collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2026

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs

Kejian Zhu, Zhuoran Jin, Shangqing Tu +5

Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) exhibit fundamentally different behaviors in enhancing multi-task reasoning for large language models (LLMs). Our preli…

cs.CL2026

From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization

Chenxi Zhou, Pengfei Cao, Jiang Li +4

Post-Training Quantization (PTQ) is critical for the efficient deployment of Large Language Models (LLMs). While 4-bit quantization is widely regarded as an optimal trade-off, redu…

cs.CL2026

MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning

Jiachun Li, Shaoping Huang, Zhuoran Jin +5

Recent progress in the reasoning capabilities of multimodal large language models (MLLMs) has empowered them to address more complex tasks such as scientific analysis and mathemati…

cs.CL2025

Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences

Zhuoran Jin, Hongbang Yuan, Kejian Zhu +5

Reward models (RMs) play a critical role in aligning AI behaviors with human preferences, yet they face two fundamental challenges: (1) Modality Imbalance, where most RMs are mainl…

cs.CL2025

Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents

Tianyi Men, Zhuoran Jin, Pengfei Cao +3

As Multimodal Large Language Models (MLLMs) advance, multimodal agents show promise in real-world tasks like web navigation and embodied intelligence. However, due to limitations i…

cs.CL2025

Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis

Kejian Zhu, Shangqing Tu, Zhuoran Jin +3

The development of large language models (LLMs) depends on trustworthy evaluation. However, most current evaluations rely on public benchmarks, which are prone to data contaminatio…