ABSTRACT Rich data and powerful machine learning models allow us to design drugs for a specific protein targetin silico. Recently, the inclusion of 3D structures during targeted drug …

Abstract Graph Contrastive Learning (GCL) has emerged as a powerful approach for gener-ating graph representations without the need for manual annotation. Most advanced GCL methods …

With the widespread deployment of long-context large language models (LLMs), there has been a growing demand for eficient support of high-throughput infer-ence. However, as the key-value …

SYNTACTIC AND SEMANTIC CONTROL OF LARGE LANGUAGE MODELS VIA SEQUENTIAL MONTE CARLO João Loula∗1 Benjamin LeBrun∗5 Li Du∗6 Ben Lipkin1 Clemente Pasti2 …

The success of the Internet in enabling human collaboration raises an intriguing question: can we create a similar platform to facilitate collaboration among autonomous agents? With the rapid …

ABSTRACT Vision-Language Models (VLMs) are powerful tools for processing and under- standing text and images. We study the processing of visual tokens in the lan- guage model …

ABSTRACT In the era of Large Language Models (LLMs), Mixture-of-Experts (MoE) architec- tures offer a promising approach to managing computational costs while scaling up model …

We present Q-chunking, a simple yet effective recipe for improving reinforcement learning (RL) algorithms for long-horizon, sparse-reward tasks. Our recipe is designed for the offline-to …

ABSTRACT Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal annotated support samples. While existing FS-PCS …

ABSTRACT We propose the Large View Synthesis Model (LVSM), a novel transformer-based approach for scalable and generalizable novel view synthesis from sparse-view inputs. We …