collaborators

7 papers

cs.LG2026

Train What You Deploy: Closing the MLP Reachability Gap in Low-Rank Clone Distillation

Wenhui Chen, Zhifeng Li, Jie Zhou +5

A compressed student has two shapes that need not agree: the weight it deploys at inference and the weight family its training can reach. We show that a state-of-the-art weight-inh…

cs.CL2026

How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks

Yanlin Fei, Nazhou Liu, Xinmiao Yu +7

AI has long assisted scientific research, but the rapid advance of LLMs and agentic scaffolds is reshaping the landscape; a single system can now carry whole-stage research from an…

cs.AI2026

Reconstruction: A Blind Benchmark for Recovering Research Ideas from Pre-Publication Bibliographies

Shaolong Chen, Yanlin Fei, Nazhou Liu +7

Can a language model recover the true research idea of a published paper when given only that paper's pre-publication bibliography? We introduce Reconstruction, a blind idea-recove…

cs.LG2026

Interpretability-Guided Layer Selection over Subspace Projection: SAEs as Stethoscopes, Not Scalpels, for Raw Task Vector Model Editing

Li Lei, Madalina Ciobanu, Qingqing Mao +1

LLMs increasingly require surgical model editing to enhance domain-specific capabilities without incurring the computational cost or catastrophic forgetting associated with full fi…

cs.CL2026

AdaDPO: Self-Adaptive Direct Preference Optimization with Balanced Gradient Updates

Shaolong Chen, Madalina Ciobanu, Qingqing Mao +1

DPO has become a widely adopted alternative to RLHF for aligning LLMs with human preferences, eliminating the need for a separate reward model or RL loop. Recent theoretical analys…

cs.CL2026

State-of-the-Art Arabic Language Modeling with Sparse MoE Fine-Tuning and Chain-of-Thought Distillation

Navan Preet Singh, Anurag Garikipati, Ahmed Abulkhair +6

This paper introduces Arabic-DeepSeek-R1, an application-driven open-source Arabic LLM that leverages a sparse MoE backbone to address the digital equity gap for under-represented…