| 10 |
Agent JIT Compilation for Latency-Optimizing Web Agent Planning and Scheduling |
Caleb Winston, Ron Yifeng Wang et al. |
cs.LG, cs.AI |
| 10 |
SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering |
Qingnan Ren, Shun Zou et al. |
|
| 10 |
It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs |
Sangwoo Park, Woongyeong Yeo et al. |
|
| 10 |
MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems |
Hyunji Lee, Justin Chih-Yao Chen et al. |
|
| 10 |
PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Models |
Ziliang Zhao, Zenan Xu et al. |
|
| 10 |
Ethical Hyper-Velocity (EHV): A Provably Deterministic Governance-Aware JIT Compiler Architecture for Agentic Systems |
Riddhi Mohan Sharma |
|
| 10 |
Interactive Evaluation Requires a Design Science |
Keyang Xuan, Peiyang Song et al. |
|
| 9 |
HiRes: Inspectable Precedent Memory for Reaction Condition Recommendation |
Shreyas Vinaya Sathyanarayana, Raja Sekhar Pappala et al. |
cs.LG, cs.AI, q-bio.MN |
| 9 |
LLMEval-Logic: A Solver-Verified Chinese Benchmark for Logical Reasoning of LLMs with Adversarial Hardening |
Ming Zhang, Qiyuan Peng et al. |
|
| 8 |
DeepWeb-Bench: A Deep Research Benchmark Demanding Massive Cross-Source Evidence and Long-Horizon Derivation |
Sixiong Xie, Zhuofan Shi et al. |
cs.AI |
| 8 |
Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment |
Zhiqin Yang, Yonggang Zhang et al. |
|
| 8 |
On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists |
Seungone Kim, Dongkeun Yoon et al. |
|
| 8 |
S-Bus: Automatic Read-Set Reconstruction for Multi-Agent LLM State Coordination |
Sajjad Khan |
|
| 7 |
Mem-$π$: Adaptive Memory through Learning When and What to Generate |
Xiaoqiang Wang, Chao Wang et al. |
cs.CL, cs.AI |
| 7 |
Quality and Security Signals in AI-Generated Python Refactoring Pull Requests |
Mohamed Almukhtar, Anwar Ghammam et al. |
cs.SE, cs.AI |
| 6 |
WikiVQABench: A Knowledge-Grounded Visual Question Answering Benchmark from Wikipedia and Wikidata |
Basel Shbita, Pengyuan Li et al. |
cs.CV, cs.AI |
| 6 |
Teaching AI Through Benchmark Construction: QuestBench as a Course-Based Practice for Accountable Knowledge Work |
Haiyang Shen, Jiuzheng Wang et al. |
cs.AI |
| 6 |
Leveraging LLMs for Grammar Adaptation: A Study on Metamodel-Grammar Co-Evolution |
Weixing Zhang, Bowen Jiang et al. |
cs.CL, cs.SE |
| 6 |
Text Analytics Evaluation Framework: A Case Study on LLMs and Social Media |
Yuefeng Shi, Nedjma Ousidhoum et al. |
cs.CL |
| 6 |
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining |
Weimin Xiong, Shuhao Gu et al. |
|
| 5 |
AiraXiv: An AI-Driven Open-Access Platform for Human and AI Scientists |
Junshu Pan, Panzhong Lu et al. |
cs.AI, cs.CL, cs.LG |
| 5 |
FedCritic: Serverless Federated Critic Learning-based Resource Allocation for Multi-Cell OFDMA in 6G |
Amin Farajzadeh, Melike Erol-Kantarci |
cs.LG, cs.AI, cs.CV, cs.NI |
| 5 |
SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents |
Bingchen Zhao, Dhruv Srikanth et al. |
cs.SE, cs.AI, cs.CL |
| 5 |
Tracing the ongoing emergence of human-like reasoning in Large Language Models |
Paolo Morosi, Nikoleta Pantelidou et al. |
cs.CL, cs.AI |
| 5 |
MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization |
Md Mehrab Tanjim, Jayakumar Subramanian et al. |
|
| 5 |
Learn-by-Wire Training Control Governance: Bounded Autonomous Training Under Stress for Stability and Efficiency |
Anis Radianis |
|
| 5 |
Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection |
Guanglong Sun, Siyuan Zhang et al. |
|
| 5 |
Rethinking Visual Attribution for Chest X-ray Reasoning in Large Vision Language Models |
Guangzhi Xiong, Qiao Jin et al. |
|
| 5 |
Generative Recursive Reasoning |
Junyeob Baek, Mingyu Jo et al. |
|
| 4 |
TempGlitch: Evaluating Vision-Language Models for Temporal Glitch Detection in Gameplay Videos |
Yakun Yu, Ashley Wiens et al. |
cs.CV, cs.AI |
| 4 |
Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning |
Benhao Huang, Zhengyang Geng et al. |
cs.LG |
| 4 |
roto 2.0: The Robot Tactile Olympiad |
Elle Miller, Jayaram Reddy et al. |
cs.RO, cs.LG |
| 4 |
LamPO: A Lambda Style Policy Optimization for Reasoning Language Models |
Zhe Yuan, Yipeng Zhou et al. |
cs.CL |
| 4 |
Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos |
X. Feng, J. Zhu et al. |
|
| 4 |
A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook |
Kaiwen Luo, Zhenhong Zhou et al. |
|
| 4 |
OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond |
Zunhai Su, Rui Yang et al. |
|
| 3 |
HITL-D: Human In The Loop Diffusion Assisted Shared Control |
Riley Zilka, Sergey Khlynovskiy et al. |
cs.RO, cs.AI, cs.HC |
| 3 |
torchtune: PyTorch native post-training library |
Mark Obozov, Maxime Griot et al. |
cs.LG, cs.AI |
| 3 |
Stdlib or Third-Party? Empirical Performance and Correctness of LLM-Assisted Zero-Dependency Python Libraries |
Peng Ding, Rick Stevens |
cs.SE, cs.AI, cs.PL |
| 3 |
You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories |
Zhepei Wei, Xinyu Zhu et al. |
cs.LG, cs.CL |
| 3 |
TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization |
Lucheng Fu, Ye Yu et al. |
cs.CL, cs.AI, cs.LG |
| 3 |
Reliable Automated Triage in Spanish Clinical Notes: A Hybrid Framework for Risk-Aware HIV Suspicion Identification |
Rodrigo Morales-Sánchez, Soto Montalvo et al. |
cs.CL |
| 3 |
Metaphors in Literary Post-Editing: Opening Pandora's Box? |
Aletta G. Dorst, Mayra O. Nas et al. |
cs.CL |
| 3 |
Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation |
Zhifei Xie, Kaiyu Pang et al. |
|
| 3 |
iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance |
Jun Zheng, Zhengze Xu et al. |
|
| 3 |
SENSE: Satellite-based ENergy Synthesis for Sustainable Environment |
Kailai Sun, Mingyi He et al. |
|
| 3 |
ThoughtTrace: Understanding User Thoughts in Real-World LLM Interactions |
Chuanyang Jin, Binze Li et al. |
|
| 3 |
Base Models Look Human To AI Detectors |
Yixuan Even Xu, Ziqian Zhong et al. |
|
| 2 |
DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards |
Kaiyi Zhang, Wei Wu et al. |
cs.LG, cs.CL |
| 2 |
Mitigating Label Bias with Interpretable Rubric Embeddings |
Calvin Isley, Johann D. Gaebler et al. |
cs.LG |
| 2 |
Neural Negative Binomial Regression for Weekly Seismicity Forecasting: Per-Cell Dispersion Estimation and Tail Risk Assessment |
Alim Igilik |
physics.geo-ph, cs.LG, stat.ML |
| 2 |
LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models |
Abdullah Al Nomaan Nafi, Fnu Suya et al. |
cs.CL |
| 2 |
Do LLMs Know What Luxembourgish Borrows? Probing Lexical Neology in Low-Resource Multilingual Models |
Nina Hosseini-Kivanani |
cs.CL |
| 2 |
Learning from Language Feedback via Variational Policy Distillation |
Yang Li, Erik Nijkamp et al. |
|
| 2 |
Stable Audio 3 |
Zach Evans, Julian D. Parker et al. |
|
| 2 |
The Unlearnability Phenomenon in RLVR for Language Models |
Yulin Chen, He He et al. |
|
| 2 |
Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning |
Dian Zheng, Manyuan Zhang et al. |
|
| 2 |
UniT: Unified Geometry Learning with Group Autoregressive Transformer |
Haotian Wang, Yusong Huang et al. |
|
| 2 |
Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR |
Utkarsh Tyagi, Xingang Guo et al. |
|
| 2 |
Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks |
John T. Halloran, Noopur S. Bhatt |
|
| 1 |
Quantifying Hyperparameter Transfer and the Importance of Embedding Layer Learning Rate |
Dayal Singh Kalra, Maissam Barkeshli |
cs.LG, cond-mat.dis-nn, cs.AI, stat.ML |
| 1 |
Mind the Sim-to-Real Gap & Think Like a Scientist |
Harsh Parikh, Gabriel Levin-Konigsberg et al. |
cs.AI, cs.LG, stat.ME |
| 1 |
Ordering Matters: Rank-Aware Selective Fusion for Blended Emotion Recognition |
Junghyun Lee, Hyunseo Kim et al. |
cs.CV, cs.AI |
| 1 |
Findings of the Fifth Shared Task on Multilingual Coreference Resolution: Expanding Datasets for Long-Range Entities |
Michal Novák, Miloslav Konopík et al. |
cs.CL |
| 1 |
"I didn't Make the Micro Decisions": Measuring, Inducing, and Exposing Goal-Level AI Contributions in Collaboration |
Eunsu Kim, Jessica R. Mindel et al. |
cs.CL |
| 1 |
SymbolicLight V1: Spike-Gated Dual-Path Language Modeling with High Activation Sparsity and Sub-Billion-Scale Pre-Training Evidence |
Ting Liu |
cs.CL, cs.AI |
| 1 |
TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload |
Zhiben Chen, Youpeng Zhao et al. |
|
| 1 |
Toto 2.0: Time Series Forecasting Enters the Scaling Era |
Emaad Khwaja, Chris Lettieri et al. |
|
| 1 |
OcclusionFormer: Arranging Z-Order for Layout-Grounded Image Generation |
Ziye Li, Henghui Ding |
|
| 0 |
Variance Reduction for Expectations with Diffusion Teachers |
Jesse Bettencourt, Xindi Wu et al. |
cs.LG, cs.AI, cs.CV, stat.CO, stat.ML |
| 0 |
Approximation Theory for Neural Networks: Old and New |
Soumendu Sundar Mukherjee, Himasish Talukdar |
cs.LG, cond-mat.dis-nn, cs.AI, cs.NE |
| 0 |
PALS: Power-Aware LLM Serving for Mixture-of-Experts Models |
Can Hankendi, Rana Shahout et al. |
cs.AI, cs.DC |
| 0 |
EvoStruct: Bridging Evolutionary and Structural Priors for Antibody CDR Design via Protein Language Model Adaptation |
Mansoor Ahmed, Sujin Lee et al. |
cs.LG |
| 0 |
Velocityformer: Broken-Symmetry-Matched Equivariant Graph Transformers for Cosmological Velocity Reconstruction |
Tilman Tröster, David Mirkovic et al. |
astro-ph.CO, cs.LG |
| 0 |
Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning |
Yi Huang, Qingyun Sun et al. |
cs.LG |
| 0 |
A Machine Learning Framework for Weighted Least Squares GNSS Positioning based on Activation Functions |
Pin-Hsun Lee, Harry Leib |
cs.LG |
| 0 |
Gaussian Sheaf Neural Networks |
André Ribeiro, Ana Luiza Tenório et al. |
cs.LG, math.AT, math.CT |
| 0 |
Polynomial-Time Robust Multiclass Linear Classification under Gaussian Marginals |
Ilias Diakonikolas, Giannis Iakovidis et al. |
cs.LG, cs.DS |
| 0 |
Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks |
Qishi Zhan, Ziheng Chen et al. |
cs.LG |
| 0 |
Quantifying the cross-linguistic effects of syncretism on agreement attraction |
Utku Turk, Eva Neu |
cs.CL |
| 0 |
Post-Hoc Understanding of Metaphor Processing in Decoder-Only Language Models via Conditional Scale Entropy |
Lawhori Chakrabarti, Jennifer Johnson-Leung et al. |
cs.CL |
| 0 |
Manga109-v2026: Revisiting Manga109 Annotations for Modern Manga Understanding |
Jeonghun Baek, Atsuyuki Miyai et al. |
cs.CL, cs.AI, cs.CV |
| 0 |
DynMuon: A Dynamic Spectral Shaping View of Muon |
Fangzhou Wu, Rikhav Shah et al. |
|
| 0 |
Decoupling the Benefits of Subword Tokenization for Language Model Training via Byte-level Simulation |
Théo Gigant, Bowen Peng et al. |
|
| 0 |
Lost in the Folds: When Cross-Validation Is Not a Deep Ensemble for Uncertainty Estimation |
Kirscher Tristan, Bujotzek Markus et al. |
|
| 0 |
OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization |
Mark Boss, Vikram Voleti et al. |
|
| 0 |
PanoWorld: A Generative Spatial World Model for Consistent Whole-House Panorama Synthesis |
Jinrang Jia, Zhenjia Li et al. |
|
| 0 |
DrawMotion: Generating 3D Human Motions by Freehand Drawing |
Tao Wang, Lei Jin et al. |
|
| 0 |
Bug or Feature^2: Weight Drift, Activation Sparsity, and Spikes |
Egor Shvetsov, Aleksandr Serkov et al. |
|
| -1 |
Stitched Value Model for Diffusion Alignment |
Hyojun Go, Hyungjin Chung et al. |
|
| -2 |
HRM-Text: Efficient Pretraining Beyond Scaling |
Guan Wang, Changling Liu et al. |
|