page regions, persistent memory of website structure, and procedural fluency with common interaction patterns. We introduce WebChallenger, a web agent framework that addresses each gap through architecture design rather than model scale, built around PageMem: a structured page representation deterministically constructed from the DOM that exposes each page as a hierarchy of semantic sections with short summaries. On this shared substrate we build three mechanisms that mirror the three cognitive advantages: a divide-and-conquer observation pipeline that lets the agent skim section summaries and extract details only from task-relevant regions; a lightweight exploration and memory system that traverses each website once to build a reusable map of pages and element behaviors; and compound action workflows that collapse common multi-step interactions into single agent actions, handling partial state changes automatically. Because all three operate over PageMem, the framework generalizes across websites without site-specific adapters. Using off-the-shelf open-weight models without fine-tuning, our system achieves 56.3% on WebArena, 48.7% on VisualWebArena, 51.0% on Online-Mind2Web, and 70.9% on WorkArena, approaching frontier proprietary systems at a fraction of the cost. Our code is released at https://github.com/jayoohwang1/webchallenger △ Less

Submitted 9 June, 2026; originally announced June 2026.

Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them

Authors: Woojung Han, Seil Kang, Youngjun Jun, Min-Hung Chen, Fu-En Yang, Seong Jae Hwang

Abstract: Image-to-Video diffusion models leverage input images to generate visually stunning content, yet frequently produce motion that violates physical laws. We reveal a surprising finding: a 2-step generation often exhibits better physical consistency than a 50-step output from the same model. Through spectral analysis, we trace this to phase erosion during denoising; the phase degrades significantly (… ▽ More Image-to-Video diffusion models leverage input images to generate visually stunning content, yet frequently produce motion that violates physical laws. We reveal a surprising finding: a 2-step generation often exhibits better physical consistency than a 50-step output from the same model. Through spectral analysis, we trace this to phase erosion during denoising; the phase degrades significantly (dropping by $\approx 18\%$ from step 2 to step 50), whereas the magnitude remains relatively stable. Building on this insight, we propose PhaseLock, a training-free framework that preserves the valid motion priors from few-step inference throughout the denoising trajectory. Rather than relying on full-step inference for physical consistency, PhaseLock extracts a motion prior from just 2 steps and enforces it onto high-fidelity generation via Latent Delta Guidance. Our approach effectively mitigates phase degradation, improving physical consistency by an average of 6.2 points across diverse models while largely maintaining visual fidelity, with negligible overhead ($1.06\times$ time, $1.02\times$ memory) and reduced reliance on expensive external guidance methods ($\sim5\times$ time). Project Page: https://dnwjddl.github.io/phaselock △ Less

Submitted 17 June, 2026; v1 submitted 4 June, 2026; originally announced June 2026.

Comments: ICML 2026

Resonant Minds: Closed-Loop Social Avatars with Theory of Mind

Authors: Jianxu Shangguan, Jing Xu, Hang Ye, Xiaoxuan Ma, Yizhou Wang, Jenq-Neng Hwang, Wentao Zhu

Abstract: Creating lifelike digital humans with genuine social intelligence requires unifying cognitive reasoning and multimodal generation within a coherent framework. Current approaches treat these as separate tasks: Large Language Models excel at dialogue but lack embodied expression, while diffusion-based talking head models achieve visual fidelity but ignore social cognition. To bridge this gap, we pro… ▽ More Creating lifelike digital humans with genuine social intelligence requires unifying cognitive reasoning and multimodal generation within a coherent framework. Current approaches treat these as separate tasks: Large Language Models excel at dialogue but lack embodied expression, while diffusion-based talking head models achieve visual fidelity but ignore social cognition. To bridge this gap, we propose a closed-loop dual-agent framework integrating perception, social reasoning, and expression into a continuous interaction cycle. The perception module analyzes partners' multimodal behaviors from video, while the social reasoning module infers hidden mental states through Theory of Mind and selects responses via an ensemble mechanism. The expression module then generates emotion-controllable videos that jointly synthesize speaker speech and facial expressions with listener reactive behaviors, capturing bidirectional dynamics absent in prior work. We further construct a hierarchical Persona-Scenario dataset with psychologically grounded personas and private social goals to support evaluation under information asymmetry. Experiments on this dataset demonstrate competitive or superior performance on both dialogue quality and video generation metrics. Notably, our method surpasses even the full-information Script mode on key dialogue quality dimensions, suggesting that explicit mental state inference under uncertainty can elicit more thoughtful dialogue than unrestricted information access. Project page: https://resonantminds.github.io/. △ Less

Submitted 22 June, 2026; v1 submitted 4 June, 2026; originally announced June 2026.

Comments: Project page: https://resonantminds.github.io/

TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration

Authors: Soyeong Jeong, Jinheon Baek, Minki Kang, Sung Ju Hwang

Abstract: Agents are widely deployed as assistants over documents, tools, and code. However, they typically act only on explicit user requests, which surface only the problems the user has noticed, while many other important problems coexist, hidden in plain sight, within the broader user context, with their total number unknown in advance. We frame this as the task of discovering multiple hidden problems f… ▽ More Agents are widely deployed as assistants over documents, tools, and code. However, they typically act only on explicit user requests, which surface only the problems the user has noticed, while many other important problems coexist, hidden in plain sight, within the broader user context, with their total number unknown in advance. We frame this as the task of discovering multiple hidden problems from context, in which coexisting problems should be uncovered, grounded in supporting evidence, and paired with concrete actions. To this end, we introduce TIDE, a template-guided iterative framework with two complementary mechanisms. Specifically, motivated by the observation that single-pass prediction anchors on the most salient cases and yields generic claims, we propose iterative discovery, which surfaces a small batch of candidates per round while conditioning on what has already been found, so subsequent rounds extend coverage; and thought templates, reusable schemas distilled from previously solved cases that specify what contextual signals to attend to and how to connect them, anchoring each prediction in a recognizable problem class. We validate TIDE on two realistic settings, personal workspaces and software repositories, across four model backbones, showing substantial gains over single-shot and parallel multi-agent baselines on task coverage, identification, and resolution. △ Less

Submitted 14 August, 2026; v1 submitted 3 June, 2026; originally announced June 2026.

Understanding Identity Continuity in Thermal Video through Scene-Level Consistency

Authors: Wei-Chieh Sun, Gyungmin Ko, Heejae Kwon, Hsiang-Wei Huang, Jenq-Neng Hwang

Abstract: Thermal pedestrian MOT remains challenging because weak appearance cues and frequent detection interruptions cause severe trajectory fragmentation. We study whether lightweight post-processing can recover identity continuity without relying on heavy re-identification models or complex online association. Starting from a YOLOv8 and SORT baseline, we add a modular identity-repair backend consisting… ▽ More Thermal pedestrian MOT remains challenging because weak appearance cues and frequent detection interruptions cause severe trajectory fragmentation. We study whether lightweight post-processing can recover identity continuity without relying on heavy re-identification models or complex online association. Starting from a YOLOv8 and SORT baseline, we add a modular identity-repair backend consisting of online short-gap remapping and offline tracklet relinking based on temporal, spatial, motion, and border cues. Controlled ablations on a fixed validation split and evaluation on the official PBVS Thermal Pedestrian MOT benchmark show that the main identity gains arise from conservative relinking, improving IDF1 from 82.25 to 84.93 while preserving MOTA, whereas many heuristic thresholds remain stable across broad operating ranges. These results suggest that, in low-information thermal imagery, robust identity recovery can be achieved more effectively through high-precision trajectory relinking than through increasing tracker complexity. These results provide a controlled analysis of identity recovery in thermal video, showing that scene-level spatial-temporal consistency plays a dominant role in identity continuity compared to local frame-to-frame association. △ Less

Submitted 1 June, 2026; originally announced June 2026.

Comments: Accepted to CVPR 2026 Workshop on SVC. Published in CVPR Workshops proceedings

ACM Class: I.4.8; I.4.9

Journal ref: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026, pp. 1411-1419

Quantum Tunneling-Aware Machine Learning: Physics-Derived Noise Models for Robust Deployment

Authors: Uiwon Hwang, Jaeho Hwang

Abstract: Transistor scaling is approaching a quantum-mechanical limit, as thin gate oxides induce electron leakage through quantum tunneling. Unlike conventional digital systems, AI inference can tolerate such errors provided their structure is modeled correctly. In this paper, we introduce quantum tunneling-aware machine learning (QTAML). We derive the deployment-time weight-error distribution from first… ▽ More Transistor scaling is approaching a quantum-mechanical limit, as thin gate oxides induce electron leakage through quantum tunneling. Unlike conventional digital systems, AI inference can tolerate such errors provided their structure is modeled correctly. In this paper, we introduce quantum tunneling-aware machine learning (QTAML). We derive the deployment-time weight-error distribution from first principles using the Wentzel-Kramers-Brillouin (WKB) approximation and show that it has structure that generic Gaussian noise models miss: an exact affine mean drift, a per-bit variance hierarchy dominated by the most-significant bit, and a per-layer dependence on $\|W_\ell\|_\infty$ and the trained-network Jacobian. We package these three structural properties into a single deployment-time algorithm, Tunneling-Aware Compensation (TAC), that combines closed-form mean correction with an optimal layer-adaptive bit-budget allocation derived from the WKB variance decomposition. Across four convolutional architectures at $p_\mathrm{flip}$=0.10 and a transformer encoder at $p_\mathrm{flip}$=0.05, TAC reaches $95\%$ of clean accuracy with 3.4$\times$ to 33.6$\times$ less ECC overhead than Uniform-MSP, the natural baseline derived from the same physics. The closed-form saturation ratio $ρ^*$ predicts these gains in advance, and on heterogeneous architectures WKB-derived scoring outperforms magnitude-based allocation by up to 24 percentage points at small budgets. The algorithm requires no retraining, no labels, and no inference-time overhead. We also verify the WKB-derived distributional theorems to Monte Carlo precision. These results connect WKB tunneling physics with noise-aware deep learning and suggest a principled path toward hardware--software co-design beyond conventional scaling limits. △ Less

Submitted 30 May, 2026; originally announced June 2026.

How to Relieve Distribution Shifts in Semantic Segmentation for Off-Road Environments

Authors: Ji-Hoon Hwang, Daeyoung Kim, Hyung-Suk Yoon, Dong-Wook Kim, Seung-Woo Seo

Abstract: Semantic segmentation is crucial for autonomous navigation in off-road environments, enabling precise classification of surroundings to identify traversable regions. However, distinctive factors inherent to off-road conditions, such as source-target domain discrepancies and sensor corruption from rough terrain, can result in distribution shifts that alter the data differently from the trained cond… ▽ More Semantic segmentation is crucial for autonomous navigation in off-road environments, enabling precise classification of surroundings to identify traversable regions. However, distinctive factors inherent to off-road conditions, such as source-target domain discrepancies and sensor corruption from rough terrain, can result in distribution shifts that alter the data differently from the trained conditions. This often leads to inaccurate semantic label predictions and subsequent failures in navigation tasks. To address this, we propose ST-Seg, a novel framework that expands the source distribution through style expansion (SE) and texture regularization (TR). Unlike prior methods that implicitly apply generalization within a fixed source distribution, ST-Seg offers an intuitive approach for distribution shift. Specifically, SE broadens domain coverage by generating diverse realistic styles, augmenting the limited style information of the source domain. TR stabilizes local texture representation affected by style-augmented learning through a deep texture manifold. Experiments across various distribution-shifted target domains demonstrate the effectiveness of ST-Seg, with substantial improvements over existing methods. These results highlight the robustness of ST-Seg, enhancing the real-world applicability of semantic segmentation for off-road navigation. △ Less

Submitted 13 August, 2026; v1 submitted 28 May, 2026; originally announced May 2026.

Comments: 8 pages, 6 figures. Accepted to IEEE Robotics and Automation Letters (RA-L)

Journal ref: IEEE Robotics and Automation Letters, vol. 10, issue. 5, pp. 4500-4507, 2025

From General Vision to Reliable Traversability Estimation: Adapting Vision Foundation Models for Unstructured Outdoor Environments

Authors: Ji-Hoon Hwang, Jisung Bae, Dong-Wook Kim, Yeonkyu Lee, Seung-Woo Seo

Abstract: Vision-based approaches have become the dominant paradigm for traversability estimation in unstructured outdoor environments, typically adapting vision foundation models (VFMs) via semantic segmentation supervision. However, this paradigm faces three fundamental challenges that undermine its reliability: the task-agnostic design of VFMs, the ambiguity of traversability annotations, and the discrep… ▽ More Vision-based approaches have become the dominant paradigm for traversability estimation in unstructured outdoor environments, typically adapting vision foundation models (VFMs) via semantic segmentation supervision. However, this paradigm faces three fundamental challenges that undermine its reliability: the task-agnostic design of VFMs, the ambiguity of traversability annotations, and the discrepancy between semantic labels and physical safety. We propose Vision-to-Traversability Adaptation (ViTA), a framework that adapts VFMs for reliable traversability estimation, instantiated on SAM2. ViTA injects task-specific knowledge through learnable traversability prompts while preserving the VFM's cross-domain generalization. To handle annotation ambiguity, we introduce Perspective-Diversified Training, which estimates semantic uncertainty to suppress confident predictions at ambiguous boundaries. To bridge the semantic-traversability discrepancy, we distill geometric knowledge during training, enabling slope and elevation reasoning from RGB images alone at inference. The semantic and geometric outputs are fused into a continuous traversability score that reflects both semantic uncertainty and geometric risk. Evaluations across diverse domains, including challenging real-world off-road datasets, demonstrate that ViTA achieves state-of-the-art IoU and Precision with substantial false-positive reduction and strong cross-domain generalization. △ Less

Submitted 28 May, 2026; originally announced May 2026.

Comments: 8 pages, 5figures

OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources

Authors: Jinheon Baek, Soyeong Jeong, Sangwoo Park, Woongyeong Yeo, Minki Kang, Patara Trirat, Heejun Lee, Sung Ju Hwang

Abstract: Real-world information needs require access to structurally diverse knowledge sources, from unstructured text and relational tables to knowledge graphs and property graphs. Existing retrievers, however, operate over one source at a time under a fixed query language, leaving the broader landscape of available knowledge fragmented behind incompatible interfaces. A natural attempt at unification woul… ▽ More Real-world information needs require access to structurally diverse knowledge sources, from unstructured text and relational tables to knowledge graphs and property graphs. Existing retrievers, however, operate over one source at a time under a fixed query language, leaving the broader landscape of available knowledge fragmented behind incompatible interfaces. A natural attempt at unification would collapse these sources into a shared space, but this erases the structural affordances (such as schemas, ontologies, compositional operators) that give each source its expressive power. Effective retrieval over diverse knowledge, therefore, requires not homogenization but an overarching layer that meets each source on its own terms. To achieve this, we present OmniRetrieval, a framework that takes any natural-language query, identifies appropriate knowledge sources, and dispatches source-native queries to their native execution engines. Across an extensive benchmark spanning 13 datasets and 309 distinct knowledge bases over text, relational, and graph-structured sources, OmniRetrieval exceeds single-source baselines, demonstrating that it can serve as a general-purpose interface to the heterogeneous sources while preserving the structural distinctions that make each source valuable. △ Less

Submitted 27 May, 2026; originally announced May 2026.

Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents

Authors: Suji Kim, Kangsan Kim, Sung Ju Hwang

Abstract: Computer-use agents (CUAs) have recently made substantial progress, but deploying a separate large expert for each software domain remains expensive. Small open computer-use agents are more practical specialization targets, but they remain substantially weaker and exhibit uneven domain-specific failures. A straightforward remedy is to synthesize large-scale training data for the target domain, yet… ▽ More Computer-use agents (CUAs) have recently made substantial progress, but deploying a separate large expert for each software domain remains expensive. Small open computer-use agents are more practical specialization targets, but they remain substantially weaker and exhibit uneven domain-specific failures. A straightforward remedy is to synthesize large-scale training data for the target domain, yet we find that this naive approach yields only marginal improvements. Building on this observation, we introduce LearnWeak, an annotation-free specialization framework for small computer-use agents that uses a stronger reference agent to identify the student's weaknesses in the target domain, synthesize targeted tasks, and construct supervision automatically. LearnWeak further introduces an error-aware specialization objective that disentangles planning and execution errors, enabling more behaviorally precise updates than broad uniform supervision. On OSWorld, LearnWeak achieves average gains of 11.6 and 11.1 percentage points over EvoCUA-8B and OpenCUA-7B, respectively, across eight domains. We also validate that our student-aware dataset generation and training approaches outperform existing autonomous trajectory generation and training baselines. Our work highlights the importance of student awareness in both data synthesis and agent training, pointing toward a more principled and efficient path for specializing small computer-use agents in diverse domains. △ Less

Submitted 27 May, 2026; originally announced May 2026.

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

Authors: Minki Kang, Shizhe Diao, Ryo Hachiuma, Sung Ju Hwang, Pavlo Molchanov, Yu-Chiang Frank Wang, Byung-Kwan Lee

Abstract: Vision-language models with extended reasoning succeed on complex problems, but many real-world problems require external tools that internal reasoning alone often cannot resolve. Agentic reasoning therefore interleaves two behaviors with a structural asymmetry: thinking (the self-contained default) and tool use (a high-variance auxiliary acting). We refer to this asymmetry as the Thinking-Acting… ▽ More Vision-language models with extended reasoning succeed on complex problems, but many real-world problems require external tools that internal reasoning alone often cannot resolve. Agentic reasoning therefore interleaves two behaviors with a structural asymmetry: thinking (the self-contained default) and tool use (a high-variance auxiliary acting). We refer to this asymmetry as the Thinking-Acting Gap. Under standard RL recipes like GRPO, the gap manifests as two diagnostic symptoms during training: tool use is attempted on only ~30% of rollouts, and when attempted, the tool-using rollouts within a group are all-wrong on ~40% of questions, suppressing the learning signal at the tool calls that needed it. We propose AXPO (Agent eXplorative Policy Optimization): for each all-wrong tool-using subgroup, AXPO fixes the thinking prefix and resamples the tool call and its continuation, paired with uncertainty-based prefix selection. Across nine multimodal benchmarks and three scales of Qwen3-VL-Thinking, SFT+AXPO outperforms SFT+GRPO at average (+1.8pp Pass@1 and +1.8pp Pass@4 at 8B on average) and 8B with SFT+AXPO surpasses the 32B Base on Pass@4 with 4 times fewer parameters. △ Less

Submitted 27 May, 2026; originally announced May 2026.

Comments: Project page: https://byungkwanlee.github.io/AXPO-page/

Missing Pattern Recognized Diffusion Imputation Model for Missing Not At Random

Authors: Gyuwon Sim, Sumin Lee, Heesun Bae, Byeonghu Na, Doyun Kwon, Ju-Hee Hwang, Jae-Young Lim, Il-Chul Moon

Abstract: Missing data frequently arises across diverse domains, including time-series and image domains. In the real world, missing occurrences often depend on the unobservable values themselves, which are referred to as Missing Not at Random (MNAR). In this work, we introduce the Missing Pattern Recognized Diffusion Imputation Model (PRDIM), a novel framework that explicitly captures the missing pattern a… ▽ More Missing data frequently arises across diverse domains, including time-series and image domains. In the real world, missing occurrences often depend on the unobservable values themselves, which are referred to as Missing Not at Random (MNAR). In this work, we introduce the Missing Pattern Recognized Diffusion Imputation Model (PRDIM), a novel framework that explicitly captures the missing pattern and precisely imputes unobserved values. PRDIM iteratively maximizes the likelihood of the joint distribution for observed values and missing mask under an Expectation-Maximization (EM) algorithm. In this sense, we first employ a pattern recognizer, which approximates the underlying missing pattern and provides guidance during every inference toward more plausible imputations with respect to the missing information. Through extensive experiments, we demonstrate that PRDIM consistently achieves strong imputation performance under MNAR settings across multiple data modalities. △ Less

Submitted 25 May, 2026; originally announced May 2026.

How Noisy Poses Break Inverse Dynamics: Analysis and Mitigation for Video-Based Joint Torque Estimation

Authors: Donghyun Kim, Chanyoung Kim, Eunseo Jeong, Youngjoong Kwon, Seong Jae Hwang

Abstract: Recent advances in monocular 3D human pose estimation enable accurate body tracking from video. However, translating these kinematic estimates into physical quantities, such as joint torques, remains challenging due to noise amplification through inverse dynamics. In this work, we provide a systematic analysis of how pose estimation noise propagates through the inverse dynamics pipeline. We presen… ▽ More Recent advances in monocular 3D human pose estimation enable accurate body tracking from video. However, translating these kinematic estimates into physical quantities, such as joint torques, remains challenging due to noise amplification through inverse dynamics. In this work, we provide a systematic analysis of how pose estimation noise propagates through the inverse dynamics pipeline. We present three key findings: (1) pose noise is amplified by approximately 1,000x when computing joint torques via numerical differentiation, (2) proximal joints (spine, hips) are up to 10x more sensitive to noise than distal joints (wrists, hands), and (3) low-pass filtering before differentiation substantially reduces this amplification. To enable this analysis, we develop SMPL-Dynamics, a fully differentiable inverse dynamics module for the SMPL body model that requires no external physics simulators. Our module supports end-to-end gradient computation, and we demonstrate this through differentiable pose refinement, which reduces torque error by 93% with negligible change in pose. △ Less

Submitted 23 May, 2026; originally announced May 2026.

It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs

Authors: Sangwoo Park, Woongyeong Yeo, Seanie Lee, Yumin Choi, Hyomin Lee, Kangsan Kim, Jinheon Baek, Seong Joon Oh, Sung Ju Hwang

Abstract: Contextual Integrity (CI) defines privacy not merely as keeping information hidden, but as governing information flows according to the norms of a given context. As large language models are increasingly deployed as personal agents handling sensitive workflows, adhering to CI becomes critical. However, even frontier models remain unreliable in making disclosure decisions, and existing mitigation s… ▽ More Contextual Integrity (CI) defines privacy not merely as keeping information hidden, but as governing information flows according to the norms of a given context. As large language models are increasingly deployed as personal agents handling sensitive workflows, adhering to CI becomes critical. However, even frontier models remain unreliable in making disclosure decisions, and existing mitigation strategies often degrade underlying task performance. To overcome this privacy-utility trade-off, we propose SELFCI, a complementary self-distillation framework that decouples information suppression from task resolution. SELFCI jointly optimizes two independent reverse KL divergences over distinct teacher distributions derived from feedback: one encourages preserving task-relevant information for utility, while the other enforces minimal and appropriate disclosure. This complementary formulation induces a Product-of-Experts (PoE) target, aligning the policy with the intersection of capability and privacy requirements. Empirical evaluations demonstrate that SELFCI, without relying on costly external supervision, consistently outperforms competitive baselines such as online reinforcement learning algorithms (e.g., GRPO). These trends further extend to out-of-domain settings involving agentic workflows and accumulated private context, suggesting that SELFCI provides a practical path toward CI alignment. △ Less

Submitted 18 May, 2026; originally announced May 2026.

Comments: 28 pages, 16 figures

CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models

Authors: Hsiang-Wei Huang, Junbin Lu, Kuang-Ming Chen, Jianxu Shangguan, Cheng-Yen Yang, Jenq-Neng Hwang

Abstract: Vision-Language Models (VLMs) achieve strong performance on spatial question answering benchmarks, yet it remains unclear whether such gains reflect genuine spatial intelligence. We show that existing spatial VLMs lack basic camera motion understanding, a key component of spatial cognition. We propose the Spatial Narrative Score (SNS), an evaluation framework that requires VLMs to generate explici… ▽ More Vision-Language Models (VLMs) achieve strong performance on spatial question answering benchmarks, yet it remains unclear whether such gains reflect genuine spatial intelligence. We show that existing spatial VLMs lack basic camera motion understanding, a key component of spatial cognition. We propose the Spatial Narrative Score (SNS), an evaluation framework that requires VLMs to generate explicit spatial narratives capturing both scene semantics and camera motion, followed by reasoning with a frozen proxy LLM. Under SNS, state-of-the-art spatial VLMs exhibit significant performance degradation despite high direct question answering accuracy. To address this gap, we introduce CaMo, a camera motion grounded VLM that achieves consistent performance across SNS evaluation and direct spatial question answering accuracy. Our results highlight the importance of explicit spatial narrative externalization for evaluating VLMs with transferable 3D spatial understanding. Our code, data, and model is available at https://github.com/hsiangwei0903/CaMo △ Less

Submitted 19 May, 2026; originally announced May 2026.

Comments: Code and model available at https://github.com/hsiangwei0903/CaMo

SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs

Authors: Chanuk Lee, Minki Kang, Sung Ju Hwang

Abstract: Recent studies observe that reinforcement learning with verifiable rewards (RLVR) reliably improves pass@1 on reasoning tasks, yet often fails to yield comparable gains in pass@k, raising the question of whether RLVR genuinely enables large language models to acquire novel reasoning abilities or merely enhances the efficiency of sampling reasoning modes already present in the base model. Prior ana… ▽ More Recent studies observe that reinforcement learning with verifiable rewards (RLVR) reliably improves pass@1 on reasoning tasks, yet often fails to yield comparable gains in pass@k, raising the question of whether RLVR genuinely enables large language models to acquire novel reasoning abilities or merely enhances the efficiency of sampling reasoning modes already present in the base model. Prior analyses largely support the latter view, attributing this limitation to structural properties of standard RLVR objectives that result in insufficient exploration pressure. In this work, we argue that a central structural constraint arises from reverse-KL regularization, which stabilizes training but inherently anchors the policy to the reference distribution, thereby suppressing the emergence of alternative reasoning modes. However, we show that neither removing the KL term nor replacing it with forward-KL provides a satisfactory solution, as both disrupt the efficiency-coverage trade-off by either inducing reward hacking or allocating probability mass to off-target regions. To resolve this tension, we propose SAGE, a principled framework that enables controllable empirical support expansion by reshaping the reverse-KL anchor distribution itself through a guide function q(x,y), achieving consistent improvements in both pass@1 and pass@k across challenging mathematical reasoning benchmarks. Our code is available at https://github.com/tally0818/SAGE. △ Less

Submitted 15 May, 2026; originally announced May 2026.

Comments: Preprint

HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents

Authors: Woongyeng Yeo, Yumin Choi, Taekyung Ki, Sung Ju Hwang

Abstract: Training long-horizon LLM agents with reinforcement learning is challenging because sparse outcome rewards reveal whether a task succeeds, but not which intermediate actions caused the outcome or how they should be corrected. Recent methods alleviate this issue by generating rewards or textual hints from turn-level action-output signals, or by using feedback-conditioned self-distillation. However,… ▽ More Training long-horizon LLM agents with reinforcement learning is challenging because sparse outcome rewards reveal whether a task succeeds, but not which intermediate actions caused the outcome or how they should be corrected. Recent methods alleviate this issue by generating rewards or textual hints from turn-level action-output signals, or by using feedback-conditioned self-distillation. However, generating feedback at every turn is inefficient when many intermediate turns are already successful or neutral, and applying feedback at a fixed or misaligned turn often fails to supervise the actions that contributed to the failure. To bridge this gap, we propose HINT-SD, a targeted self-distillation framework that uses full-trajectory hindsight to select failure-relevant actions and applies feedback-conditioned distillation only on targeted action spans. Experiments on BFCL v3 and AppWorld show that our method improves over the dense per-turn feedback baseline by up to 18.80 percent while achieving 2.26$\times$ lower time per training step, suggesting that selecting where to distill is a key factor for both effective and efficient long-horizon agent training. △ Less

Submitted 18 May, 2026; originally announced May 2026.

Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR

Authors: Chanuk Lee, Sangwoo Park, Minki Kang, Sung Ju Hwang

Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a scalable paradigm for improving the reasoning capabilities of large language models. However, its effectiveness is fundamentally limited by exploration: the policy can only improve on trajectories it has already sampled. While increasing the number of rollouts alleviates this issue, such brute-force scaling is computationally e… ▽ More Reinforcement learning with verifiable rewards (RLVR) has emerged as a scalable paradigm for improving the reasoning capabilities of large language models. However, its effectiveness is fundamentally limited by exploration: the policy can only improve on trajectories it has already sampled. While increasing the number of rollouts alleviates this issue, such brute-force scaling is computationally expensive, and existing approaches that modify the optimization objective provide limited control over what is explored. In this work, we propose NudgeRL, a framework for structured and diversity-driven exploration in RLVR. Our approach introduces Strategy Nudging, which conditions each rollout on lightweight, strategy-level contexts to induce diverse reasoning trajectories without relying on expensive oracle supervision. To effectively learn from such structured exploration, we further propose a unified objective, which decomposes the reward signal into inter- and intra-context components and incorporates a distillation objective to transfer discovered behaviors back to the base policy. Empirically, NudgeRL outperforms standard GRPO with up to 8 times larger rollout budgets, while outperforming oracle-guided RL baseline on average across five challenging math benchmarks. These results demonstrate that structured, context-driven exploration can serve as an efficient and scalable alternative to both brute-force rollout scaling and feasibility-oriented methods based on privileged information. Our code is available at https://github.com/tally0818/NudgeRL. △ Less

Submitted 15 May, 2026; originally announced May 2026.

Comments: 28 pages, 7 figures

Towards Continuous Sign Language Conversation from Isolated Signs

Authors: Youngmin Kim, Kyobin Choo, Jiwoo Park, Minseo Kim, Chanyoung Kim, Junhyeok Kim, Seong Jae Hwang

Abstract: Sign language is the primary language for many Deaf and Hard-of-Hearing (DHH) signers, yet most conversational AI systems still mediate interaction through spoken or written language. This spoken-language-centered interface can limit access for signers for whom spoken or written language is not the most accessible medium, motivating direct sign-to-sign conversational modeling. However, sentence-le… ▽ More Sign language is the primary language for many Deaf and Hard-of-Hearing (DHH) signers, yet most conversational AI systems still mediate interaction through spoken or written language. This spoken-language-centered interface can limit access for signers for whom spoken or written language is not the most accessible medium, motivating direct sign-to-sign conversational modeling. However, sentence-level sign video data are expensive to collect and annotate, leaving existing sign translation and production models with limited vocabulary coverage and weak open-domain generalization. We address this bottleneck by constructing continuous sign conversations from isolated signs: large-scale labeled isolated clips are collected as lexically grounded motion primitives and recomposed into sign-language-ordered utterances derived from existing dialogue corpora. We introduce SignaVox-W, which provides, to our knowledge, the largest labeled isolated-sign vocabulary to date, and SignaVox-U, a continuous 3D sign conversation dataset built from SignaVox-W. To bridge structural mismatch between spoken and signed languages, we use a retrieval-guided spoken-to-gloss translator; to bridge independently collected isolated clips, we propose BRAID, a diffusion Transformer that performs duration alignment and co-articulatory boundary inpainting. With the resulting data, we train SignaVox, a direct sign-to-sign conversational model that generates 3D body, hand, and facial motion responses from prior signing context without spoken-language text or externally provided glosses at inference time. Quantitative and qualitative evaluations show improved isolated-to-continuous motion quality, stronger response-level semantic alignment, and scalable signer-centered interaction that better supports visual-spatial articulation. △ Less

Submitted 14 May, 2026; originally announced May 2026.

NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces

Authors: Konstantinos Kontras, Trui Osselaer, Stylianos G. Mouslech, Angeliki-Ilektra Karaiskou, Guido Gagliardi, Thomas Strypsteen, Mohammad Hossein Badiei, Anku Rani, Maarten Vanmarcke, Miguel Bhagubai, Chanakya Ekbote, Jaedong Hwang, Christos Chatzichristos, Paul Pu Liang, Maarten De Vos

Abstract: Foundation models (FMs) promise to extract unified representations that generalize across downstream tasks. They have emerged across fields, including electroencephalography (EEG), but it is less clear how effective they are in this particular field. Published evaluations differ in datasets, in the EEG-specific preprocessing that might influence reported results, and in the reported metrics, frequ… ▽ More Foundation models (FMs) promise to extract unified representations that generalize across downstream tasks. They have emerged across fields, including electroencephalography (EEG), but it is less clear how effective they are in this particular field. Published evaluations differ in datasets, in the EEG-specific preprocessing that might influence reported results, and in the reported metrics, frequently obscuring the clinical relevance in EEG. We introduce NeuroAtlas, the largest EEG benchmark to date: 42 datasets and 260k hours covering clinical EEG (epilepsy, sleep medicine, brain age estimation) and brain-computer interfaces, and include multiple datasets per task along with bespoke clinical evaluation metrics. Besides evaluating EEG-FMs with respect to supervised baselines, we present results from generic time-series FMs. We report three findings. First, EEG-specific FMs do not consistently outperform time-series FMs, which have neither EEG-focused architectures nor been pretrained on EEG. Second, standard machine learning metrics are insufficient to assess clinical utility: thus, we thoroughly evaluate more appropriate measures such as the quality of event-level decision-making, hypnogram-derived features, and the brain-age gap in the domains of epilepsy, sleep, and brain age, respectively. Third, model rankings and performance can vary substantially within domains. We conclude that pretrained models perform largely on par, with only narrow advantages for a few, and that current models do not yet deliver on the promise of an out-of-the-box unified EEG model. NeuroAtlas exposes this gap and provides the datasets and metrics for the next generation of unified EEG FMs. △ Less

Submitted 14 May, 2026; originally announced May 2026.

Mitigating Mask Prior Drift and Positional Attention Collapse in Large Diffusion Vision-Language Models

Authors: Sujung Hong, Chanyong Yoon, Seong Jae Hwang

Abstract: Large diffusion vision-language models (LDVLMs) have recently emerged as a promising alternative to autoregressive models, enabling parallel decoding for efficient inference and leveraging bidirectional attention for global context. Despite these advances, their behavior under long-form generation remains underexplored. In this work, we show that existing LDVLMs suffer from repetitive generation a… ▽ More Large diffusion vision-language models (LDVLMs) have recently emerged as a promising alternative to autoregressive models, enabling parallel decoding for efficient inference and leveraging bidirectional attention for global context. Despite these advances, their behavior under long-form generation remains underexplored. In this work, we show that existing LDVLMs suffer from repetitive generation and degraded visual grounding, and identify two underlying causes. First, repetitive generation originates from a mask token prior: since generation tokens are initialized as mask tokens, their hidden representations progressively drift toward a shared prior direction over generation steps. Second, a fundamental misalignment between the positional attention bias and the iterative unmasking process suppresses attention toward informative visual tokens, degrading visual grounding. Based on these insights, we propose a training-free approach, introducing Mask Prior Suppression and Monotonic RoPE Scaling to mitigate mask prior drift and positional attention collapse during decoding. Experiments on general multimodal benchmarks and visual grounding tasks demonstrate improvements over baseline LDVLMs, with robust gains on long-form description benchmarks. Our results show that these failures can be effectively addressed with a lightweight, plug-and-play strategy that requires no additional training and generalizes across diverse LDVLM architectures. △ Less

Submitted 18 May, 2026; v1 submitted 14 May, 2026; originally announced May 2026.