Found 36 document(s)
Page 1 of 3
-
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...
-
A reasoning trace can accompany a correct answer without providing effective supervision for a particular student. We study how to construct traces that improve learning beyond answer-only supervision by considering both...
-
Industrial retrieval systems often improve quality by enlarging embedding candidate pools or adopting complex training pipelines. We show that, under a sufficiently large but practical candidate pool, embedding recall ex...
-
Muon has recently emerged as a strong optimizer for large language model pretraining by exploiting matrix structure through polar orthogonalization. However, it processes each parameter matrix independently, whereas rece...
-
Embodied AI lacks the data-rich pretraining that gave language models their agents and skills, so new manipulation capability costs demonstrations per task or a frontier model in every episode. We study a third route: a ...
-
The macroscopic capabilities of intelligent systems arise from the local interactions of many simple units. When such systems are deployed in the real world, their behaviour must nevertheless be constrained, leaving desi...
-
Despite achieving high visual fidelity, video models still suffer from physical hallucinations, limiting their reliability as world simulators. Existing methods leverage model-internal or external signals to improve phys...
-
In recent years, physical artificial intelligence (physical AI) has experienced rapid development, capturing significant attention in academia and industry. However, the field has yet to reach consensus on its definition...
-
Open-vocabulary object detection aims to detect both seen and unseen categories by leveraging the semantic knowledge of vision-language models. However, existing methods often struggle with small objects due to insuffici...
-
Beyond the Point Mass: Acceptance-Derived Weights and Distributional Losses for Speculative DecodingIn speculative decoding, a lightweight draft model proposes tokens that the target model verifies in parallel, speeding up generation without changing the target distribution. D-PACE (Wu et al., 2026) trains such drafter...
-
A model's failures can reveal gaps in the behavioral criteria guiding its training. We introduce RubricOpt, a framework that lets a policy revise these criteria within preference optimization. The policy diagnoses its ow...
-
PowerPoint presentations (PPTs) are a dominant medium for communication across diverse domains, yet high-quality PPT generation still depends heavily on labor-intensive human effort. Recent advances in large language mod...
-
Wireless digital twins (DTs) are increasingly integrated with artificial intelligence to support online modeling, prediction, and network optimization. However, most existing approaches perform adaptation within predefin...
-
Pinching-antenna systems (PASS) have garnered significant attention owing to their ability to enhance the capacity and coverage of wireless networks by guiding electromagnetic waves through waveguides before radiation. A...
-
LLM agents combine models with execution harnesses, so agentic benchmark performance reflects their joint behavior. We argue that harnesses should therefore be evaluated through their interactions with underlying models....