Useful Memories Become Faulty When Continuously Updated by LLMs Paper • 2605.12978 • Published 9 days ago • 19
Heterogeneous Scientific Foundation Model Collaboration Paper • 2604.27351 • Published 22 days ago • 217
SoundWeaver: Semantic Warm-Starting for Text-to-Audio Diffusion Serving Paper • 2603.07865 • Published Mar 9 • 3
ReIn: Conversational Error Recovery with Reasoning Inception Paper • 2602.17022 • Published Feb 19 • 1
InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning Paper • 2601.14209 • Published Jan 20 • 6
InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning Paper • 2601.14209 • Published Jan 20 • 6
Dr. Zero: Self-Evolving Search Agents without Training Data Paper • 2601.07055 • Published Jan 11 • 22
A Rising Tide Lifts All Boats: MTQE Rewards for Idioms Improve General Translation Quality Paper • 2601.06307 • Published Jan 9 • 1
ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning Paper • 2510.12693 • Published Oct 14, 2025 • 28
WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks Paper • 2601.02439 • Published Jan 5 • 18
Embodied Referring Expression Comprehension in Human-Robot Interaction Paper • 2512.06558 • Published Dec 6, 2025 • 3
LUQ: Layerwise Ultra-Low Bit Quantization for Multimodal Large Language Models Paper • 2509.23729 • Published Sep 28, 2025
AstroLLaMA: Towards Specialized Foundation Models in Astronomy Paper • 2309.06126 • Published Sep 12, 2023 • 18
Beyond the Lens: Quantifying the Impact of Scientific Documentaries through Amazon Reviews Paper • 2502.08705 • Published Feb 12, 2025
GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis Paper • 2507.21035 • Published Jul 28, 2025 • 3
Energy-Based Transformers are Scalable Learners and Thinkers Paper • 2507.02092 • Published Jul 2, 2025 • 70
Can Vision Language Models Infer Human Gaze Direction? A Controlled Study Paper • 2506.05412 • Published Jun 4, 2025 • 5
Beyond Pixels: Exploring Human-Readable SVG Generation for Simple Images with Vision Language Models Paper • 2311.15543 • Published Nov 27, 2023