Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs
Paper • 2608.12781 • Published • 35
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities
CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward
zsytony
submitted a
paper to Daily Papers 10 days ago
dongsheng
authored a
paper 20 days ago
yuhangzang
authored 2
papers 20 days ago
Sudanl
authored a
paper about 1 month ago
vanilla1116
submitted a
paper to Daily Papers about 1 month ago
Sudanl
authored a
paper about 1 month ago
dongsheng
authored a
paper about 1 month ago
Tsumugii
submitted a
paper to Daily Papers about 2 months ago
vanilla1116
submitted a
paper to Daily Papers about 2 months ago
yuhangzang
authored 2
papers 3 months ago
dongsheng
submitted a
paper to Daily Papers 3 months ago
dongsheng
authored a
paper 3 months ago
ZwwWayne
authored 6
papers 3 months ago
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
Paper • 2508.18265 • Published • 226
MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization
Paper • 2510.08540 • Published • 110
Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving
Paper • 2405.05258 • Published
An Empirical Study of Training State-of-the-Art LiDAR Segmentation Models
Paper • 2405.14870 • Published
Achieving Olympia-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning
Paper • 2512.10534 • Published • 33
OPV: Outcome-based Process Verifier for Efficient Long Chain-of-Thought Verification
Paper • 2512.10756 • Published • 35