Found 723 document(s)
Page 1 of 49
-
Modern GPU compilers expose rich layout abstractions for mapping tensors to threads and on-chip resources, but compute-unit-local (CU-local) 3D DRAM architectures lack a corresponding abstraction for specifying how opera...
-
Computational drug discovery requires agents to compose scientific operations and adapt to changing evidence and constraints. Here we introduce DrugHarness, an evolvable agent harness coupling composable scientific execu...
-
Interactive models increasingly hand complex reasoning and tool use to a slow brain in the background, leaving a realtime front model free to sustain full-duplex dialogue. Yet the user may refine, cancel or replace a req...
-
Scientific discovery requires developing worthwhile hypotheses into practical investigations, yet learning from this evolving research process remains challenging. We introduce an operational definition of valuable and t...
-
Can large language model (LLM) agents deliver expert-level operations research (OR) solutions directly from original client materials, without prior expert reformulation? Existing OR benchmarks typically begin with self-...
-
Curating large labeled CT datasets is expensive and constrained by patient privacy. We present NV-Generate-BodyMask, a 3D latent diffusion model that synthesizes whole-body CT segmentation masks with precise, joint contr...
-
A coding agent combines a large language model (LLM) with a harness that plans, edits, and executes code. We study Cortex, a supervisory layer for pre-execution governance, requirement tracking, and iterative validation ...
-
Pixel-based language models process rendered text without relying on a fixed subword vocabulary, offering a promising approach to noisy and multilingual inputs. However, their practical value depends on whether they can ...
-
Tool-using agents are trained and evaluated almost exclusively with strong simulated users who state every detail clearly, yet real users are often weaker. We construct weak users by masking sentences of a simulated user...
-
AI agents increasingly interact with external environments to complete complex user tasks. These interactions can lead to unexpected behavior and expose agents to security threats such as indirect prompt injection. Curre...
-
Deploying a large language model (LLM) requires choosing the right accelerator, parallelization strategy, engine configuration, and replica count amongst ~140 other variables across clouds, regions, and markets. These de...
-
Speculative decoding accelerates large language model (LLM) inference by using a lightweight drafter to propose a block of tokens that the target model verifies in one parallel pass. Autoregressive drafters generate this...
-
GUI world models are increasingly used to improve action selection by predicting the consequences of candidate actions, but it is unclear how much of the resulting gain comes from prediction itself rather than from the e...
-
Agent systems deployed in dynamic environments continuously update their memories, skills, and runtime configurations, leading to evolving trajectories and challenges for persistent identity authentication. Existing text...
-
Wang et al.(Computer-Aided Design 40 (2008) 999-1008) proposed a knot-subsequence characterization of full row rank for rectangular B-spline collocation matrices. We identify an incorrect inequality in their Appendix pro...