Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models Paper • 2604.08545 • Published Apr 9 • 41
MM-CondChain: A Programmatically Verified Benchmark for Visually Grounded Deep Compositional Reasoning Paper • 2603.12266 • Published Mar 12 • 19
SwimBird: Eliciting Switchable Reasoning Mode in Hybrid Autoregressive MLLMs Paper • 2602.06040 • Published Feb 5 • 10
AdaptMMBench: Benchmarking Adaptive Multimodal Reasoning for Mode Selection and Reasoning Process Paper • 2602.02676 • Published Feb 2 • 10
You Only Forward Once: An Efficient Compositional Judging Paradigm Paper • 2511.16600 • Published Nov 20, 2025 • 7
Adversarial Data Collection: Human-Collaborative Perturbations for Efficient and Robust Robotic Imitation Learning Paper • 2503.11646 • Published Mar 14, 2025 • 34
WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs Paper • 2502.04326 • Published Feb 6, 2025 • 2
SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners Paper • 2408.16768 • Published Aug 29, 2024 • 28
