12 papers
DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing
Hongzhi Zhang, Yuanze Hu, Tinghai Zhang +9
The evolution of Large Language Models (LLMs) towards autonomous agents has catalyzed progress in Deep Research. While retrieval capabilities are well-benchmarked, the post-retriev…
Klear-AgentForge: Forging Agentic Intelligence through Posttraining Scaling
Qi Wang, Hongzhi Zhang, Jia Fu +12
Despite the proliferation of powerful agentic models, the lack of critical post-training details hinders the development of strong counterparts in the open-source community. In thi…
Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learning
Jia Fu, Xinyu Yang, Hongzhi Zhang +5
Precise, correct feedback is crucial for effectively training large language models (LLMs) in code reinforcement learning. However, synthesizing high-quality test cases remains a p…
RLEP: Reinforcement Learning with Experience Replay for LLM Reasoning
Hongzhi Zhang, Jia Fu, Jingyuan Zhang +4
Reinforcement learning (RL) for large language models is an energy-intensive endeavor: training can be unstable, and the policy may gradually drift away from its pretrained weights…
Evaluating Multimodal Large Language Models on Video Captioning via Monte Carlo Tree Search
Linhao Yu, Xinguang Ji, Yahui Liu +7
Video captioning can be used to assess the video understanding capabilities of Multimodal Large Language Models (MLLMs). However, existing benchmarks and evaluation protocols suffe…
DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding
Hongzhi Zhang, Jingyuan Zhang, Xingguang Ji +2
Typical video modeling methods, such as LLava, represent videos as sequences of visual tokens, which are then processed by the LLM backbone for effective video understanding. Howev…