5 papers
SteerSearch: Interactive Search Reasoning with Mid-Response Steering
Udit Thakur, Baohao Liao, Matteo Nulli +4
Search-augmented language models increasingly serve as long-horizon research agents, yet most open training methods assume a fixed user goal throughout search. We study mid-respons…
Adapting Vision-Language Models for E-commerce Understanding at Scale
Matteo Nulli, Vladimir Orshulevich, Tala Bazazo +9
E-commerce product understanding demands by nature, strong multimodal comprehension from text, images, and structured attributes. General-purpose Vision-Language Models (VLMs) enab…
Meeting SLOs, Slashing Hours: Automated Enterprise LLM Optimization with OptiKIT
Nicholas Santavas, Kareem Eissa, Patrycja Cieplicka +6
Enterprise LLM deployment faces a critical scalability challenge: organizations must optimize models systematically to scale AI initiatives within constrained compute budgets, yet…
Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation
Stefan Vasilev, Christian Herold, Baohao Liao +3
This paper introduces Unilogit, a novel self-distillation method for machine unlearning in Large Language Models. Unilogit addresses the challenge of selectively forgetting specifi…
ClusComp: A Simple Paradigm for Model Compression and Efficient Finetuning
Baohao Liao, Christian Herold, Seyyed Hadi Hashemi +3
As large language models (LLMs) scale, model compression is crucial for edge deployment and accessibility. Weight-only quantization reduces model size but suffers from performance…