4 citations · 5 across the 9 of their papers we have counts for
10 papers
Clarification Is Not Correction: LLMs Fail to Let Go
Jianzhe Lin, Xiaolin Li, Fei Wang +3
Dialogue failures in language models are usually framed as memory failures: context too long, summaries lossy, a constraint forgotten. We argue this misses a deeper problem: in man…
When LLM Agents Fail to Read the Room: ReAdapt for Relational Social Reasoning
Jianzhe Lin, Xiaolin Li, Yunda Liu +2
A social agent's most basic decisions (should I react to this post? who should I reach out to?) are not purely content problems. The right action often hinges on the latent relatio…
Only Ask What You Don't Know: Grounded Delta Planning for Efficient Multi-step RAG
Wei-Chieh Chou, Xuanjun Chen, Jian-Ren Lin +3
Multi-hop question answering remains challenging for Retrieval-Augmented Generation (RAG) because existing approaches either propagate errors across iterative retrieval rounds or o…
Self-Improvement Can Self-Regress: The Rise-and-Collapse Failure Mode of LLM Self-Training
Jianzhe Lin
Self-improvement can self-regress. In REINFORCE post-training for code, a model can quickly improve on its optimized metric and then collapse within the same training campaign. We…
Repeated post-training is not Self-improving: Diagnosing Scientific Amnesia in Continual DPO Pipelines
Jianzhe Lin, Fei Wang, Xiaolin Li +2
Industrial LLM teams often ship behavior updates by repeatedly DPO-training a base model on sequences of related preference-data campaigns. The dominant failure mode in this regime…
When Good Verifiers Go Bad: Silent Negative Transfer in Verifier-Guided VLM Training
Jianzhe Lin
Verifier reliability is not portable across tasks. A verifier-guided self-DPO pipeline with genuine held-out gains on MathVista (+9.6 points on self-training data, +8.0 held out) c…
Towards Continuous Intelligence Growth: Self-Training, Continual Learning, and Dual-Scale Memory in SuperIntelliAgent
Jianzhe Lin, Zeyu Pan, Yun Zhu +2
We introduce SuperIntelliAgent, an agentic learning framework that couples a trainable small diffusion model (the learner) with a frozen large language model (the verifier) to enab…
Learning How To Ask: Cycle-Consistency Refines Prompts in Multimodal Foundation Models
Maurice Diesendruck, Jianzhe Lin, Shima Imani +3
When LLMs perform zero-shot inference, they typically use a prompt with a task specification, and generate a completion. However, there is no work to explore the possibility of the…
Multi-User Chat Assistant (MUCA): a Framework Using LLMs to Facilitate Group Conversations
Manqing Mao, Paishun Ting, Yijian Xiang +3
Recent advancements in large language models (LLMs) have provided a new avenue for chatbot development. Most existing research, however, has primarily centered on single-user chatb…
BatchPrompt: Accomplish more with less
Jianzhe Lin, Maurice Diesendruck, Liang Du +1
As the ever-increasing token limits of large language models (LLMs) have enabled long context as input, prompting with single data samples might no longer an efficient way. A strai…