Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models Paper • 2602.00217 • Published Jan 30 • 1
Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs Paper • 2606.26387 • Published Jun 24 • 1
Creativity or Brute Force? Using Brainteasers as a Window into the Problem-Solving Abilities of Large Language Models Paper • 2505.10844 • Published May 16, 2025
CTR-LoRA: Curvature-Aware and Trust-Region Guided Low-Rank Adaptation for Large Language Models Paper • 2510.15962 • Published Oct 11, 2025