OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs Paper • 2608.21360 • Published 28 days ago • 31
OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs Paper • 2608.21360 • Published 28 days ago • 31
EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory Paper • 2606.21649 • Published Jun 19 • 36 • 3
EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory Paper • 2606.21649 • Published Jun 19 • 36
EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory Paper • 2606.21649 • Published Jun 19 • 36
OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains Paper • 2606.14702 • Published Jun 12 • 33
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application Paper • 2606.12191 • Published Jun 10 • 73
UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification Paper • 2605.06221 • Published May 7 • 22
Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models Paper • 2604.08545 • Published Apr 9 • 42
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding Paper • 2604.05015 • Published Apr 6 • 236