When Choices Become Priors: Contrastive Decoding for Scientific Figure Multiple-Choice QA Paper • 2603.28026 • Published Mar 30 • 1
ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time? Paper • 2606.05553 • Published 3 days ago • 42
TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration Paper • 2606.04743 • Published 4 days ago • 37
CLAG: Adaptive Memory Organization via Agent-Driven Clustering for Small Language Model Agents Paper • 2603.15421 • Published Apr 20 • 23
MolDeTox: Evaluating Language Model's Stepwise Fragment Editing for Molecular Detoxification Paper • 2605.12181 • Published 26 days ago • 8
ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack Paper • 2509.25843 • Published Apr 14 • 19
Lost in the Noise: How Reasoning Models Fail with Contextual Distractors Paper • 2601.07226 • Published Jan 12 • 33
User-Oriented Multi-Turn Dialogue Generation with Tool Use at scale Paper • 2601.08225 • Published Jan 13 • 53
The Curious Case of Analogies: Investigating Analogical Reasoning in Large Language Models Paper • 2511.20344 • Published Nov 25, 2025 • 14
Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards Paper • 2506.11474 • Published Jun 13, 2025 • 18
GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts Paper • 2509.25160 • Published Sep 29, 2025 • 32
Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training Paper • 2509.25758 • Published Sep 30, 2025 • 25
CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction Paper • 2508.03159 • Published Aug 5, 2025 • 23
Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models Paper • 2506.19697 • Published Jun 24, 2025 • 44