Skip to content

Author

Guan-Jun Jiang

We have 10 of 23 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 Nov 2026

Reward Budgeting Reduces Premature Convergence in Reinforcement Learning for LLM Reasoning

RL for LLM reasoning often plateaus early as its policy sharpens. Policy entropy is studied as both a diagnostic and a control signal, but increasing it alone does not reliably change the eventual plateau in our experiments. We analyze RL's implicit target policy using a sharpness factor $\kappa$ and effective counterp...

Meng-Ni Jia, Meng-Yu Zhou, Xiao-Xi Jiang et al. · 0 citations
Preprint Oct 2026

A Lightweight Velocity Correction Framework for Improving Instruction Following in Few-Step Text-to-Image Generation

Few-step text-to-image generators produce high-quality images with few network forward passes, yet struggle with complex prompts involving multiple subjects, interactions, spatial relations, counting, and attribute binding. Can these errors be reduced without changing the generator's parameters or increasing its forwar...

Ya-Ting Gao, Zheng Zhu, Zi-Hao Wen et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Teacher-Student Gaps Are Not Enough: Outcome-Guided On-Policy Distillation for Multi-Turn Autonomous Agents

Outcome-Guided On-Policy Distillation is proposed, which applies trajectory-relative weighting to teacher supervision and calibrates these weights using final task outcomes from paired student continuations and selectively strengthens supervision on the student's original trajectories at turns where teacher guidance be...

Tong Zhang, Zhou Liu, Yi-Hao Liu et al. · 0 citations
#artificial intelligence Open access Sep 2026

Token-Disentangled Latent Test-Time Scaling for Vision-Language Reasoning

This work presents Token-Disentangled Latent Test-Time Scaling, an inference-time framework that makes latent refinement token-role-aware and outperforms strong output-space test-time scaling baselines under matched decoded-candidate budgets.

Hao-Xuan Ma, Yi-Hao Liu, Yu-Tao Sun et al. · 0 citations

Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective

ConSPO is a Contrastive Sequence-level Policy Optimization method that uses length-normalized sequence log-probabilities as rollout scores and contrasts verified positive rollouts against negative distractors within the same group, and outperforms strong baselines on challenging reasoning benchmarks.

Feng Zhang, Xin-Hong Ma, Zi-Qiang Dong et al. · 1 citation
#machine learning Preprint Sep 2026

Generative Query Suggestion via Intent Coverage and Query-Level Credit Assignment

Generative query suggestion aims to enhance user engagement by anticipating user intents and recommending relevant follow-up queries. A central challenge is to generate slates whose individual queries are useful while the slate covers distinct intents. We propose an Intent-Driven Query Suggestion Framework with dual-st...

Xin-Peng Liu, Lu-Yao Ma, Jia-Yi Qiao et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Elastic Horizon: Discovering the Effective Interaction Frontier in Agentic Reinforcement Learning

Elastic Horizon is introduced, a closed-loop controller that tracks a dynamic boundary beyond which additional interactions yield diminishing returns while cost grows linearly and stabilizes the horizon inside the saturation band from both under- and over-capacity initializations.

Gang-Yi Zhang, Jun-Jie Meng, Le-Tian Zhang et al. · 0 citations
Preprint Jul 2026

From Passive Retrieval to Active Memory Navigation: Learning to Use Memory as a Structured Action Space

NapMem is introduced, a framework for learning to use long-term user memory as a structured action space rather than passively retrieved context, and suggests that long-term user memory benefits from coupling structured storage with a learned policy for using memory at the appropriate granularity.

Yue Xu, Yutao Sun, Yihao Liu et al. · 3 citations
Jul 2026

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills

This work introduces Skill Self-Play (Skill-SP), a co-evolutionary framework comprising a proposer, a solver, and a dynamic skill controller that effectively bridges the gap between structured verification and open-ended exploration.

Siyuan Huang, Pengyu Cheng, Haotian Liu et al. · 2 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.