CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation Paper • 2602.24286 • Published 18 days ago • 88
Lost in Backpropagation: The LM Head is a Gradient Bottleneck Paper • 2603.10145 • Published 7 days ago • 10
Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights Paper • 2603.12228 • Published 5 days ago • 10
Prism-Δ: Differential Subspace Steering for Prompt Highlighting in Large Language Models Paper • 2603.10705 • Published 6 days ago • 11
One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers Paper • 2603.12245 • Published 5 days ago • 17
WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing Paper • 2603.11593 • Published 6 days ago • 22
Reasoning Models Struggle to Control their Chains of Thought Paper • 2603.05706 • Published 12 days ago • 28
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections Paper • 2603.12180 • Published 5 days ago • 59
Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs Paper • 2603.09906 • Published 7 days ago • 66
Lost in Stories: Consistency Bugs in Long Story Generation by LLMs Paper • 2603.05890 • Published 12 days ago • 84
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning Paper • 2603.04597 • Published 13 days ago • 193
Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents Paper • 2603.12634 • Published 5 days ago • 6
Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation Paper • 2603.12793 • Published 5 days ago • 31
Implicit Intelligence -- Evaluating Agents on What Users Don't Say Paper • 2602.20424 • Published 22 days ago • 4
Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting Paper • 2602.20933 • Published 21 days ago • 4
Causal Motion Diffusion Models for Autoregressive Motion Generation Paper • 2602.22594 • Published 20 days ago • 7