arxivApr 17bullish

Shuffle the Context: RoPE-Perturbed Self-Distillation for Long-Context Adaptation

arXiv:2604.14339v1 Announce Type: new Abstract: Large language models (LLMs) increasingly operate in settings that require reliable long-context understanding, such as retrieval-augmented generation and multi-document reasoning. A common strategy is to fine-tune pretrained short-context models at th

MEQW2 models #long-context #language-models #self-distillation

arxivApr 10

Corruption-robust Offline Multi-agent Reinforcement Learning From Human Feedback

arXiv:2603.28281v2 Announce Type: replace Abstract: We consider robustness against data corruption in offline multi-agent reinforcement learning from human feedback (MARLHF) under a strong-contamination model: given a dataset $D$ of trajectory-preference tuples (each preference being an $n$-dimensio

#machine-learning #reinforcement-learning #robustness Read on arxiv →

arxivApr 9bearish

Non-identifiability of Explanations from Model Behavior in Deep Networks of Image Authenticity Judgments

arXiv:2604.07254v1 Announce Type: cross Abstract: Deep neural networks can predict human judgments, but this does not imply that they rely on human-like information or reveal the cues underlying those judgments. Prior work has addressed this issue using attribution heatmaps, but their explanatory va

VGEFBA3 models #computer-vision #machine-learning #explanability Read on arxiv →

arxivApr 6

Towards Realistic Class-Incremental Learning with Free-Flow Increments

arXiv:2604.02765v1 Announce Type: new Abstract: Class-incremental learning (CIL) is typically evaluated under predefined schedules with equal-sized tasks, leaving more realistic and complex cases unexplored. However, a practical CIL system should learns immediately when any number of new classes arr

#class-incremental-learning #machine-learning #robustness Read on arxiv →