RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published Oct 1 • 49
Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models Paper • 2609.39820 • Published Sep 30 • 12
Selecting The Most Informative Tokens in Natural Language Autoencoders Paper • 2609.37040 • Published Sep 29 • 15
Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression Paper • 2609.36322 • Published Sep 28 • 31
Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies Paper • 2609.38155 • Published Sep 29 • 73
VoxMem: Benchmarking Multimodal Memory in Large Audio Language Models Paper • 2609.32607 • Published Sep 26 • 32