5 papers
MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation
Yutong Wang, Pengliang Ji, Chaoqun Yang +4
The LLM-as-a-Judge paradigm shows promise for evaluating generative content but lacks reliability in reasoning-intensive scenarios, such as programming. Inspired by recent advances…
LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning
Zihang Liu, Tianyu Pang, Oleg Balabanov +5
Recent studies have shown that supervised fine-tuning of LLMs on a small number of high-quality datasets can yield strong reasoning capabilities. However, full fine-tuning (Full FT…
Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale
David Acuna, Chao-Han Huck Yang, Yuntian Deng +6
Despite rapid progress, multimodal reasoning still lacks a systematic approach to synthesize large-scale vision-centric datasets beyond visual math. We introduce a framework able t…
BrailleLLM: Braille Instruction Tuning with Large Language Models for Braille Domain Tasks
Tianyuan Huang, Zepeng Zhu, Hangdi Xing +6
Braille plays a vital role in education and information accessibility for visually impaired individuals. However, Braille information processing faces challenges such as data scarc…
UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens
Ruichuan An, Sihan Yang, Renrui Zhang +10
Personalized models have demonstrated remarkable success in understanding and generating concepts provided by users. However, existing methods use separate concept tokens for under…