Author

Sheng Xu

h-index 16 View on Semantic Scholar

We have 6 of 46 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2026

DIPrune: Task-Aware Token Pruning with Dual Importance for Efficient Multimodal Language Models

Recent training-free pruning approaches for Multimodal Large Language Models (MLLMs) effectively cut computational overhead by exploiting visual redundancy or text-vision attention. However, they frequently suffer from semantic degradation due to their task-agnostic design or unreliable attention estimates. Based on ou...

Shuo Yang, Chang-Bai Li, Lin-Lin Yang et al. · 0 citations

#machine learning Preprint Sep 2026

GraphHCA: Closed-Form Hindsight Credit Assignment for Long-Horizon LLM Agents

GraphHCA is proposed, a model-free realization of HCA that eliminates explicit hindsight-distribution estimation and achieves state-of-the-art results on ALFWorld and WebShop at both LLM scales, and on Sokoban with a vision-language agent.

Hao-Dong Zhu, Yang-Yang Ren, Chang-Bai Li et al. · 0 citations

#machine learning Preprint Sep 2026

Cross-Rollout Bellman Closure for Long-Horizon Agentic Reinforcement Learning

Cross-Rollout Bellman Closure (CRBC) is introduced, which merges each rollout group into a finite empirical process with absorbing success and failure boundaries and evaluates its behavior-policy Bellman fixed point with one linear solve.

Yang-Yang Ren, Hao-Dong Zhu, Lin-Lin Yang et al. · 0 citations

#machine learning Preprint Sep 2026

MaPP: A Unified Marginalized Posterior-Predictive Framework for Data-Efficient RLVR

MaPP (Marginalized Posterior-Predictive), a unified framework for data-efficient RLVR that denoises response-level advantage estimation and improves prompt selection using a shared Beta posterior, is proposed.

Yang-Yang Ren, Hao-Dong Zhu, Sheng Xu et al. · 0 citations

#machine learning Jul 2025

Squeeze10-LLM: Squeezing LLMs' Weights by 10 Times via a Staged Mixed-Precision Quantization Method

Squeeze10-LLM is a staged mixed-precision post-training quantization (PTQ) framework and achieves state-of-the-art performance for sub-2bit weight-only quantization, improving average accuracy from 43% to 56% on six zero-shot classification tasks--a significant boost over existing PTQ methods.

Qingcheng Zhu, Yang-Yang Ren, Lin-Lin Yang et al. · arXiv.org · 1 citation

Jul 2026

Kalman Meets Curriculum: Efficient Dynamic Prompt Selection for Adaptive RL Finetuning

A Kalman-Guided Prompt Selection method (KGPS), which reformulates prompt selection as a dynamic state estimation problem rather than static difficulty prediction, and consistently improves both final accuracy and rollout efficiency over strong baselines, establishing state-of-the-art performance among online prompt se...

Hao-Dong Zhu, Yang-Yang Ren, Yanjing Li et al. · arXiv.org · 2 citations · ⚡2