Submitted by shenzhi-wang 92 Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning · 18 authors 2
Submitted by zafstojano 44 REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards · 7 authors 3
Submitted by andito 42 SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics · 14 authors 5
Submitted by ZedongWangAI 31 Taming LLMs by Scaling Learning Rates with Gradient Grouping · 7 authors 3
Submitted by rhyang2021 25 ARIA: Training Language Agents with Intention-Driven Reward Aggregation · 8 authors 1
Submitted by wangzifu 24 Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles · 7 authors 1
Submitted by yejunliang23 22 ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding · 5 authors 1
Submitted by kinam0252 22 Temporal In-Context Fine-Tuning for Versatile Control of Video Diffusion Models · 3 authors 1
Submitted by karrykkk 22 LoHoVLA: A Unified Vision-Language-Action Model for Long-Horizon Embodied Tasks · 5 authors 1
Submitted by lemonaddie 20 Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control · 8 authors 1
Submitted by che111 20 SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning · 13 authors 1
Submitted by sy1998 17 EarthMind: Towards Multi-Granular and Multi-Sensor Earth Observation with Large Multimodal Models · 8 authors 1
Submitted by xssstory 16 AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning · 13 authors 1
Submitted by Ray2333 14 MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning · 8 authors 1
Submitted by yolay 11 Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models · 9 authors 1
Submitted by MasterZhou 10 Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs · 10 authors 1
Submitted by Amirhossein-Alimohammadi 10 Cora: Correspondence-aware image editing using few step diffusion · 6 authors 1
Submitted by AtsuMiyai 9 WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks · 12 authors 3
Submitted by zhangchenxu 8 VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL · 8 authors 1
Submitted by yeonseokjeong 8 From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval · 3 authors 1
Submitted by yizecheng 8 DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors · 4 authors 1
Submitted by alemiaschi 7 Stress-testing Machine Generated Text Detection: Shifting Language Models Writing Style to Fool Detectors · 7 authors 1
Submitted by FreaxRuby 6 WHEN TO ACT, WHEN TO WAIT: Modeling Structural Trajectories for Intent Triggerability in Task-Oriented Dialogue · 8 authors 1
Submitted by pyf98 6 OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning · 7 authors 1
Submitted by iliashum 6 Cascading Adversarial Bias from Injection to Distillation in Language Models · 6 authors 1
Submitted by zd11024 6 Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors · 4 authors 1
Submitted by ChenDY 6 Normalized Attention Guidance: Universal Negative Guidance for Diffusion Model · 4 authors 2
Submitted by Saibo-creator 5 zip2zip: Inference-Time Adaptive Vocabularies for Language Models via Token Compression · 7 authors 1
Submitted by CNcreator0331 5 Pro3D-Editor : A Progressive-Views Perspective for Consistent and Precise 3D Editing · 4 authors 1
Submitted by Taoer 5 Stepsize anything: A unified learning rate schedule for budgeted-iteration training · 5 authors 1
Submitted by vinthony 5 VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning · 4 authors 1
Submitted by shuzyuan 4 LLM in the Loop: Creating the PARADEHATE Dataset for Hate Speech Detoxification · 7 authors 2
Submitted by xwjzds 4 SATA-BENCH: Select All That Apply Benchmark for Multiple Choice Questions · 6 authors 1
Submitted by matthieufp 4 ComposeAnything: Composite Object Priors for Text-to-Image Generation · 3 authors 2
Submitted by Shengran 4 Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents · 5 authors 1
Submitted by Omartificial-Intelligence-Space 3 From Guidelines to Practice: A New Paradigm for Arabic Language Model Evaluation · 6 authors 2
Submitted by Omartificial-Intelligence-Space 3 From Guidelines to Practice: A New Paradigm for Arabic Language Model Evaluation · 6 authors 2
Submitted by bing-li-ai 3 OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions · 5 authors 1
Submitted by itaynakash 3 Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models · 4 authors 1
Submitted by kargaranamir 2 How Programming Concepts and Neurons Are Shared in Code Language Models · 4 authors 1
Submitted by Rabinovich 2 RARE: Retrieval-Aware Robustness Evaluation for Retrieval-Augmented Generation Systems · 8 authors 1
Submitted by Shiweiliuiiiiiii 2 LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning · 8 authors 1
Submitted by JJ-TMT 2 CityLens: Benchmarking Large Language-Vision Models for Urban Socioeconomic Sensing · 7 authors 1
Submitted by xiaobinzhuang 2 MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation · 12 authors 1
Submitted by attentionisallyouneed369 2 Neuro2Semantic: A Transfer Learning Framework for Semantic Reconstruction of Continuous Language from Human Intracranial EEG · 6 authors 1
Submitted by mgolov 2 Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts · 6 authors 1
Submitted by tuvu 1 SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models · 6 authors 1
Submitted by arnodjiang 1 IVY-FAKE: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detection · 6 authors 1
Submitted by jisx 1 Massively Multilingual Adaptation of Large Language Models Using Bilingual Translation Data · 6 authors 1
Submitted by prasannareddyp 1 Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation · 6 authors 1
Submitted by susanliang 1 BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Models · 10 authors 1
Submitted by yongchao98 1 R1-Code-Interpreter: Training LLMs to Reason with Code via Supervised and Reinforcement Learning · 7 authors 1
Submitted by vickywu 1 MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability · 9 authors 1
Submitted by chtmp223 1 Frankentext: Stitching random text fragments into long-form narratives · 4 authors 1
Submitted by junhongmit 1 Plan and Budget: Effective and Efficient Test-Time Scaling on Large Language Model Reasoning · 7 authors 1
Submitted by PoTaTo721 1 MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labeling · 3 authors 1
Submitted by Floki00 - Synthesis of discrete-continuous quantum circuits with multimodal diffusion models · 5 authors 1
Submitted by domiso - SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillation · 7 authors 1