4 citations · 6 across the 20 of their papers we have counts for
20 papers
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…
When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL
Jiakang Wang, Runze Liu, Qingpeng Cai +7
Reinforcement learning (RL) has shown great promise in large language models (LLMs) post-training, which typically rely on token-level clipping to maintain stability during optimiz…
Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
Runze Liu, Jiakang Wang, Yuling Shi +11
Reinforcement Learning (RL) has shown remarkable success in enhancing the reasoning capabilities of Large Language Models (LLMs). Process-Supervised RL (PSRL) has emerged as a more…
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…
AR-GRPO: Training Autoregressive Image Generation Models via Reinforcement Learning
Shihao Yuan, Yahui Liu, Yang Yue +5
Inspired by the success of reinforcement learning (RL) in refining large language models (LLMs), we propose AR-GRPO, an approach to integrate online RL training into autoregressive…
Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization
Zhenpeng Su, Leiyu Pan, Xue Bai +8
We present Klear-Reasoner, a model with long reasoning capabilities that demonstrates careful deliberation during problem solving, achieving outstanding performance across multiple…
Agentic Reinforced Policy Optimization
Guanting Dong, Hangyu Mao, Kai Ma +11
Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn rea…
Leanabell-Prover-V2: Verifier-integrated Reasoning for Formal Theorem Proving via Reinforcement Learning
Xingguang Ji, Yahui Liu, Qi Wang +7
We introduce our Leanabell-Prover-V2, a 7B large language models (LLMs) that can produce formal theorem proofs in Lean 4, with verifier-integrated Long Chain-of-Thoughts (CoT). Fol…
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…
Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR
Jiakang Wang, Runze Liu, Fuzheng Zhang +4
Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training method for improving the reasoning abilities of Large Language Models (LLMs). However, e…
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…
What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning
Gangwei Jiang, Yahui Liu, Zhaoyi Li +5
Recent advances in reasoning with large language models (LLMs) have popularized Long Chain-of-Thought (LCoT), a strategy that encourages deliberate and step-by-step reasoning befor…
TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos
Fanheng Kong, Jingyuan Zhang, Hongzhi Zhang +7
Videos are unique in their integration of temporal elements, including camera, scene, action, and attribute, along with their dynamic relationships over time. However, existing ben…
Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval
Fanheng Kong, Jingyuan Zhang, Yahui Liu +8
Multimodal information retrieval (MIR) faces inherent challenges due to the heterogeneity of data sources and the complexity of cross-modal alignment. While previous studies have i…
Clapper: Compact Learning and Video Representation in VLMs
Lingyu Kong, Hongzhi Zhang, Jingyuan Zhang +4
Current vision-language models (VLMs) have demonstrated remarkable capabilities across diverse video understanding applications. Designing VLMs for video inputs requires effectivel…
Data Metabolism: An Efficient Data Design Schema For Vision Language Model
Jingyuan Zhang, Hongzhi Zhang, Zhou Haonan +7
Data curation plays a crucial role in training powerful Visual Language Models (VLMs). In this work, we introduce the concept of Data Metabolism and present our data-centric framew…
Capybara-OMNI: An Efficient Paradigm for Building Omni-Modal Language Models
Xingguang Ji, Jiakang Wang, Hongzhi Zhang +6
With the development of Multimodal Large Language Models (MLLMs), numerous outstanding accomplishments have emerged within the open-source community. Due to the complexity of creat…
Routing to the Right Expertise: A Trustworthy Judge for Instruction-based Image Editing
Chenxi Sun, Hongzhi Zhang, Qi Wang +1
Instruction-based Image Editing (IIE) models have made significantly improvement due to the progress of multimodal large language models (MLLMs) and diffusion models, which can und…
Leanabell-Prover: Posttraining Scaling in Formal Reasoning
Jingyuan Zhang, Qi Wang, Xingguang Ji +6
Recent advances in automated theorem proving (ATP) through LLMs have highlighted the potential of formal reasoning with Lean 4 codes. However, ATP has not yet be revolutionized by…