Base Models Can Reason By Taking a Cue From Training Data Paper • 2610.06851 • Published 6 days ago • 24
The Functionalizer: Lossless Functional Decomposition for Subword Tokenization Paper • 2609.15991 • Published 23 days ago • 17
The Functionalizer: Lossless Functional Decomposition for Subword Tokenization Paper • 2609.15991 • Published 23 days ago • 17
ModaLens: Measuring Image Sensitivity in Report-Conditioned Medical VLMs Paper • 2609.15635 • Published 27 days ago • 8
Towards a Deterministic Math Solver for Clinical Language Models Paper • 2609.10728 • Published Sep 9 • 2
Modular Cognitive Architecture Emerges in Large Language Models Paper • 2608.13567 • Published Jun 27 • 16
Agents Catching Agents: Shortcut Cascades and Benchmark Gaming in Clinical Multi-Agent Systems Paper • 2608.03744 • Published Aug 4 • 6
Loud or Silent? A Reusable Framework for Per-Modality Failure Analysis in Multimodal Clinical AI Paper • 2608.01462 • Published Aug 2 • 4
Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination Paper • 2607.00924 • Published Jul 1 • 10
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments Paper • 2606.13681 • Published Jun 11 • 146
SENSE: Satellite-based ENergy Synthesis for Sustainable Environment Paper • 2605.18101 • Published May 18 • 13
PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents Paper • 2605.19932 • Published May 19 • 5
PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents Paper • 2605.19932 • Published May 19 • 5
EquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers Paper • 2604.09130 • Published Apr 10 • 4
Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models Paper • 2603.24844 • Published Mar 25 • 9