9 papers · 1 filter
From Solving to Verifying: A Unified Objective for Robust Reasoning in LLMs
Xiaoxuan Wang, Bo Liu, Song Jiang +4
The reasoning capabilities of large language models (LLMs) have been significantly improved through reinforcement learning (RL). Nevertheless, LLMs still struggle to consistently v…
PROF: An LLM-based Reward Code Preference Optimization Framework for Offline Imitation Learning
Shengjie Sun, Jiafei Lyu, Runze Liu +4
Offline imitation learning (offline IL) enables training effective policies without requiring explicit reward annotations. Recent approaches attempt to estimate rewards for unlabel…
SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models
Chenyu Wang, Paria Rashidinejad, DiJia Su +9
Diffusion large language models (dLLMs) are emerging as an efficient alternative to autoregressive models due to their ability to decode multiple tokens in parallel. However, align…
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
Terry Yue Zhuo, Xiaolong Jin, Hange Liu +37
Crowdsourced model evaluation platforms, such as Chatbot Arena, enable real-time evaluation from human perspectives to assess the quality of model responses. In the coding domain,…
GEM: A Gym for Agentic LLMs
Zichen Liu, Anya Sims, Keyu Duan +16
The training paradigm for large language models (LLMs) is moving from static datasets to experience-based learning, where agents acquire skills via interacting with complex environ…
Inpainting-Guided Policy Optimization for Diffusion Large Language Models
Siyan Zhao, Mengchen Liu, Jing Huang +8
Masked diffusion large language models (dLLMs) are emerging as promising alternatives to autoregressive LLMs, offering competitive performance while supporting unique generation ca…
Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play
Qinsi Wang, Bo Liu, Tianyi Zhou +6
Although reinforcement learning (RL) has emerged as a promising approach for improving vision-language models (VLMs) and multimodal large language models (MLLMs), current methods r…
MAPGD: Multi-Agent Prompt Gradient Descent for Collaborative Prompt Optimization
Yichen Han, Yuhang Han, Siteng Huang +7
Prompt engineering is crucial for fully leveraging large language models (LLMs), yet most existing optimization methods follow a single trajectory, resulting in limited adaptabilit…
TAD-Bench: A Comprehensive Benchmark for Embedding-Based Text Anomaly Detection
Yang Cao, Sikun Yang, Chen Li +5
Text anomaly detection is crucial for identifying spam, misinformation, and offensive language in natural language processing tasks. Despite the growing adoption of embedding-based…