Showing 1–50 of 67 results for author: Lao, C

From Trajectories to Evidence: Auditable Experimental Records for Industrial Research Agents

Authors: Zijie Zhuang, Changxin Lao, Pengbo Xu, Hanwen Xu, Ruochen Yang, Yingzhi He, Peng Zhang, Jiangxia Cao, Yusheng Huang, Guohong Mu, Jian Liang, Ruiming Tang, Shuang Yang, Zhaojie Liu, Wenwu Ou, Kun Gai

Abstract: Research agents increasingly conduct multi-round machine-learning experiments in industrial recommendation settings and retain the resulting trajectories to guide later decisions. Yet a completed trajectory is not automatically evidence: generated artifacts may be unsupported or incomplete, executed rounds may be invalid or confounded, and later modifications may obscure earlier findings. We study… ▽ More Research agents increasingly conduct multi-round machine-learning experiments in industrial recommendation settings and retain the resulting trajectories to guide later decisions. Yet a completed trajectory is not automatically evidence: generated artifacts may be unsupported or incomplete, executed rounds may be invalid or confounded, and later modifications may obscure earlier findings. We study \textbf{trajectory-to-evidence conversion}, asking what a completed research process has actually established. We introduce an evidence-grounded framework that couples bounded verification of consequential artifacts with post-execution claim qualification. A context-isolated generate--verify--repair process checks artifacts for evidence violations and missing downstream requirements before release. After execution, validity and attribution checks consolidate evidence across rounds, qualify intervention-level claims as actionable repairs, diagnostic guards, or withheld findings, and preserve admitted claims as auditable records with explicit provenance and applicability boundaries. A hybrid LLM-assisted controller subsequently applies, defers, or rejects records based on available target evidence. Record audits characterize which claims survive qualification, while downstream diagnostics identify affirmative applicability judgment as a bottleneck for the tested controller. Across paper-to-target adaptations, later rounds often improve on the first, while final rounds frequently underperform an earlier best, exposing non-monotonic trajectory evolution. Candidates produced through the complete workflow also yielded positive online lifts relative to deployed baselines. △ Less

Submitted 5 August, 2026; originally announced August 2026.

RecoReward: Recommender-Guided Multimodal Description Generation for Recommendation

Authors: Guohong Mu, Yueyang Liu, Jiangxia Cao, Changxin Lao, Zijie Zhuang, Yuhui Zhang, Jiaqi Feng, Ruochen Yang, Shuang Yang, Zhaojie Liu, Qibin Hou

Abstract: Multimodal large language models (MLLMs) can convert multimodal item content into structured descriptions used as semantic features for recommendation. Conventional content-only generation, however, cannot use downstream user signals to determine which semantics should be emphasized. Recent user-conditioned methods incorporate these signals through user histories or profiles, but they require user… ▽ More Multimodal large language models (MLLMs) can convert multimodal item content into structured descriptions used as semantic features for recommendation. Conventional content-only generation, however, cannot use downstream user signals to determine which semantics should be emphasized. Recent user-conditioned methods incorporate these signals through user histories or profiles, but they require user information at inference and make generation user-dependent. In this paper, we introduce RecoReward, which instead uses behavior-derived rewards during training and preserves content-only inference. To instantiate this idea in live-stream recommendation, we treat historically engaged users as a proxy for future target users and use observational non-target users to estimate affinity shared broadly across users. The Recommender Affinity Score (RAS) contrasts these signals to provide user-selective feedback for reinforcement learning, allowing the learned policy to generate a single shared description without user inputs. In our offline benchmark, RecoReward-9B outperforms its Qwen3.5-9B baseline and all other evaluated models across seven recall metrics. Online A/B testing also shows performance gains. These results show that RecoReward trains the MLLM to produce item features that benefit downstream recommendation while retaining content-only serving. △ Less

Submitted 2 August, 2026; v1 submitted 28 July, 2026; originally announced July 2026.

Comments: 16 pages, 4 figures

$x$-Prediction Flow: Efficient Continuous Decoding for Masked Diffusion Language Models

Authors: Weitian Wang, Lianlei Shan, Shubham Rai, Cecilia De La Parra, Akash Kumar

Abstract: Masked diffusion language models (MDLMs) generate text by iteratively unmasking tokens, but their standard decoder reduces each step to a binary action: a position is either committed to a single token or left fully masked, discarding rich predictive information rather than carrying it forward, and forcing premature, irrevocable commitments that lead to poor performance under a limited decoding bu… ▽ More Masked diffusion language models (MDLMs) generate text by iteratively unmasking tokens, but their standard decoder reduces each step to a binary action: a position is either committed to a single token or left fully masked, discarding rich predictive information rather than carrying it forward, and forcing premature, irrevocable commitments that lead to poor performance under a limited decoding budget. In this paper, we reinterpret mask prediction as a clean-state prediction ($x$-prediction) and show that it can be used to induce a continuous flow in the input embedding space. Building on this view, we propose a continuous decoding framework for MDLMs where tokens can accumulate partial progress at each diffusion step and remain revisable. To match the uneven contextual constraints across positions in language, we replace the globally synchronous schedule in image diffusion with a confidence-based asynchronous update in which the diffusion progress is token-wise accumulated. Additionally, we introduce a lightweight policy network and formulate its training as a reinforcement learning problem. Applied to pretrained LLaDA, our decoder retains 83--97% of full-budget accuracy using under 15% of the diffusion steps, largely outperforming discrete mask-prediction decoding at matched budgets. △ Less

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

Comments: under review

AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems

Authors: Changxin Lao, Fei Pan, Guozhuang Ma, Han Li, Huihuang Lin, Jijun Shi, Kangzhi Zhao, Kun Gai, Mo Zhou, Qinqin Zhou, Quan Chen, Ruochen Yang, Shifu Bie, Shijie Yi, Shuang Yang, Shuo Yang, Wenhao Li, Wentao Xie, Xiao Lv, Xuming Wang, Yijun Wang, Yiming Chen, Yusheng Huang, Zhongyuan Wang, Zibo Zhao , et al. (37 additional authors not shown)

Abstract: Recommendation algorithm iteration is moving from an artisanal, engineer-bound process toward an industrialized research loop, but this transition remains blocked by a structural execution bottleneck: the idea-to-launch cycle still depends on human engineers to generate hypotheses, modify production code, launch A/B experiments, and attribute online results. Innovation therefore scales linearly wi… ▽ More Recommendation algorithm iteration is moving from an artisanal, engineer-bound process toward an industrialized research loop, but this transition remains blocked by a structural execution bottleneck: the idea-to-launch cycle still depends on human engineers to generate hypotheses, modify production code, launch A/B experiments, and attribute online results. Innovation therefore scales linearly with headcount rather than compounding with evidence, compute, and accumulated experimental knowledge. We present AgentX, a production-deployed multi-agent system that fundamentally restructures this production function. AgentX operates as a self-evolving development engine: it autonomously generates, implements, evaluates, and learns from recommendation experiments at a scale and pace that no manual workflow can sustain. The system orchestrates four tightly coupled stages in a closed loop. A Brainstorm Agent synthesizes evidence from historical experiments, system architecture, data analysis, and external research into ranked, executable proposals. A Developing Agent translates each proposal into production-ready code through repository-grounded generation and multi-dimensional reliability verification. An Evaluation Agent conducts safe online rollout with guardrail-vetoed A/B judgment, converting both successes and failures into structured knowledge assets. A Harness Evolution layer (SGPO) then distills execution trajectories into semantic-gradient updates that continuously sharpen the agents themselves -- making the system not merely automated, but self-improving. △ Less

Submitted 26 June, 2026; v1 submitted 25 June, 2026; originally announced June 2026.

Comments: Authors are listed alphabetically by their first name

OneReason Technical Report

Authors: OneRec Team, Biao Yang, Boyang Ding, Chenglong Chu, Dunju Zang, Fei Pan, Han Li, Hao Jiang, Honghui Bao, Huanjie Wang, Jian Liang, Jiangxia Cao, Jiao Ou, Jiaxin Deng, Jinghao Zhang, Kun Gai, Lu Ren, Peiru Du, Pengfei Zheng, Rongzhou Zhang, Ruiming Tang, Shiyao Wang, Siyang Mao, Siyuan Lou, Teng Shi , et al. (59 additional authors not shown)

Abstract: Generative recommendation models in the OneRec family have been widely deployed in many real-world services, such as short-video, live-streaming, advertising, and e-commerce. However, these generative models can only benefit from the scaling advantage, while their reasoning ability is hard to activate, since we cannot construct meaningful Chain-of-Thought (CoT) sequences consisting of itemic token… ▽ More Generative recommendation models in the OneRec family have been widely deployed in many real-world services, such as short-video, live-streaming, advertising, and e-commerce. However, these generative models can only benefit from the scaling advantage, while their reasoning ability is hard to activate, since we cannot construct meaningful Chain-of-Thought (CoT) sequences consisting of itemic tokens only. Inspired by the success of the reasoning-style ``think before answer'' paradigm in the LLM field, we conduct preliminary studies (i.e., OneRec-Think, OpenOneRec) to explore reasoning capability in generative recommendation. Nevertheless, we notice an unexpected phenomenon: the thinking mode does not show advantages over the non-thinking mode. Drawing insights from recent findings on CoT robustness in multi-modal language models, we argue that effective reasoning in recommendation rests on two factors: perception, the ability to ground itemic tokens in their underlying language semantics, and cognition, the ability to reorganize a user's behavior sequence into coherent latent interest points. We therefore propose OneReason, which includes: (1) strong itemic token perception in pre-training, (2) a three-level cognition-enhanced CoT format for recommendation tasks in SFT, and (3) a specialize-then-unify training recipe in RL to enhance the thinking ability. △ Less

Submitted 4 June, 2026; originally announced June 2026.

Comments: Work in progress

A Few GPUs, A Whole Lotta Scale: Faithful LLM Training Emulation with PrismLLM

Authors: Shaoke Xi, ChonLam Lao, Boyi Jia, Jiaqi Gao, Zhipeng Zhang, Jiamin Cao, Brian Sutioso, Erci Xu, Minlan Yu, Kui Ren, Yong Li, Zhengping Qian, Ennan Zhai, Jingren Zhou

Abstract: Large language model (LLM) training today runs on clusters spanning thousands of GPUs. While this scale enables rapid model advances, developing, debugging, and performance-tuning the training framework inevitably becomes complex and costly. This is because engineers often need to reproduce production behaviors to diagnose failures or evaluate optimizations, thereby demanding frequent and even exc… ▽ More Large language model (LLM) training today runs on clusters spanning thousands of GPUs. While this scale enables rapid model advances, developing, debugging, and performance-tuning the training framework inevitably becomes complex and costly. This is because engineers often need to reproduce production behaviors to diagnose failures or evaluate optimizations, thereby demanding frequent and even exclusive access to production-scale clusters -- which becomes increasingly hard given that the majority of GPUs are already committed to production workloads. Simulation relies on complex performance models that are difficult to maintain, and downscaled experiments often fail to capture scale-dependent behaviors. We present PrismLLM to decouple large-scale execution from the need to access large clusters, enabling engineers to run and observe ranks of interest under faithful large-scale behavior using only a few GPUs. PrismLLM constructs a high-fidelity execution graph via a slicing-based approach that captures computation, communication, and dependencies of the target scale. Then, PrismLLM performs hybrid emulation where selected ranks execute the original program while the remaining ranks are replayed as virtual participants. Experiments on large-scale LLM training workloads show that PrismLLM accurately reproduces performance and memory behavior, achieving only 0.58\% average error in iteration time and less than 0.01\% error in peak GPU memory usage. PrismLLM can emulate clusters of up to 8192 GPUs using fewer than 1\% of the physical GPUs required by the original deployment. △ Less

Submitted 15 May, 2026; originally announced May 2026.

Comments: 13 pages body, 21 pages total

Self-Driving Datasets: From 20 Million Papers to Nuanced Biomedical Knowledge at Scale

Authors: Haydn Jones, Yimeng Zeng, Alden Rose, Li S. Yifei, Yining Huang, Kaiwen Wu, Jiaming Liang, Maggie Ziyu Huan, Yoseph Barash, Cesar de la Fuente-Nunez, Osbert Bastani, Zachary Ives, Mark Yatskar, Jacob R. Gardner

Abstract: Manually curated biomedical repositories -- spanning bioactivity, genomics, and chemistry -- are expensive to maintain, lag behind primary literature, and discard experimental context, obscuring nuances needed to assess data correctness and coverage. We show that PubMed itself can be autonomously and cost-effectively turned into structured datasets that are larger, more nuanced, and more accurate… ▽ More Manually curated biomedical repositories -- spanning bioactivity, genomics, and chemistry -- are expensive to maintain, lag behind primary literature, and discard experimental context, obscuring nuances needed to assess data correctness and coverage. We show that PubMed itself can be autonomously and cost-effectively turned into structured datasets that are larger, more nuanced, and more accurate than the curated databases they replace. We present three coupled contributions: (1) an LLM-based entity-tagging pipeline, grounded in nine biomedical ontologies, that tags 4.5B entities across 19 categories in a 22.5M-paper, 2.5T-token PubMed corpus; (2) hybrid sparse-dense retrieval supporting entity-filtered semantic queries over the tagged corpus; and (3) Starling, a multi-agent deep research system that, given only a natural-language task description, designs precision- and recall-targeted retrieval filters, induces an extraction schema, and emits structured records with nuance-rich fields and supporting passages. Across six tasks -- blood-brain barrier permeability, oral bioavailability, acute toxicity (LD50), gene-disease associations, protein subcellular localization, and chemical reactions -- Starling produces ~6.3M records (91K-3M per task); several are, to our knowledge, the largest public datasets for their property. Frontier-model rejection of our extractions is 0.6-7.7% across tasks, far below error rates we measure on widely used curated counterparts (e.g., 16.5% on BBB_Martins, 7.3% on Bioavailability_Ma). Beyond scale and accuracy, the supporting passages carry nuance tabular databases discard -- e.g., oral bioavailability may depend on fed vs. fasted state. Together, the corpus, retrieval, and agent establish a foundation for AI-driven therapeutic design. Code and datasets: https://github.com/starling-labs/starling. △ Less

Submitted 16 June, 2026; v1 submitted 7 May, 2026; originally announced May 2026.

The autoPET3 Challenge: Automated Lesion Segmentation in Whole-Body PET/CT $\unicode{x2013}$ Multitracer Multicenter Generalization

Authors: Jakob Dexl, Katharina Jeblick, Andreas Mittermeier, Balthasar Schachtner, Anna Theresa Stüber, Johanna Topalis, Maximilian Rokuss, Fabian Isensee, Klaus H. Maier-Hein, Hamza Kalisch, Jens Kleesiek, Constantin M. Seibold, Hussain Alasmawi, Lap Yan Lennon Chan, Yixuan Yuan, Alexander Jaus, Rainer Stiefelhagen, Pauline Ornela Megne Choudja, Konstantin Nikolaou, Christian La Fougère, Sergios Gatidis, Matthias P. Fabritius, Maurice Heimer, Gizem Abaci, Lalith Kumar Shiyam Sundar , et al. (5 additional authors not shown)

Abstract: We report the design and results of the third autoPET challenge (MICCAI 2024), which benchmarked automated lesion segmentation in whole-body PET/CT under a compositional generalization setting. Training data comprised 1,014 [18F]-FDG PET/CT studies from the University Hospital Tübingen and 597 [18F]/[68Ga]-PSMA PET/CT studies from the LMU University Hospital Munich, constituting the largest public… ▽ More We report the design and results of the third autoPET challenge (MICCAI 2024), which benchmarked automated lesion segmentation in whole-body PET/CT under a compositional generalization setting. Training data comprised 1,014 [18F]-FDG PET/CT studies from the University Hospital Tübingen and 597 [18F]/[68Ga]-PSMA PET/CT studies from the LMU University Hospital Munich, constituting the largest publicly available annotated PSMA PET/CT dataset to date. The held-out test set of 200 studies covered four tracer-center combinations, two of which represented unseen compositional pairings. A complementary data-centric award category isolated the contribution of data handling strategies by restricting participants to a fixed baseline model. Seventeen teams submitted 27 algorithms, predominantly nnU-Net-based 3D networks with PET/CT channel concatenation. The top-ranked algorithm achieved a mean DSC of 0.66, FNV of 3.18 mL, and FPV of 2.78 mL across all four test conditions, improving DSC by 8% and reducing the false-negative volume by 5 mL relative to the provided baseline. Ranking was stable across bootstrap resampling and alternative ranking schemes for the top tier. Beyond the benchmark, we provide an in-depth analysis of segmentation performance at the patient and lesion level. Three main conclusions can be drawn: (1) in-domain multitracer PET/CT segmentation is sufficient and probably approaching reader agreement; (2) compositional generalization to unseen tracer-center combinations remains an open problem mainly driven by systematic volume overestimation; (3) heterogeneity and case difficulty drive performance variation substantially more than the choice of algorithm among top-ranked teams. △ Less

Submitted 11 May, 2026; v1 submitted 7 May, 2026; originally announced May 2026.

Comments: Preprint submitted to Medical Image Analysis

UCCL-Zip: Lossless Compression Supercharged GPU Communication

Authors: Shuang Ma, Chon Lam Lao, Zhiying Xu, Zhuang Wang, Ziming Mao, Delong Meng, Jia Zhen, Jun Wu, Ion Stoica, Yida Wang, Yang Zhou

Abstract: The rapid growth of large language models (LLMs) has made GPU communication a critical bottleneck. While prior work reduces communication volume via quantization or lossy compression, these approaches introduce numerical errors that can degrade convergence, accuracy, and stability. We present UCCL-Zip, a unified design that integrates lossless compression directly into GPU communication primitives… ▽ More The rapid growth of large language models (LLMs) has made GPU communication a critical bottleneck. While prior work reduces communication volume via quantization or lossy compression, these approaches introduce numerical errors that can degrade convergence, accuracy, and stability. We present UCCL-Zip, a unified design that integrates lossless compression directly into GPU communication primitives. UCCL-Zip supports both point-to-point (P2P) and collective communication without modifying user-facing APIs or compromising numerical correctness. For P2P communication, Uzip-P2P employs a split-send pipeline that exposes transmissible data early and overlaps compression with communication, while preserving high GPU efficiency by operating on large data blocks. For collective communication, Uzip-NCCL integrates compression into NCCL's persistent kernel model via fused execution, eliminating redundant memory traffic and kernel launches. In real workloads, UCCL-Zip accelerates RL weight synchronization by up to 47.5% and reduces vLLM end-to-end inference latency by up to 10%, all without application changes. △ Less

Submitted 21 April, 2026; v1 submitted 18 April, 2026; originally announced April 2026.

MaRI: Accelerating Ranking Model Inference via Structural Re-parameterization in Large Scale Recommendation System

Authors: Yusheng Huang, Pengbo Xu, Shen Wang, Changxin Lao, Jiangxia Cao, Shuang Wen, Shuang Yang, Zhaojie Liu, Han Li, Kun Gai

Abstract: Ranking models, i.e., coarse-ranking and fine-ranking models, serve as core components in large-scale recommendation systems, responsible for scoring massive item candidates based on user preferences. To meet the stringent latency requirements of online serving, structural lightweighting or knowledge distillation techniques are commonly employed for ranking model acceleration. However, these appro… ▽ More Ranking models, i.e., coarse-ranking and fine-ranking models, serve as core components in large-scale recommendation systems, responsible for scoring massive item candidates based on user preferences. To meet the stringent latency requirements of online serving, structural lightweighting or knowledge distillation techniques are commonly employed for ranking model acceleration. However, these approaches typically lead to a non-negligible drop in accuracy. Notably, the angle of lossless acceleration by optimizing feature fusion matrix multiplication, particularly through structural reparameterization, remains underexplored. In this paper, we propose MaRI, a novel Matrix Re-parameterized Inference framework, which serves as a complementary approach to existing techniques while accelerating ranking model inference without any accuracy loss. MaRI is motivated by the observation that user-side computation is redundant in feature fusion matrix multiplication, and we therefore adopt the philosophy of structural reparameterization to alleviate such redundancy. △ Less

Submitted 26 February, 2026; originally announced February 2026.

Comments: Work in progress

SARM: LLM-Augmented Semantic Anchor for End-to-End Live-Streaming Ranking

Authors: Ruochen Yang, Yueyang Liu, Zijie Zhuang, Changxin Lao, Yuhui Zhang, Jiangxia Cao, Jia Xu, Xiang Chen, Haoke Xiao, Xiangyu Wu, Xiaoyou Zhou, Xiao Lv, Shuang Yang, Tingwen Liu, Zhaojie Liu, Han Li, Kun Gai

Abstract: Large-scale live-streaming recommendation requires precise modeling of non-stationary content semantics under strict real-time serving constraints. In industrial deployment, two common approaches exhibit fundamental limitations: discrete semantic abstractions sacrifice descriptive precision through clustering, while dense multimodal embeddings are extracted independently and remain weakly aligned… ▽ More Large-scale live-streaming recommendation requires precise modeling of non-stationary content semantics under strict real-time serving constraints. In industrial deployment, two common approaches exhibit fundamental limitations: discrete semantic abstractions sacrifice descriptive precision through clustering, while dense multimodal embeddings are extracted independently and remain weakly aligned with ranking optimization, limiting fine-grained content-aware ranking. To address these limitations, we propose \textbf{SARM}, an end-to-end ranking architecture that integrates natural-language semantic anchors directly into ranking optimization, enabling fine-grained author representations conditioned on multimodal content. Each semantic anchor is represented as learnable text tokens jointly optimized with ranking features, allowing the model to adapt content descriptions to ranking objectives. A lightweight dual-token gated design captures domain-specific live-streaming semantics, while an asymmetric deployment strategy preserves low-latency online training and serving. Extensive offline evaluation and large-scale A/B tests show consistent improvements over production baselines. SARM is fully deployed and serves over 400 million users daily. △ Less

Submitted 9 February, 2026; originally announced February 2026.

QARM V2: Quantitative Alignment Multi-Modal Recommendation for Reasoning User Sequence Modeling

Authors: Tian Xia, Jiaqi Zhang, Yueyang Liu, Hongjian Dou, Tingya Yin, Jiangxia Cao, Xulei Liang, Tianlu Xie, Lihao Liu, Xiang Chen, Shen Wang, Changxin Lao, Haixiang Gan, Jinkai Yu, Keting Cen, Lu Hao, Xu Zhang, Qiqiang Zhong, Zhongbo Sun, Yiyu Wang, Shuang Yang, Mingxin Wen, Xiangyu Wu, Shaoguo Liu, Tingting Gao , et al. (3 additional authors not shown)

Abstract: With the evolution of large language models (LLMs), there is growing interest in leveraging their rich semantic understanding to enhance industrial recommendation systems (RecSys). Traditional RecSys relies on ID-based embeddings for user sequence modeling in the General Search Unit (GSU) and Exact Search Unit (ESU) paradigm, which suffers from low information density, knowledge isolation, and wea… ▽ More With the evolution of large language models (LLMs), there is growing interest in leveraging their rich semantic understanding to enhance industrial recommendation systems (RecSys). Traditional RecSys relies on ID-based embeddings for user sequence modeling in the General Search Unit (GSU) and Exact Search Unit (ESU) paradigm, which suffers from low information density, knowledge isolation, and weak generalization ability. While LLMs offer complementary strengths with dense semantic representations and strong generalization, directly applying LLM embeddings to RecSys faces critical challenges: representation unmatch with business objectives and representation unlearning end-to-end with downstream tasks. In this paper, we present QARM V2, a unified framework that bridges LLM semantic understanding with RecSys business requirements for user sequence modeling. △ Less

Submitted 9 February, 2026; originally announced February 2026.

Comments: Work in progress

Purely Agent-Driven Black-Box Optimization for Biological Design

Authors: Natalie Maus, Yimeng Zeng, Haydn Thomas Jones, Yining Huang, Gaurav Ng Goel, Alden Rose, Kyurae Kim, Hyun-Su Lee, Marcelo Der Torossian Torres, Fangping Wan, Cesar de la Fuente-Nunez, Mark Yatskar, Osbert Bastani, Jacob R. Gardner

Abstract: Many key challenges in biological design -- such as small-molecule drug discovery, antimicrobial peptide development, and protein engineering -- can be framed as black-box optimization over vast, complex structured spaces. Existing methods rely mainly on raw structural data and struggle to exploit the rich scientific literature. While large language models (LLMs) have been added to these pipelines… ▽ More Many key challenges in biological design -- such as small-molecule drug discovery, antimicrobial peptide development, and protein engineering -- can be framed as black-box optimization over vast, complex structured spaces. Existing methods rely mainly on raw structural data and struggle to exploit the rich scientific literature. While large language models (LLMs) have been added to these pipelines, they have been confined to narrow roles within structure-centered optimizers. We instead cast biological black-box optimization as an agent-driven, language-based reasoning process. We introduce Purely Agent-driven BLack-box Optimization (PABLO), a hierarchical agentic system that uses scientific LLMs pretrained on chemistry and biology literature to generate and iteratively refine biological candidates. On both the standard GuacaMol molecular design and antimicrobial peptide optimization tasks, PABLO achieves state-of-the-art performance, substantially improving sample efficiency and final objective values over established baselines. Compared to prior optimization methods that incorporate LLMs, PABLO achieves competitive token usage per run despite relying on LLMs throughout the optimization loop. Beyond raw performance, the agentic formulation offers key advantages for realistic design: it naturally incorporates semantic task descriptions, retrieval-augmented domain knowledge, and complex constraints. In follow-up in vitro validation, PABLO-optimized peptides showed strong activity against drug-resistant pathogens, underscoring the practical potential of PABLO for therapeutic discovery. △ Less

Submitted 7 May, 2026; v1 submitted 29 January, 2026; originally announced January 2026.

Foresight Prediction Enhanced Live-Streaming Recommendation

Authors: Jiangxia Cao, Ruochen Yang, Xiang Chen, Changxin Lao, Yueyang Liu, Yusheng Huang, Yuanhao Tian, Xiangyu Wu, Shuang Yang, Zhaojie Liu, Guorui Zhou

Abstract: Live-streaming, as an emerging media enabling real-time interaction between authors and users, has attracted significant attention. Unlike the stable playback time of traditional TV live or the fixed content of short video, live-streaming, due to the dynamics of content and time, poses higher requirements for the recommendation algorithm of the platform - understanding the ever-changing content in… ▽ More Live-streaming, as an emerging media enabling real-time interaction between authors and users, has attracted significant attention. Unlike the stable playback time of traditional TV live or the fixed content of short video, live-streaming, due to the dynamics of content and time, poses higher requirements for the recommendation algorithm of the platform - understanding the ever-changing content in real time and push it to users at the appropriate moment. Through analysis, we find that users have a better experience and express more positive behaviors during highlight moments of the live-streaming. Furthermore, since the model lacks access to future content during recommendation, yet user engagement depends on how well subsequent content aligns with their interests, an intuitive solution is to predict future live-streaming content. Therefore, we perform semantic quantization on live-streaming segments to obtain Semantic ids (Sid), encode the historical Sid sequence to capture the author's characteristics, and model Sid evolution trend to enable foresight prediction of future content. This foresight enhances the ranking model through refined features. Extensive offline and online experiments demonstrate the effectiveness of our method. △ Less

Submitted 7 December, 2025; originally announced December 2025.

Comments: Accepted by WSDM 2026

HTTM: Head-wise Temporal Token Merging for Faster VGGT

Authors: Weitian Wang, Lukas Meiner, Rai Shubham, Cecilia De La Parra, Akash Kumar

Abstract: The Visual Geometry Grounded Transformer (VGGT) marks a significant leap forward in 3D scene reconstruction, as it is the first model that directly infers all key 3D attributes (camera poses, depths, and dense geometry) jointly in one pass. However, this joint inference mechanism requires global attention layers that perform all-to-all attention computation on tokens from all views. For reconstruc… ▽ More The Visual Geometry Grounded Transformer (VGGT) marks a significant leap forward in 3D scene reconstruction, as it is the first model that directly infers all key 3D attributes (camera poses, depths, and dense geometry) jointly in one pass. However, this joint inference mechanism requires global attention layers that perform all-to-all attention computation on tokens from all views. For reconstruction of large scenes with long-sequence inputs, this causes a significant latency bottleneck. In this paper, we propose head-wise temporal merging (HTTM), a training-free 3D token merging method for accelerating VGGT. Existing merging techniques merge tokens uniformly across different attention heads, resulting in identical tokens in the layers' output, which hinders the model's representational ability. HTTM tackles this problem by merging tokens in multi-head granularity, which preserves the uniqueness of feature tokens after head concatenation. Additionally, this enables HTTM to leverage the spatial locality and temporal correspondence observed at the head level to achieve higher merging ratios with lower merging costs compared to existing methods. Thus, HTTM achieves up to $7\times$ acceleration over the original VGGT with negligible performance drops in a GPU-based inference. △ Less

Submitted 16 August, 2026; v1 submitted 26 November, 2025; originally announced November 2025.

Comments: Accepted to CVPR26

The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models

Authors: Phuc Minh Nguyen, Chinh D. La, Duy M. H. Nguyen, Nitesh V. Chawla, Binh T. Nguyen, Khoa D. Doan

Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key method for improving Large Language Models' reasoning capabilities, yet recent evidence suggests it may paradoxically shrink the reasoning boundary rather than expand it. This paper investigates the shrinkage issue of RLVR by analyzing its learning dynamics and reveals two critical phenomena that explain this failure. First… ▽ More Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key method for improving Large Language Models' reasoning capabilities, yet recent evidence suggests it may paradoxically shrink the reasoning boundary rather than expand it. This paper investigates the shrinkage issue of RLVR by analyzing its learning dynamics and reveals two critical phenomena that explain this failure. First, we expose negative interference in RLVR, where learning to solve certain training problems actively reduces the likelihood of correct solutions for others, leading to the decline of Pass@$k$ performance, or the probability of generating a correct solution within $k$ attempts. Second, we uncover the winner-take-all phenomenon: RLVR disproportionately reinforces problems with high likelihood, correct solutions, under the base model, while suppressing other initially low-likelihood ones. Through extensive theoretical and empirical analysis on multiple mathematical reasoning benchmarks, we show that this effect arises from the inherent on-policy sampling in standard RL objectives, causing the model to converge toward narrow solution strategies. Based on these insights, we propose a simple yet effective data curation algorithm that focuses RLVR learning on low-likelihood problems, achieving notable improvement in Pass@$k$ performance. Our code is available at https://github.com/mail-research/SELF-llm-interference. △ Less

Submitted 2 October, 2025; originally announced October 2025.

Comments: 23 pages, 15 figures

PepCompass: Navigating peptide embedding spaces using Riemannian Geometry

Authors: Marcin Możejko, Adam Bielecki, Jurand Prądzyński, Marcin Traskowski, Antoni Janowski, Hyun-Su Lee, Marcelo Der Torossian Torres, Michał Kmicikiewicz, Paulina Szymczak, Karol Jurasz, Michał Kucharczyk, Cesar de la Fuente-Nunez, Ewa Szczurek

Abstract: Antimicrobial peptide discovery is challenged by the astronomical size of peptide space and the relative scarcity of active peptides. Generative models provide continuous latent "maps" of peptide space, but conventionally ignore decoder-induced geometry and rely on flat Euclidean metrics, rendering exploration and optimization distorted and inefficient. Prior manifold-based remedies assume fixed i… ▽ More Antimicrobial peptide discovery is challenged by the astronomical size of peptide space and the relative scarcity of active peptides. Generative models provide continuous latent "maps" of peptide space, but conventionally ignore decoder-induced geometry and rely on flat Euclidean metrics, rendering exploration and optimization distorted and inefficient. Prior manifold-based remedies assume fixed intrinsic dimensionality, which critically fails in practice for peptide data. Here, we introduce PepCompass, a geometry-aware framework for peptide exploration and optimization. At its core, we define a Union of $κ$-Stable Riemannian Manifolds $\mathbb{M}^κ$, a family of decoder-induced manifolds that captures local geometry while ensuring computational stability. We propose two local exploration methods: Second-Order Riemannian Brownian Efficient Sampling, which provides a convergent second-order approximation to Riemannian Brownian motion, and Mutation Enumeration in Tangent Space, which reinterprets tangent directions as discrete amino-acid substitutions. Combining these yields Local Enumeration Bayesian Optimization (LE-BO), an efficient algorithm for local activity optimization. Finally, we introduce Potential-minimizing Geodesic Search (PoGS), which interpolates between prototype embeddings along property-enriched geodesics, biasing discovery toward seeds, i.e. peptides with favorable activity. In-vitro validation confirms the effectiveness of PepCompass: PoGS yields four novel seeds, and subsequent optimization with LE-BO discovers 25 highly active peptides with broad-spectrum activity, including against resistant bacterial strains. These results demonstrate that geometry-informed exploration provides a powerful new paradigm for antimicrobial peptide design. △ Less

Submitted 25 February, 2026; v1 submitted 2 October, 2025; originally announced October 2025.

From Supervision to Exploration: What Does Protein Language Model Learn During Reinforcement Learning?

Authors: Hanqun Cao, Hongrui Zhang, Junde Xu, Zhou Zhang, Lingdong Shen, Minghao Sun, Ge Liu, Jinbo Xu, Wu-Jun Li, Jinren Ni, Cesar de la Fuente-Nunez, Tianfan Fu, Yejin Choi, Pheng-Ann Heng, Fang Wu

Abstract: Protein language models (PLMs) have advanced computational protein science through large-scale pretraining and scalable architectures. In parallel, reinforcement learning (RL) has broadened exploration and enabled precise multi-objective optimization in protein design. Yet whether RL can push PLMs beyond their pretraining priors to uncover latent sequence-structure-function rules remains unclear.… ▽ More Protein language models (PLMs) have advanced computational protein science through large-scale pretraining and scalable architectures. In parallel, reinforcement learning (RL) has broadened exploration and enabled precise multi-objective optimization in protein design. Yet whether RL can push PLMs beyond their pretraining priors to uncover latent sequence-structure-function rules remains unclear. We address this by pairing RL with PLMs across four domains: antimicrobial peptide design, kinase variant optimization, antibody engineering, and inverse folding. Using diverse RL algorithms and model classes, we ask if RL improves sampling efficiency and, more importantly, if it reveals capabilities not captured by supervised learning. Across benchmarks, RL consistently boosts success rates and sample efficiency. Performance follows a three-factor interaction: task headroom, reward fidelity, and policy capacity jointly determine gains. When rewards are accurate and informative, policies have sufficient capacity, and tasks leave room beyond supervised baselines, improvements scale; when rewards are noisy or capacity is constrained, gains saturate despite exploration. This view yields practical guidance for RL in protein design: prioritize reward modeling and calibration before scaling policy size, match algorithm and regularization strength to task difficulty, and allocate capacity where marginal gains are largest. Implementation is available at https://github.com/chq1155/RL-PLM. △ Less

Submitted 1 October, 2025; originally announced October 2025.

Comments: 24 pages, 7 figures, 4 tables

A deep reinforcement learning platform for antibiotic discovery

Authors: Hanqun Cao, Marcelo D. T. Torres, Jingjie Zhang, Zijun Gao, Fang Wu, Chunbin Gu, Jure Leskovec, Yejin Choi, Cesar de la Fuente-Nunez, Guangyong Chen, Pheng-Ann Heng

Abstract: Antimicrobial resistance (AMR) is projected to cause up to 10 million deaths annually by 2050, underscoring the urgent need for new antibiotics. Here we present ApexAmphion, a deep-learning framework for de novo design of antibiotics that couples a 6.4-billion-parameter protein language model with reinforcement learning. The model is first fine-tuned on curated peptide data to capture antimicrobia… ▽ More Antimicrobial resistance (AMR) is projected to cause up to 10 million deaths annually by 2050, underscoring the urgent need for new antibiotics. Here we present ApexAmphion, a deep-learning framework for de novo design of antibiotics that couples a 6.4-billion-parameter protein language model with reinforcement learning. The model is first fine-tuned on curated peptide data to capture antimicrobial sequence regularities, then optimised with proximal policy optimization against a composite reward that combines predictions from a learned minimum inhibitory concentration (MIC) classifier with differentiable physicochemical objectives. In vitro evaluation of 100 designed peptides showed low MIC values (nanomolar range in some cases) for all candidates (100% hit rate). Moreover, 99 our of 100 compounds exhibited broad-spectrum antimicrobial activity against at least two clinically relevant bacteria. The lead molecules killed bacteria primarily by potently targeting the cytoplasmic membrane. By unifying generation, scoring and multi-objective optimization with deep reinforcement learning in a single pipeline, our approach rapidly produces diverse, potent candidates, offering a scalable route to peptide antibiotics and a platform for iterative steering toward potency and developability within hours. △ Less

Submitted 16 September, 2025; originally announced September 2025.

Comments: 42 pages, 16 figures

A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design

Authors: Haydn Thomas Jones, Natalie Maus, Josh Magnus Ludan, Maggie Ziyu Huan, Jiaming Liang, Marcelo Der Torossian Torres, Jiatao Liang, Zachary Ives, Yoseph Barash, Cesar de la Fuente-Nunez, Jacob R. Gardner, Mark Yatskar

Abstract: AI-driven discovery can greatly reduce design time and enhance new therapeutics' effectiveness. Models using simulators explore broad design spaces but risk violating implicit constraints due to a lack of experimental priors. For example, in a new analysis we performed on a diverse set of models on the GuacaMol benchmark using supervised classifiers, over 60\% of molecules proposed had high probab… ▽ More AI-driven discovery can greatly reduce design time and enhance new therapeutics' effectiveness. Models using simulators explore broad design spaces but risk violating implicit constraints due to a lack of experimental priors. For example, in a new analysis we performed on a diverse set of models on the GuacaMol benchmark using supervised classifiers, over 60\% of molecules proposed had high probability of being mutagenic. In this work, we introduce Medex, a dataset of priors for design problems extracted from literature describing compounds used in lab settings. It is constructed with LLM pipelines for discovering therapeutic entities in relevant paragraphs and summarizing information in concise fair-use facts. Medex consists of 32.3 million pairs of natural language facts, and appropriate entity representations (i.e. SMILES or refseq IDs). To demonstrate the potential of the data, we train LLM, CLIP, and LLava architectures to reason jointly about text and design targets and evaluate on tasks from the Therapeutic Data Commons (TDC). Medex is highly effective for creating models with strong priors: in supervised prediction problems that use our data as pretraining, our best models with 15M learnable parameters outperform larger 2B TxGemma on both regression and classification TDC tasks, and perform comparably to 9B models on average. Models built with Medex can be used as constraints while optimizing for novel molecules in GuacaMol, resulting in proposals that are safer and nearly as effective. We release our dataset at https://huggingface.co/datasets/medexanon/Medex, and will provide expanded versions as available literature grows. △ Less

Submitted 11 September, 2025; v1 submitted 14 August, 2025; originally announced August 2025.

MixA-Q: Revisiting Activation Sparsity for Vision Transformers from a Mixed-Precision Quantization Perspective

Authors: Weitian Wang, Rai Shubham, Cecilia De La Parra, Akash Kumar

Abstract: In this paper, we propose MixA-Q, a mixed-precision activation quantization framework that leverages intra-layer activation sparsity (a concept widely explored in activation pruning methods) for efficient inference of quantized window-based vision transformers. For a given uniform-bit quantization configuration, MixA-Q separates the batched window computations within Swin blocks and assigns a lowe… ▽ More In this paper, we propose MixA-Q, a mixed-precision activation quantization framework that leverages intra-layer activation sparsity (a concept widely explored in activation pruning methods) for efficient inference of quantized window-based vision transformers. For a given uniform-bit quantization configuration, MixA-Q separates the batched window computations within Swin blocks and assigns a lower bit width to the activations of less important windows, improving the trade-off between model performance and efficiency. We introduce a Two-Branch Swin Block that processes activations separately in high- and low-bit precision, enabling seamless integration of our method with most quantization-aware training (QAT) and post-training quantization (PTQ) methods, or with simple modifications. Our experimental evaluations over the COCO dataset demonstrate that MixA-Q achieves a training-free 1.35x computational speedup without accuracy loss in PTQ configuration. With QAT, MixA-Q achieves a lossless 1.25x speedup and a 1.53x speedup with only a 1% mAP drop by incorporating activation pruning. Notably, by reducing the quantization error in important regions, our sparsity-aware quantization adaptation improves the mAP of the quantized W4A4 model (with both weights and activations in 4-bit precision) by 0.7%, reducing quantization degradation by 24%. △ Less

Submitted 25 July, 2025; originally announced July 2025.

Comments: Accepted to ICCV 2025

Predicting and generating antibiotics against future pathogens with ApexOracle

Authors: Tianang Leng, Fangping Wan, Marcelo Der Torossian Torres, Cesar de la Fuente-Nunez

Abstract: Antimicrobial resistance (AMR) is escalating and outpacing current antibiotic development. Thus, discovering antibiotics effective against emerging pathogens is becoming increasingly critical. However, existing approaches cannot rapidly identify effective molecules against novel pathogens or emerging drug-resistant strains. Here, we introduce ApexOracle, an artificial intelligence (AI) model that… ▽ More Antimicrobial resistance (AMR) is escalating and outpacing current antibiotic development. Thus, discovering antibiotics effective against emerging pathogens is becoming increasingly critical. However, existing approaches cannot rapidly identify effective molecules against novel pathogens or emerging drug-resistant strains. Here, we introduce ApexOracle, an artificial intelligence (AI) model that both predicts the antibacterial potency of existing compounds and designs de novo molecules active against strains it has never encountered. Departing from models that rely solely on molecular features, ApexOracle incorporates pathogen-specific context through the integration of molecular features captured via a foundational discrete diffusion language model and a dual-embedding framework that combines genomic- and literature-derived strain representations. Across diverse bacterial species and chemical modalities, ApexOracle consistently outperformed state-of-the-art approaches in activity prediction and demonstrated reliable transferability to novel pathogens with little or no antimicrobial data. Its unified representation-generation architecture further enables the in silico creation of "new-to-nature" molecules with high predicted efficacy against priority threats. By pairing rapid activity prediction with targeted molecular generation, ApexOracle offers a scalable strategy for countering AMR and preparing for future infectious-disease outbreaks. △ Less

Submitted 10 July, 2025; originally announced July 2025.

Comments: 3 figures

Lightweight MSA Design Advances Protein Folding From Evolutionary Embeddings

Authors: Hanqun Cao, Xinyi Zhou, Zijun Gao, Chenyu Wang, Xin Gao, Zhi Zhang, Cesar de la Fuente-Nunez, Chunbin Gu, Ge Liu, Pheng-Ann Heng

Abstract: Protein structure prediction often hinges on multiple sequence alignments (MSAs), which underperform on low-homology and orphan proteins. We introduce PLAME, a lightweight MSA design framework that leverages evolutionary embeddings from pretrained protein language models to generate MSAs that better support downstream folding. PLAME couples these embeddings with a conservation--diversity loss that… ▽ More Protein structure prediction often hinges on multiple sequence alignments (MSAs), which underperform on low-homology and orphan proteins. We introduce PLAME, a lightweight MSA design framework that leverages evolutionary embeddings from pretrained protein language models to generate MSAs that better support downstream folding. PLAME couples these embeddings with a conservation--diversity loss that balances agreement on conserved positions with coverage of plausible sequence variation. Beyond generation, we develop (i) an MSA selection strategy to filter high-quality candidates and (ii) a sequence-quality metric that is complementary to depth-based measures and predictive of folding gains. On AlphaFold2 low-homology/orphan benchmarks, PLAME delivers state-of-the-art improvements in structure accuracy (e.g., lDDT/TM-score), with consistent gains when paired with AlphaFold3. Ablations isolate the benefits of the selection strategy, and case studies elucidate how MSA characteristics shape AlphaFold confidence and error modes. Finally, we show PLAME functions as a lightweight adapter, enabling ESMFold to approach AlphaFold2-level accuracy while retaining ESMFold-like inference speed. PLAME thus provides a practical path to high-quality folding for proteins lacking strong evolutionary neighbors. △ Less

Submitted 25 September, 2025; v1 submitted 17 June, 2025; originally announced July 2025.

Self-Calibrating BCIs: Ranking and Recovery of Mental Targets Without Labels

Authors: Jonathan Grizou, Carlos de la Torre-Ortiz, Tuukka Ruotsalo

Abstract: We consider the problem of recovering a mental target (e.g., an image of a face) that a participant has in mind from paired EEG (i.e., brain responses) and image (i.e., perceived faces) data collected during interactive sessions without access to labeled information. The problem has been previously explored with labeled data but not via self-calibration, where labeled data is unavailable. Here, we… ▽ More We consider the problem of recovering a mental target (e.g., an image of a face) that a participant has in mind from paired EEG (i.e., brain responses) and image (i.e., perceived faces) data collected during interactive sessions without access to labeled information. The problem has been previously explored with labeled data but not via self-calibration, where labeled data is unavailable. Here, we present the first framework and an algorithm, CURSOR, that learns to recover unknown mental targets without access to labeled data or pre-trained decoders. Our experiments on naturalistic images of faces demonstrate that CURSOR can (1) predict image similarity scores that correlate with human perceptual judgments without any label information, (2) use these scores to rank stimuli against an unknown mental target, and (3) generate new stimuli indistinguishable from the unknown mental target (validated via a user study, N=53). △ Less

Submitted 1 December, 2025; v1 submitted 11 June, 2025; originally announced June 2025.

Comments: 10 pages, 4 figures, 11 appendix pages, 7 appendix figures

Towards Easy and Realistic Network Infrastructure Testing for Large-scale Machine Learning

Authors: Jinsun Yoo, ChonLam Lao, Lianjie Cao, Bob Lantz, Minlan Yu, Tushar Krishna, Puneet Sharma

Abstract: This paper lays the foundation for Genie, a testing framework that captures the impact of real hardware network behavior on ML workload performance, without requiring expensive GPUs. Genie uses CPU-initiated traffic over a hardware testbed to emulate GPU to GPU communication, and adapts the ASTRA-sim simulator to model interaction between the network and the ML workload. This paper lays the foundation for Genie, a testing framework that captures the impact of real hardware network behavior on ML workload performance, without requiring expensive GPUs. Genie uses CPU-initiated traffic over a hardware testbed to emulate GPU to GPU communication, and adapts the ASTRA-sim simulator to model interaction between the network and the ML workload. △ Less

Submitted 29 April, 2025; originally announced April 2025.

Comments: Presented as a poster in NSDI 25

An Extensible Software Transport Layer for GPU Networking

Authors: Yang Zhou, Zhongjie Chen, Ziming Mao, ChonLam Lao, Shuo Yang, Pravein Govindan Kannan, Jiaqi Gao, Yilong Zhao, Yongji Wu, Kaichao You, Fengyuan Ren, Zhiying Xu, Costin Raiciu, Ion Stoica

Abstract: Fast-evolving machine learning (ML) workloads have increasing requirements for networking. However, host network transport on RDMA NICs is hard to evolve, causing problems for ML workloads. For example, single-path RDMA traffic is prone to flow collisions that severely degrade collective communication performance. We present UCCL, an extensible software transport layer to evolve GPU networking. UC… ▽ More Fast-evolving machine learning (ML) workloads have increasing requirements for networking. However, host network transport on RDMA NICs is hard to evolve, causing problems for ML workloads. For example, single-path RDMA traffic is prone to flow collisions that severely degrade collective communication performance. We present UCCL, an extensible software transport layer to evolve GPU networking. UCCL decouples the data path and control path of existing RDMA NICs and efficiently runs the control-path transport on host CPUs. This software extensibility brings in transport innovations that cannot be achieved in hardware for ML workloads, e.g., a multipath transport to resolve flow collisions. ML collectives atop UCCL achieve up to 4.5x higher performance compared to existing RDMA NICs. △ Less

Submitted 4 August, 2025; v1 submitted 24 April, 2025; originally announced April 2025.

OmegAMP: Targeted AMP Discovery via Biologically Informed Generation

Authors: Diogo Soares, Leon Hetzel, Paulina Szymczak, Marcelo Der Torossian Torres, Johanna Sommer, Cesar de la Fuente-Nunez, Fabian Theis, Stephan Günnemann, Ewa Szczurek

Abstract: Deep learning-based antimicrobial peptide (AMP) discovery faces critical challenges such as limited controllability, lack of representations that efficiently model antimicrobial properties, and low experimental hit rates. To address these challenges, we introduce OmegAMP, a framework designed for reliable AMP generation with increased controllability. Its diffusion-based generative model leverages… ▽ More Deep learning-based antimicrobial peptide (AMP) discovery faces critical challenges such as limited controllability, lack of representations that efficiently model antimicrobial properties, and low experimental hit rates. To address these challenges, we introduce OmegAMP, a framework designed for reliable AMP generation with increased controllability. Its diffusion-based generative model leverages a novel conditioning mechanism to achieve fine-grained control over desired physicochemical properties and to direct generation towards specific activity profiles, including species-specific effectiveness. This is further enhanced by a biologically informed encoding space that significantly improves overall generative performance. Complementing these generative capabilities, OmegAMP leverages a novel synthetic data augmentation strategy to train classifiers for AMP filtering, drastically reducing false positive rates and thereby increasing the likelihood of experimental success. Our in silico experiments demonstrate that OmegAMP delivers state-of-the-art performance across key stages of the AMP discovery pipeline, enabling us to achieve an unprecedented success rate in wet lab experiments. We tested 25 candidate peptides, 24 of them (96%) demonstrated antimicrobial activity, proving effective even against multi-drug resistant strains. Our findings underscore OmegAMP's potential to significantly advance computational frameworks in the fight against antimicrobial resistance. △ Less

Submitted 24 June, 2026; v1 submitted 24 April, 2025; originally announced April 2025.

Large Scale Multi-Task Bayesian Optimization with Large Language Models

Authors: Yimeng Zeng, Natalie Maus, Haydn Thomas Jones, Jeffrey Tao, Fangping Wan, Marcelo Der Torossian Torres, Cesar de la Fuente-Nunez, Ryan Marcus, Osbert Bastani, Jacob R. Gardner

Abstract: In multi-task Bayesian optimization, the goal is to leverage experience from optimizing existing tasks to improve the efficiency of optimizing new ones. While approaches using multi-task Gaussian processes or deep kernel transfer exist, the performance improvement is marginal when scaling beyond a moderate number of tasks. We introduce a novel approach leveraging large language models (LLMs) to le… ▽ More In multi-task Bayesian optimization, the goal is to leverage experience from optimizing existing tasks to improve the efficiency of optimizing new ones. While approaches using multi-task Gaussian processes or deep kernel transfer exist, the performance improvement is marginal when scaling beyond a moderate number of tasks. We introduce a novel approach leveraging large language models (LLMs) to learn from, and improve upon, previous optimization trajectories, scaling to approximately 1500 distinct tasks. Specifically, we propose a feedback loop in which an LLM is fine-tuned on the high quality solutions to specific tasks found by Bayesian optimization (BO). This LLM is then used to generate initialization points for future BO searches for new tasks. The trajectories of these new searches provide additional training data for fine-tuning the LLM, completing the loop. We evaluate our method on two distinct domains: database query optimization and antimicrobial peptide design. Results demonstrate that our approach creates a positive feedback loop, where the LLM's generated initializations gradually improve, leading to better optimization performance. As this feedback loop continues, we find that the LLM is eventually able to generate solutions to new tasks in just a few shots that are better than the solutions produced by "from scratch" by Bayesian optimization while simultaneously requiring significantly fewer oracle calls. △ Less

Submitted 12 June, 2025; v1 submitted 11 March, 2025; originally announced March 2025.

On the Computational Tractability of the (Many) Shapley Values

Authors: Reda Marzouk, Shahaf Bassan, Guy Katz, Colin de la Higuera

Abstract: Recent studies have examined the computational complexity of computing Shapley additive explanations (also known as SHAP) across various models and distributions, revealing their tractability or intractability in different settings. However, these studies primarily focused on a specific variant called Conditional SHAP, though many other variants exist and address different limitations. In this wor… ▽ More Recent studies have examined the computational complexity of computing Shapley additive explanations (also known as SHAP) across various models and distributions, revealing their tractability or intractability in different settings. However, these studies primarily focused on a specific variant called Conditional SHAP, though many other variants exist and address different limitations. In this work, we analyze the complexity of computing a much broader range of such variants, including Conditional, Interventional, and Baseline SHAP, while exploring both local and global computations. We show that both local and global Interventional and Baseline SHAP can be computed in polynomial time for various ML models under Hidden Markov Model distributions, extending popular algorithms such as TreeSHAP beyond empirical distributions. On the downside, we prove intractability results for these variants over a wide range of neural networks and tree ensembles. We believe that our results emphasize the intricate diversity of computing Shapley values, demonstrating how their complexity is substantially shaped by both the specific SHAP variant, the model type, and the distribution. △ Less

Submitted 17 February, 2025; originally announced February 2025.

Comments: To appear in AISTATS 2025

Covering Multiple Objectives with a Small Set of Solutions Using Bayesian Optimization

Authors: Natalie Maus, Kyurae Kim, Yimeng Zeng, Haydn Thomas Jones, Fangping Wan, Marcelo Der Torossian Torres, Cesar de la Fuente-Nunez, Jacob R. Gardner

Abstract: In multi-objective black-box optimization, the goal is typically to find solutions that optimize a set of $T$ black-box objective functions, $f_1, \ldots f_T$, simultaneously. Traditional approaches often seek a single Pareto-optimal set that balances trade-offs among all objectives. In contrast, we consider a problem setting that departs from this paradigm: finding a small set of $K < T$ solution… ▽ More In multi-objective black-box optimization, the goal is typically to find solutions that optimize a set of $T$ black-box objective functions, $f_1, \ldots f_T$, simultaneously. Traditional approaches often seek a single Pareto-optimal set that balances trade-offs among all objectives. In contrast, we consider a problem setting that departs from this paradigm: finding a small set of $K < T$ solutions, that collectively "cover" the $T$ objectives. A set of solutions is defined as "covering" if, for each objective $f_1, \ldots f_T$, there is at least one good solution. A motivating example for this problem setting occurs in drug design. For example, we may have $T$ pathogens and aim to identify a set of $K < T$ antibiotics such that at least one antibiotic can be used to treat each pathogen. This problem, known as coverage optimization, has yet to be tackled with the Bayesian optimization (BO) framework. To fill this void, we develop Multi-Objective Coverage Bayesian Optimization (MOCOBO), a BO algorithm for solving coverage optimization. Our approach is based on a new acquisition function reminiscent of expected improvement in the vanilla BO setup. We demonstrate the performance of our method on high-dimensional black-box optimization tasks, including applications in peptide and molecular design. Results show that the coverage of the $K < T$ solutions found by MOCOBO matches or nearly matches the coverage of $T$ solutions obtained by optimizing each objective individually. Furthermore, in in vitro experiments, the peptides found by MOCOBO exhibited high potency against drug-resistant pathogens, further demonstrating the potential of MOCOBO for drug discovery. All of our code is publicly available at the following link: https://github.com/nataliemaus/mocobo. △ Less

Submitted 27 October, 2025; v1 submitted 31 January, 2025; originally announced January 2025.

TrainMover: An Interruption-Resilient Runtime for ML Training

Authors: ChonLam Lao, Jiaqi Gao, Jiamin Cao, Zhipeng Zhang, Pengcheng Zhang, Jiangfei Duan, Zhilong Zheng, Yu Guan, Yichi Xu, Yong Li, Zhengping Qian, Aditya Akella, Minlan Yu, Ennan Zhai, Dennis Cai, Jingren Zhou

Abstract: Large-scale ML training jobs are frequently interrupted by hardware and software anomalies, failures, and management events. Existing solutions like checkpoint-restart or runtime reconfiguration suffer from long downtimes and degraded performance. We present TrainMover, a resilient LLM training runtime that leverages elastic and standby machines to handle interruptions with minimal downtime and ze… ▽ More Large-scale ML training jobs are frequently interrupted by hardware and software anomalies, failures, and management events. Existing solutions like checkpoint-restart or runtime reconfiguration suffer from long downtimes and degraded performance. We present TrainMover, a resilient LLM training runtime that leverages elastic and standby machines to handle interruptions with minimal downtime and zero memory overhead. To achieve these goals, TrainMover introduces three key techniques: two-phase, delta-based communication group setup; communication-free sandboxed warmup; and general standby design that enables failure recovery from any role. Our evaluation shows that TrainMover consistently achieves around 20 seconds of downtime when handling various interruptions at the 1024-GPU scale. TrainMover is projected to reduce wasted GPU hours by 55% compared to the best alternative, saving 1.4 million GPU-hours per week at the 64K-GPU scale. △ Less

Submitted 15 May, 2026; v1 submitted 17 December, 2024; originally announced December 2024.

Comments: 14 pages body, 19 pages total

Enhancing Agricultural Environment Perception via Active Vision and Zero-Shot Learning

Authors: Michele Carlo La Greca, Mirko Usuelli, Matteo Matteucci

Abstract: Agriculture, fundamental for human sustenance, faces unprecedented challenges. The need for efficient, human-cooperative, and sustainable farming methods has never been greater. The core contributions of this work involve leveraging Active Vision (AV) techniques and Zero-Shot Learning (ZSL) to improve the robot's ability to perceive and interact with agricultural environment in the context of frui… ▽ More Agriculture, fundamental for human sustenance, faces unprecedented challenges. The need for efficient, human-cooperative, and sustainable farming methods has never been greater. The core contributions of this work involve leveraging Active Vision (AV) techniques and Zero-Shot Learning (ZSL) to improve the robot's ability to perceive and interact with agricultural environment in the context of fruit harvesting. The AV Pipeline implemented within ROS 2 integrates the Next-Best View (NBV) Planning for 3D environment reconstruction through a dynamic 3D Occupancy Map. Our system allows the robotics arm to dynamically plan and move to the most informative viewpoints and explore the environment, updating the 3D reconstruction using semantic information produced through ZSL models. Simulation and real-world experimental results demonstrate our system's effectiveness in complex visibility conditions, outperforming traditional and static predefined planning methods. ZSL segmentation models employed, such as YOLO World + EfficientViT SAM, exhibit high-speed performance and accurate segmentation, allowing flexibility when dealing with semantic information in unknown agricultural contexts without requiring any fine-tuning process. △ Less

Submitted 19 September, 2024; originally announced September 2024.

Provide Proactive Reproducible Analysis Transparency with Every Publication

Authors: Paul Meijer, Nicole Howard, Jessica Liang, Autumn Kelsey, Sathya Subramanian, Ed Johnson, Paul Mariz, James Harvey, Madeline Ambrose, Vitalii Tereshchenko, Aldan Beaubien, Neelima Inala, Yousef Aggoune, Stark Pister, Anne Vetto, Melissa Kinsey, Tom Bumol, Ananda Goldrath, Xiaojun Li, Troy Torgerson, Peter Skene, Lauren Okada, Christian La France, Zach Thomson, Lucas Graybuck

Abstract: The high incidence of irreproducible research has led to urgent appeals for transparency and equitable practices in open science. For the scientific disciplines that rely on computationally intensive analyses of large data sets, a granular understanding of the analysis methodology is an essential component of reproducibility. This paper discusses the guiding principles of a computational reproduci… ▽ More The high incidence of irreproducible research has led to urgent appeals for transparency and equitable practices in open science. For the scientific disciplines that rely on computationally intensive analyses of large data sets, a granular understanding of the analysis methodology is an essential component of reproducibility. This paper discusses the guiding principles of a computational reproducibility framework that enables a scientist to proactively generate a complete reproducible trace as analysis unfolds, and share data, methods and executable tools as part of a scientific publication, allowing other researchers to verify results and easily re-execute the steps of the scientific investigation. △ Less

Submitted 17 August, 2024; originally announced August 2024.

EdgeSight: Enabling Modeless and Cost-Efficient Inference at the Edge

Authors: ChonLam Lao, Jiaqi Gao, Ganesh Ananthanarayanan, Aditya Akella, Minlan Yu

Abstract: Traditional ML inference is evolving toward modeless inference, which abstracts the complexity of model selection from users, allowing the system to automatically choose the most appropriate model for each request based on accuracy and resource requirements. While prior studies have focused on modeless inference within data centers, this paper tackles the pressing need for cost-efficient modeless… ▽ More Traditional ML inference is evolving toward modeless inference, which abstracts the complexity of model selection from users, allowing the system to automatically choose the most appropriate model for each request based on accuracy and resource requirements. While prior studies have focused on modeless inference within data centers, this paper tackles the pressing need for cost-efficient modeless inference at the edge -- particularly within its unique constraints of limited device memory, volatile network conditions, and restricted power consumption. To overcome these challenges, we propose EdgeSight, a system that provides cost-efficient EdgeSight serving for diverse DNNs at the edge. EdgeSight employs an edge-data center (edge-DC) architecture, utilizing confidence scaling to reduce the number of model options while meeting diverse accuracy requirements. Additionally, it supports lossy inference in volatile network environments. Our experimental results show that EdgeSight outperforms existing systems by up to 1.6x in P99 latency for modeless services. Furthermore, our FPGA prototype demonstrates similar performance at certain accuracy levels, with a power consumption reduction of up to 3.34x. △ Less

Submitted 14 January, 2025; v1 submitted 29 May, 2024; originally announced May 2024.

Comments: 12 pages

On the Tractability of SHAP Explanations under Markovian Distributions

Authors: Reda Marzouk, Colin de La Higuera

Abstract: Thanks to its solid theoretical foundation, the SHAP framework is arguably one the most widely utilized frameworks for local explainability of ML models. Despite its popularity, its exact computation is known to be very challenging, proven to be NP-Hard in various configurations. Recent works have unveiled positive complexity results regarding the computation of the SHAP score for specific model f… ▽ More Thanks to its solid theoretical foundation, the SHAP framework is arguably one the most widely utilized frameworks for local explainability of ML models. Despite its popularity, its exact computation is known to be very challenging, proven to be NP-Hard in various configurations. Recent works have unveiled positive complexity results regarding the computation of the SHAP score for specific model families, encompassing decision trees, random forests, and some classes of boolean circuits. Yet, all these positive results hinge on the assumption of feature independence, often simplistic in real-world scenarios. In this article, we investigate the computational complexity of the SHAP score by relaxing this assumption and introducing a Markovian perspective. We show that, under the Markovian assumption, computing the SHAP score for the class of Weighted automata, Disjoint DNFs and Decision Trees can be performed in polynomial time, offering a first positive complexity result for the problem of SHAP score computation that transcends the limitations of the feature independence assumption. △ Less

Submitted 24 May, 2024; v1 submitted 5 May, 2024; originally announced May 2024.

Comments: Accepted at ICML 2024

Some Lower Bounds on the Reach of an Algebraic Variety

Authors: Chris La Valle, Josué Tonelli-Cueto

Abstract: Separation bounds are a fundamental measure of the complexity of solving a zero-dimensional system as it measures how difficult it is to separate its zeroes. In the positive dimensional case, the notion of reach takes its place. In this paper, we provide bounds on the reach of a smooth algebraic variety in terms of several invariants of interest: the condition number, Smale's $γ$ and the bit-size.… ▽ More Separation bounds are a fundamental measure of the complexity of solving a zero-dimensional system as it measures how difficult it is to separate its zeroes. In the positive dimensional case, the notion of reach takes its place. In this paper, we provide bounds on the reach of a smooth algebraic variety in terms of several invariants of interest: the condition number, Smale's $γ$ and the bit-size. We also provide probabilistic bounds for random algebraic varieties under some general assumptions. △ Less

Submitted 30 May, 2024; v1 submitted 23 February, 2024; originally announced February 2024.

Comments: 9 pages in double column

MSC Class: 14Q20; 14P99; 14Q65

Rectilinear Crossing Number of Graphs Excluding Single-Crossing Graphs as Minors

Authors: Vida Dujmović, Camille La Rose

Abstract: The crossing number of a graph $G$ is the minimum number of crossings in a drawing of $G$ in the plane. A rectilinear drawing of a graph $G$ represents vertices of $G$ by a set of points in the plane and represents each edge of $G$ by a straight-line segment connecting its two endpoints. The rectilinear crossing number of $G$ is the minimum number of crossings in a rectilinear drawing of $G$. By… ▽ More The crossing number of a graph $G$ is the minimum number of crossings in a drawing of $G$ in the plane. A rectilinear drawing of a graph $G$ represents vertices of $G$ by a set of points in the plane and represents each edge of $G$ by a straight-line segment connecting its two endpoints. The rectilinear crossing number of $G$ is the minimum number of crossings in a rectilinear drawing of $G$. By the crossing lemma, the crossing number of an $n$-vertex graph $G$ can be $O(n)$ only if $|E(G)|\in O(n)$. Graphs of bounded genus and bounded degree (Böröczky, Pach and Tóth, 2006) and in fact all bounded degree proper minor-closed families (Wood and Telle, 2007) have been shown to admit linear crossing number, with tight $Θ(Δn)$ bound shown by Dujmović, Kawarabayashi, Mohar and Wood, 2008. Much less is known about rectilinear crossing number. It is not bounded by any function of the crossing number. We prove that graphs that exclude a single-crossing graph as a minor have the rectilinear crossing number $O(Δn)$. This dependence on $n$ and $Δ$ is best possible. A single-crossing graph is a graph whose crossing number is at most one. Thus the result applies to $K_5$-minor-free graphs, for example. It also applies to bounded treewidth graphs, since each family of bounded treewidth graphs excludes some fixed planar graph as a minor. Prior to our work, the only bounded degree minor-closed families known to have linear rectilinear crossing number were bounded degree graphs of bounded treewidth (Wood and Telle, 2007), as well as, bounded degree $K_{3,3}$-minor-free graphs (Dujmović, Kawarabayashi, Mohar and Wood, 2008). In the case of bounded treewidth graphs, our $O(Δn)$ result is again tight and improves on the previous best known bound of $O(Δ^2 n)$ by Wood and Telle, 2007 (obtained for convex geometric drawings). △ Less

Submitted 22 February, 2024; originally announced February 2024.

Relative frequencies of constrained events in stochastic processes: An analytical approach

Authors: S. Rusconi, E. Akhmatskaya, D. Sokolovski, N. Ballard, J. C. de la Cal

Abstract: The stochastic simulation algorithm (SSA) and the corresponding Monte Carlo (MC) method are among the most common approaches for studying stochastic processes. They rely on knowledge of interevent probability density functions (PDFs) and on information about dependencies between all possible events. Analytical representations of a PDF are difficult to specify in advance, in many real life applicat… ▽ More The stochastic simulation algorithm (SSA) and the corresponding Monte Carlo (MC) method are among the most common approaches for studying stochastic processes. They rely on knowledge of interevent probability density functions (PDFs) and on information about dependencies between all possible events. Analytical representations of a PDF are difficult to specify in advance, in many real life applications. Knowing the shapes of PDFs, and using experimental data, different optimization schemes can be applied in order to evaluate probability density functions and, therefore, the properties of the studied system. Such methods, however, are computationally demanding, and often not feasible. We show that, in the case where experimentally accessed properties are directly related to the frequencies of events involved, it may be possible to replace the heavy Monte Carlo core of optimization schemes with an analytical solution. Such a replacement not only provides a more accurate estimation of the properties of the process, but also reduces the simulation time by a factor of order of the sample size (at least $\approx 10^4$). The proposed analytical approach is valid for any choice of PDF. The accuracy, computational efficiency, and advantages of the method over MC procedures are demonstrated in the exactly solvable case and in the evaluation of branching fractions in controlled radical polymerization (CRP) of acrylic monomers. This polymerization can be modeled by a constrained stochastic process. Constrained systems are quite common, and this makes the method useful for various applications. △ Less

Submitted 9 February, 2024; originally announced February 2024.

Measuring the perception of the personalized activities with CloudIA robot

Authors: Alessandra Sorrentino, Laura Fiorini, Carlo La Viola, Filippo Cavallo

Abstract: Socially Assistive Robots represent a valid solution for improving the quality of life and the mood of older adults. In this context, this work presents the CloudIA robot, a non-human-like robot intended to promote sociality and well-being among older adults. The design of the robot and of the provided services were carried out by a multidisciplinary team of designers and technology developers in… ▽ More Socially Assistive Robots represent a valid solution for improving the quality of life and the mood of older adults. In this context, this work presents the CloudIA robot, a non-human-like robot intended to promote sociality and well-being among older adults. The design of the robot and of the provided services were carried out by a multidisciplinary team of designers and technology developers in tandem with professional caregivers. The capabilities of the robot were implemented according to the received guidelines and tested in two nursing facilities by 15 older people. Qualitative and quantitative metrics were used to investigate the engagement of the participants during the interaction with the robot, and to investigate any differences in the interaction during the proposed activities. The results highlighted the general tendency of humanizing the robotic platform and demonstrated the feasibility of introducing the CloudIA robot in support of the professional caregivers' work. From this pilot test, further ideas on improving the personalization of the robotic platform emerged. △ Less

Submitted 11 December, 2023; originally announced December 2023.

Comments: 6 pages, 4 figures, 1 Table

Report number: CONCATENATE/2023/12

Synthesizing Physical Backdoor Datasets: An Automated Framework Leveraging Deep Generative Models

Authors: Sze Jue Yang, Chinh D. La, Quang H. Nguyen, Kok-Seng Wong, Anh Tuan Tran, Chee Seng Chan, Khoa D. Doan

Abstract: Backdoor attacks, representing an emerging threat to the integrity of deep neural networks, have garnered significant attention due to their ability to compromise deep learning systems clandestinely. While numerous backdoor attacks occur within the digital realm, their practical implementation in real-world prediction systems remains limited and vulnerable to disturbances in the physical world. Co… ▽ More Backdoor attacks, representing an emerging threat to the integrity of deep neural networks, have garnered significant attention due to their ability to compromise deep learning systems clandestinely. While numerous backdoor attacks occur within the digital realm, their practical implementation in real-world prediction systems remains limited and vulnerable to disturbances in the physical world. Consequently, this limitation has given rise to the development of physical backdoor attacks, where trigger objects manifest as physical entities within the real world. However, creating the requisite dataset to train or evaluate a physical backdoor model is a daunting task, limiting the backdoor researchers and practitioners from studying such physical attack scenarios. This paper unleashes a recipe that empowers backdoor researchers to effortlessly create a malicious, physical backdoor dataset based on advances in generative modeling. Particularly, this recipe involves 3 automatic modules: suggesting the suitable physical triggers, generating the poisoned candidate samples (either by synthesizing new samples or editing existing clean samples), and finally refining for the most plausible ones. As such, it effectively mitigates the perceived complexity associated with creating a physical backdoor dataset, transforming it from a daunting task into an attainable objective. Extensive experiment results show that datasets created by our "recipe" enable adversaries to achieve an impressive attack success rate on real physical world data and exhibit similar properties compared to previous physical backdoor attack studies. This paper offers researchers a valuable toolkit for studies of physical backdoors, all within the confines of their laboratories. △ Less

Submitted 15 March, 2024; v1 submitted 6 December, 2023; originally announced December 2023.

ROSO: Improving Robotic Policy Inference via Synthetic Observations

Authors: Yusuke Miyashita, Dimitris Gahtidis, Colin La, Jeremy Rabinowicz, Jurgen Leitner

Abstract: In this paper, we propose the use of generative artificial intelligence (AI) to improve zero-shot performance of a pre-trained policy by altering observations during inference. Modern robotic systems, powered by advanced neural networks, have demonstrated remarkable capabilities on pre-trained tasks. However, generalizing and adapting to new objects and environments is challenging, and fine-tuning… ▽ More In this paper, we propose the use of generative artificial intelligence (AI) to improve zero-shot performance of a pre-trained policy by altering observations during inference. Modern robotic systems, powered by advanced neural networks, have demonstrated remarkable capabilities on pre-trained tasks. However, generalizing and adapting to new objects and environments is challenging, and fine-tuning visuomotor policies is time-consuming. To overcome these issues we propose Robotic Policy Inference via Synthetic Observations (ROSO). ROSO uses stable diffusion to pre-process a robot's observation of novel objects during inference time to fit within its distribution of observations of the pre-trained policies. This novel paradigm allows us to transfer learned knowledge from known tasks to previously unseen scenarios, enhancing the robot's adaptability without requiring lengthy fine-tuning. Our experiments show that incorporating generative AI into robotic inference significantly improves successful outcomes, finishing up to 57% of tasks otherwise unsuccessful with the pre-trained policy. △ Less

Submitted 29 November, 2023; v1 submitted 28 November, 2023; originally announced November 2023.

Comments: ACRA 2023 Oral

Neural Network Based Approach to Recognition of Meteor Tracks in the Mini-EUSO Telescope Data

Authors: Mikhail Zotov, Dmitry Anzhiganov, Aleksandr Kryazhenkov, Dario Barghini, Matteo Battisti, Alexander Belov, Mario Bertaina, Marta Bianciotto, Francesca Bisconti, Carl Blaksley, Sylvie Blin, Giorgio Cambiè, Francesca Capel, Marco Casolino, Toshikazu Ebisuzaki, Johannes Eser, Francesco Fenu, Massimo Alberto Franceschi, Alessio Golzio, Philippe Gorodetzky, Fumiyoshi Kajino, Hiroshi Kasuga, Pavel Klimov, Massimiliano Manfrin, Laura Marcelli , et al. (19 additional authors not shown)

Abstract: Mini-EUSO is a wide-angle fluorescence telescope that registers ultraviolet (UV) radiation in the nocturnal atmosphere of Earth from the International Space Station. Meteors are among multiple phenomena that manifest themselves not only in the visible range but also in the UV. We present two simple artificial neural networks that allow for recognizing meteor signals in the Mini-EUSO data with high… ▽ More Mini-EUSO is a wide-angle fluorescence telescope that registers ultraviolet (UV) radiation in the nocturnal atmosphere of Earth from the International Space Station. Meteors are among multiple phenomena that manifest themselves not only in the visible range but also in the UV. We present two simple artificial neural networks that allow for recognizing meteor signals in the Mini-EUSO data with high accuracy in terms of a binary classification problem. We expect that similar architectures can be effectively used for signal recognition in other fluorescence telescopes, regardless of the nature of the signal. Due to their simplicity, the networks can be implemented in onboard electronics of future orbital or balloon experiments. △ Less

Submitted 25 November, 2023; originally announced November 2023.

Comments: 15 pages

Journal ref: Algorithms 2023, 16(9), 448

Improved Segmentation of Deep Sulci in Cortical Gray Matter Using a Deep Learning Framework Incorporating Laplace's Equation

Authors: Sadhana Ravikumar, Ranjit Ittyerah, Sydney Lim, Long Xie, Sandhitsu Das, Pulkit Khandelwal, Laura E. M. Wisse, Madigan L. Bedard, John L. Robinson, Terry Schuck, Murray Grossman, John Q. Trojanowski, Edward B. Lee, M. Dylan Tisdall, Karthik Prabhakaran, John A. Detre, David J. Irwin, Winifred Trotman, Gabor Mizsei, Emilio Artacho-Pérula, Maria Mercedes Iñiguez de Onzono Martin, Maria del Mar Arroyo Jiménez, Monica Muñoz, Francisco Javier Molina Romero, Maria del Pilar Marcos Rabal , et al. (7 additional authors not shown)

Abstract: When developing tools for automated cortical segmentation, the ability to produce topologically correct segmentations is important in order to compute geometrically valid morphometry measures. In practice, accurate cortical segmentation is challenged by image artifacts and the highly convoluted anatomy of the cortex itself. To address this, we propose a novel deep learning-based cortical segmentat… ▽ More When developing tools for automated cortical segmentation, the ability to produce topologically correct segmentations is important in order to compute geometrically valid morphometry measures. In practice, accurate cortical segmentation is challenged by image artifacts and the highly convoluted anatomy of the cortex itself. To address this, we propose a novel deep learning-based cortical segmentation method in which prior knowledge about the geometry of the cortex is incorporated into the network during the training process. We design a loss function which uses the theory of Laplace's equation applied to the cortex to locally penalize unresolved boundaries between tightly folded sulci. Using an ex vivo MRI dataset of human medial temporal lobe specimens, we demonstrate that our approach outperforms baseline segmentation networks, both quantitatively and qualitatively. △ Less

Submitted 3 March, 2023; v1 submitted 1 March, 2023; originally announced March 2023.

Comments: Accepted at the 28th biennial international conference on Information Processing in Medical Imaging (IPMI 2023)

THC: Accelerating Distributed Deep Learning Using Tensor Homomorphic Compression

Authors: Minghao Li, Ran Ben Basat, Shay Vargaftik, ChonLam Lao, Kevin Xu, Michael Mitzenmacher, Minlan Yu

Abstract: Deep neural networks (DNNs) are the de facto standard for essential use cases, such as image classification, computer vision, and natural language processing. As DNNs and datasets get larger, they require distributed training on increasingly larger clusters. A main bottleneck is the resulting communication overhead where workers exchange model updates (i.e., gradients) on a per-round basis. To add… ▽ More Deep neural networks (DNNs) are the de facto standard for essential use cases, such as image classification, computer vision, and natural language processing. As DNNs and datasets get larger, they require distributed training on increasingly larger clusters. A main bottleneck is the resulting communication overhead where workers exchange model updates (i.e., gradients) on a per-round basis. To address this bottleneck and accelerate training, a widely-deployed approach is compression. However, previous deployments often apply bi-directional compression schemes by simply using a uni-directional gradient compression scheme in each direction. This results in significant computational overheads at the parameter server and increased compression error, leading to longer training and lower accuracy. We introduce Tensor Homomorphic Compression (THC), a novel bi-directional compression framework that enables the direct aggregation of compressed values and thus eliminating the aforementioned computational overheads. Moreover, THC is compatible with in-network aggregation (INA), which allows for further acceleration. Our evaluation shows that training representative vision and language models with THC reaches target accuracy by 1.40x to 1.47x faster using INA and 1.28x to 1.33x faster using a software PS compared with state-of-the-art systems. △ Less

Submitted 5 March, 2024; v1 submitted 16 February, 2023; originally announced February 2023.

Comments: 12 pages body, 21 pages total

Rapid-Motion-Track: Markerless Tracking of Fast Human Motion with Deeper Learning

Authors: Renjie Li, Chun Yu Lao, Rebecca St. George, Katherine Lawler, Saurabh Garg, Son N. Tran, Quan Bai, Jane Alty

Abstract: Objective The coordination of human movement directly reflects function of the central nervous system. Small deficits in movement are often the first sign of an underlying neurological problem. The objective of this research is to develop a new end-to-end, deep learning-based system, Rapid-Motion-Track (RMT) that can track the fastest human movement accurately when webcams or laptop cameras are us… ▽ More Objective The coordination of human movement directly reflects function of the central nervous system. Small deficits in movement are often the first sign of an underlying neurological problem. The objective of this research is to develop a new end-to-end, deep learning-based system, Rapid-Motion-Track (RMT) that can track the fastest human movement accurately when webcams or laptop cameras are used. Materials and Methods We applied RMT to finger tapping, a well-validated test of motor control that is one of the most challenging human motions to track with computer vision due to the small keypoints of digits and the high velocities that are generated. We recorded 160 finger tapping assessments simultaneously with a standard 2D laptop camera (30 frames/sec) and a high-speed wearable sensor-based 3D motion tracking system (250 frames/sec). RMT and a range of DLC models were applied to the video data with tapping frequencies up to 8Hz to extract movement features. Results The movement features (e.g. speed, rhythm, variance) identified with the new RMT system exhibited very high concurrent validity with the gold-standard measurements (97.3\% of RMT measures were within +/-0.5Hz of the Optotrak measures), and outperformed DLC and other advanced computer vision tools (around 88.2\% of DLC measures were within +/-0.5Hz of the Optotrak measures). RMT also accurately tracked a range of other rapid human movements such as foot tapping, head turning and sit-to -stand movements. Conclusion: With the ubiquity of video technology in smart devices, the RMT method holds potential to transform access and accuracy of human movement assessment. △ Less

Submitted 18 January, 2023; originally announced February 2023.

An Artificial Intelligence-based model for cell killing prediction: development, validation and explainability analysis of the ANAKIN model

Authors: Francesco G. Cordoni, Marta Missiaggia, Emanuele Scifoni, Chiara La Tessa

Abstract: The present work develops ANAKIN: an Artificial iNtelligence bAsed model for (radiation induced) cell KIlliNg prediction. ANAKIN is trained and tested over 513 cell survival experiments with different types of radiation contained in the publicly available PIDE database. We show how ANAKIN accurately predicts several relevant biological endpoints over a wide broad range on ions beams and for a high… ▽ More The present work develops ANAKIN: an Artificial iNtelligence bAsed model for (radiation induced) cell KIlliNg prediction. ANAKIN is trained and tested over 513 cell survival experiments with different types of radiation contained in the publicly available PIDE database. We show how ANAKIN accurately predicts several relevant biological endpoints over a wide broad range on ions beams and for a high number of cell--lines. We compare the prediction of ANAKIN to the only two radiobiological model for RBE prediction used in clinics, that is the Microdosimetric Kinetic Model (MKM) and the Local Effect Model (LEM version III), showing how ANAKIN has higher accuracy over the all considered biological endpoints. At last, via modern techniques of Explainable Artificial Intelligence (XAI), we show how ANAKIN predictions can be understood and explained, highlighting how ANAKIN is in fact able to reproduce relevant well-known biological patterns, such as the overkilling effect. △ Less

Submitted 19 January, 2023; originally announced January 2023.

Learning crop type mapping from regional label proportions in large-scale SAR and optical imagery

Authors: Laura E. C. La Rosa, Dario A. B. Oliveira, Pedram Ghamisi

Abstract: The application of deep learning algorithms to Earth observation (EO) in recent years has enabled substantial progress in fields that rely on remotely sensed data. However, given the data scale in EO, creating large datasets with pixel-level annotations by experts is expensive and highly time-consuming. In this context, priors are seen as an attractive way to alleviate the burden of manual labelin… ▽ More The application of deep learning algorithms to Earth observation (EO) in recent years has enabled substantial progress in fields that rely on remotely sensed data. However, given the data scale in EO, creating large datasets with pixel-level annotations by experts is expensive and highly time-consuming. In this context, priors are seen as an attractive way to alleviate the burden of manual labeling when training deep learning methods for EO. For some applications, those priors are readily available. Motivated by the great success of contrastive-learning methods for self-supervised feature representation learning in many computer-vision tasks, this study proposes an online deep clustering method using crop label proportions as priors to learn a sample-level classifier based on government crop-proportion data for a whole agricultural region. We evaluate the method using two large datasets from two different agricultural regions in Brazil. Extensive experiments demonstrate that the method is robust to different data types (synthetic-aperture radar and optical images), reporting higher accuracy values considering the major crop types in the target regions. Thus, it can alleviate the burden of large-scale image annotation in EO applications. △ Less

Submitted 24 August, 2022; originally announced August 2022.

Marginal Inference queries in Hidden Markov Models under context-free grammar constraints

Authors: Reda Marzouk, Colin de La Higuera

Abstract: The primary use of any probabilistic model involving a set of random variables is to run inference and sampling queries on it. Inference queries in classical probabilistic models is concerned by the computation of marginal or conditional probabilities of events given as an input. When the probabilistic model is sequential, more sophisticated marginal inference queries involving complex grammars ma… ▽ More The primary use of any probabilistic model involving a set of random variables is to run inference and sampling queries on it. Inference queries in classical probabilistic models is concerned by the computation of marginal or conditional probabilities of events given as an input. When the probabilistic model is sequential, more sophisticated marginal inference queries involving complex grammars may be of interest in fields such as computational linguistics and NLP. In this work, we address the question of computing the likelihood of context-free grammars (CFGs) in Hidden Markov Models (HMMs). We provide a dynamic algorithm for the exact computation of the likelihood for the class of unambiguous context-free grammars. We show that the problem is NP-Hard, even with the promise that the input CFG has a degree of ambiguity less than or equal to 2. We then propose a fully polynomial randomized approximation scheme (FPRAS) algorithm to approximate the likelihood for the case of polynomially-bounded ambiguous CFGs. △ Less

Submitted 26 June, 2022; originally announced June 2022.

Minimizing Entropy to Discover Good Solutions to Recurrent Mixed Integer Programs

Authors: Charly Robinson La Rocca, Emma Frejinger, Jean-François Cordeau

Abstract: Current state-of-the-art solvers for mixed-integer programming (MIP) problems are designed to perform well on a wide range of problems. However, for many real-world use cases, problem instances come from a narrow distribution. This has motivated the development of specialized methods that can exploit the information in historical datasets to guide the design of heuristics. Recent works have shown… ▽ More Current state-of-the-art solvers for mixed-integer programming (MIP) problems are designed to perform well on a wide range of problems. However, for many real-world use cases, problem instances come from a narrow distribution. This has motivated the development of specialized methods that can exploit the information in historical datasets to guide the design of heuristics. Recent works have shown that machine learning (ML) can be integrated with an MIP solver to inject domain knowledge and efficiently close the optimality gap. This hybridization is usually done with deep learning (DL), which requires a large dataset and extensive hyperparameter tuning to perform well. This paper proposes an online heuristic that uses the notion of entropy to efficiently build a model with minimal training data and tuning. We test our method on the locomotive assignment problem (LAP), a recurring real-world problem that is challenging to solve at scale. Experimental results show a speed up of an order of magnitude compared to a general purpose solver (CPLEX) with a relative gap of less than 2%. We also observe that for some instances our method can discover better solutions than CPLEX within the time limit. △ Less

Submitted 7 February, 2022; originally announced February 2022.

Comments: 8 pages, 4 figures

Efficient Data-Plane Memory Scheduling for In-Network Aggregation

Authors: Hao Wang, Yuxuan Qin, ChonLam Lao, Yanfang Le, Wenfei Wu, Kai Chen

Abstract: As the scale of distributed training grows, communication becomes a bottleneck. To accelerate the communication, recent works introduce In-Network Aggregation (INA), which moves the gradients summation into network middle-boxes, e.g., programmable switches to reduce the traffic volume. However, switch memory is scarce compared to the volume of gradients transmitted in distributed training. Althoug… ▽ More As the scale of distributed training grows, communication becomes a bottleneck. To accelerate the communication, recent works introduce In-Network Aggregation (INA), which moves the gradients summation into network middle-boxes, e.g., programmable switches to reduce the traffic volume. However, switch memory is scarce compared to the volume of gradients transmitted in distributed training. Although literature applies methods like pool-based streaming or dynamic sharing to tackle the mismatch, switch memory is still a potential performance bottleneck. Furthermore, we observe the under-utilization of switch memory due to the synchronization requirement for aggregator deallocation in recent works. To improve the switch memory utilization, we propose ESA, an $\underline{E}$fficient Switch Memory $\underline{S}$cheduler for In-Network $\underline{A}$ggregation. At its cores, ESA enforces the preemptive aggregator allocation primitive and introduces priority scheduling at the data-plane, which improves the switch memory utilization and average job completion time (JCT). Experiments show that ESA can improve the average JCT by up to $1.35\times$. △ Less

Submitted 17 January, 2022; originally announced January 2022.