PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization Paper • 2608.30597 • Published 16 days ago • 26
SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem Paper • 2609.07064 • Published 9 days ago • 139
PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization Paper • 2608.30597 • Published 16 days ago • 26
Rethinking Personalized Reward Modeling for LLMs under Preference Heterogeneity via Group-Debiased Federated Learning Paper • 2608.01556 • Published Aug 3
Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation Paper • 2609.08798 • Published 8 days ago • 94
UniSAFE: A Comprehensive Benchmark for Safety Evaluation of Unified Multimodal Models Paper • 2603.17476 • Published Mar 18
When and Where to Attack? Stage-wise Attention-Guided Adversarial Attack on Large Vision Language Models Paper • 2602.04356 • Published Feb 4
mSFT: Addressing Dataset Mixtures Overfiting Heterogeneously in Multi-task SFT Paper • 2603.21606 • Published Mar 23 • 39
MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models Paper • 2602.17602 • Published Feb 19 • 56
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation Paper • 2507.10524 • Published Jul 14, 2025 • 76
EXAONE-Deep Collection EXAONE reasoning model series of 2.4B, 7.8B, and 32B, optimized for reasoning tasks including math and coding • 10 items • Updated Jul 7, 2025 • 99
DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs Paper • 2503.07067 • Published Mar 10, 2025 • 34