Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
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…
cs.LG2026
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…
cs.LG2024
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…