7 papers
How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks
Yanlin Fei, Nazhou Liu, Xinmiao Yu +6
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…
Reaction-Network-Level Discovery of Ammonia Synthesis Catalysts via Ten-Million-Scale Generative Exploration
Ruili Li, Rui Qi, Shuoqi Zhang +5
Catalyst discovery for ammonia synthesis is inherently a reaction-network challenge because catalytic performance is governed not by a single adsorbed intermediate, but by a surfac…
CLaaS: Continual learning as a service for sample efficient online learning
Kion Fallah, Silen Naihin, Barak Widawsky +1
Deployed large language model agents must adapt to distribution shift in dynamic environments. Ideally, adaptation can be performed from accumulated agent experiences and retain pr…
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…
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…
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…