4 papers
Align-RAG: Alignment Is All You Need for TSFM In-Context Learning
Mohammad Asadi, Soheil Hor, Bardiya Akhbari +6
Retrieval-augmented forecasting promises to adapt frozen Time Series Foundation Models (TSFMs) to new domains without fine-tuning, but recent methods typically rely on learned fusi…
NanoFlux: Adversarial Dual-LLM Evaluation and Distillation For Multi-Domain Reasoning
Raviteja Anantha, Soheil Hor, Teodor Nicola Antoniu +1
We present NanoFlux, a novel adversarial framework for generating targeted training data to improve LLM reasoning, where adversarially-generated datasets containing fewer than 200…
Adaptive Inference: Theoretical Limits and Unexplored Opportunities
Soheil Hor, Ying Qian, Mert Pilanci +1
This paper introduces the first theoretical framework for quantifying the efficiency and performance gain opportunity size of adaptive inference algorithms. We provide new approxim…
Sense, Predict, Adapt, Repeat: A Blueprint for Design of New Adaptive AI-Centric Sensing Systems
Soheil Hor, Amin Arbabian
As Moore's Law loses momentum, improving size, performance, and efficiency of processors has become increasingly challenging, ending the era of predictable improvements in hardware…