collaborators

8 papers

cs.IR2026

LEAPS: An LLM-Empowered Adaptive Plugin in Taobao AI Search

Lei Wang, Jinhang Wu, Zhibin Wang +1

The rapid rise of large language models has shifted user search behavior from discrete keywords to natural-language, multi-constraint queries--a shift existing e-commerce search ar…

cs.CL2026

AgentSkiller: Scaling Generalist Agent Intelligence through Semantically Integrated Cross-Domain Data Synthesis

Zexu Sun, Bokai Ji, Hengyi Cai +4

Large Language Model agents demonstrate potential in solving real-world problems via tools, yet generalist intelligence is bottlenecked by scarce high-quality, long-horizon data. E…

cs.LG2026

Internalizing LLM Reasoning via Discovery and Replay of Latent Actions

Zhenning Shi, Yijia Zhu, Junhan Shi +3

The internalization of chain-of-thought processes into hidden states has emerged as a highly efficient paradigm for scaling test-time compute. However, existing activation steering…

cs.LG2026

Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models

Ziwei Luo, Ziqi Jin, Lei Wang +2

This work presents self-rewarding sequential Monte Carlo (SMC), an inference-time scaling algorithm enabling effective sampling of masked diffusion language models (MDLMs). Our alg…

cs.CL2026

How Order-Sensitive Are LLMs? OrderProbe for Deterministic Structural Reconstruction

Yingjie He, Zhaolu Kang, Kehan Jiang +19

Large language models (LLMs) excel at semantic understanding, yet their ability to reconstruct internal structure from scrambled inputs remains underexplored. Sentence-level restor…

cs.LG2025

FedReFT: Federated Representation Fine-Tuning with All-But-Me Aggregation

Fatema Siddika, Md Anwar Hossen, J. Pablo Muñoz +3

Parameter-efficient fine-tuning (PEFT) adapts large pre-trained models by updating only a small subset of parameters. Recently, Representation Fine-Tuning (ReFT) has emerged as an…