Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inferenceby Matthew Riemer, Gopeshh Subbaraj, Glen…
ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residualsby Utkarsh Saxena, Sayeh Sharify, Kaushik…
I0T: Embedding Standardization Method Towards Zero Modality Gapby Na Min An, Eunki Kim, James Thorne,…
Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processesby Katarzyna Kobalczyk, Claudio Fanconi,…
Exploring Multi-Modal Integration with Tool-Augmented LLM Agents for Precise Causal Discoveryby ChengAo Shen, Zhengzhang Chen,…
COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanismby Jianing He, Qi Zhang, Hongyun…
Beyond Accuracy: On the Effects of Fine-tuning Towards Vision-Language Model’s Prediction Rationalityby Qitong Wang, Tang…
Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusionby Massimiliano Viola, Kevin Qu, Nando Metzger, Bingxin…
Relational Neurosymbolic Markov Modelsby Lennert De Smet, Gabriele Venturato, Luc De Raedt, Giuseppe MarraFirst submitted…
Predicting Change, Not States: An Alternate Framework for Neural PDE Surrogatesby Anthony Zhou, Amir Barati…