works on

From the 1 of 38 linked papers with an AI index.

activity
20242026
most citedKimi K2.5: Visual Agentic Intelligence

2 citations · 3 across the 30 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2026

TaoBench: Do Automated Theorem Prover LLMs Generalize Beyond MathLib?

Alexander K Taylor, Junyi Zhang, Ethan Ji +10

Automated theorem proving (ATP) benchmarks largely consist of problems formalized in MathLib, so current ATP training and evaluation are heavily biased toward MathLib's definitiona…

cs.LG2026

Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training

Junkai Zhang, Zihao Wang, Lin Gui +7

Reinforcement fine-tuning (RFT) often suffers from reward over-optimization, where a policy model hacks the reward signals to achieve high scores while producing low-quality output…

cs.LG2026

DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning

Haoxiang Sun, Lizhen Xu, Bing Zhao +5

Reinforcement Learning with Verifiable Rewards (RLVR) has been shown effective in enhancing the visual reflection and reasoning capabilities of Large Multimodal Models (LMMs). Howe…

cs.LG2026

What Do Agents Learn from Trajectory-SFT: Semantics or Interfaces?

Weizheng Gu, Chengze Li, Zhuohao Yu +6

Large language models are increasingly evaluated as interactive agents, yet standard agent benchmarks conflate two qualitatively distinct sources of success: semantic tool-use and…

cs.LG2025

Generative Actor Critic

Aoyang Qin, Deqian Kong, Wei Wang +3

Conventional Reinforcement Learning (RL) algorithms, typically focused on estimating or maximizing expected returns, face challenges when refining offline pretrained models with on…

cs.LG2025

When Inverse Data Outperforms: Exploring the Pitfalls of Mixed Data in Multi-Stage Fine-Tuning

Mengyi Deng, Xin Li, Tingyu Zhu +3

Existing work has shown that o1-level performance can be achieved with limited data distillation, but most existing methods focus on unidirectional supervised fine-tuning (SFT), ov…