AI.info

Xunliang Cai

Explore Xunliang Cai on AI.info.

• AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations
• SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining
• Exploring Reasoning Reward Model for Agents
• BAPO: Boundary-Aware Policy Optimization for Reliable Agentic Search
• Scaling and Transferability of Annealing Strategies in Large Language Model Training
• OneThinker: All-in-one Reasoning Model for Image and Video
• Counteracting Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing
• PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling
• Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views
• UNO-Bench: A Unified Benchmark for Exploring the Compositional Law Between Uni-modal and Omni-modal in Omni Models