Found 4,326 document(s)
Page 105 of 289
-
Embodied perception requires positional representations that capture both physical geometry and the spatial and temporal extent of observations. We introduce POD-RoPE (Physical Observation Distribution RoPE), which repre...
-
Protein annotation agents must choose suitable bioinformatics tools, interpret their outputs, and use the resulting evidence in the final answer. Most existing systems rely on frontier-scale models. We ask whether a comp...
-
Multimodal reasoning requires models to combine multiple pieces of evidence into decisions that satisfy all relevant constraints. Evaluations centered on final-answer accuracy leave unclear whether failures arise from re...
-
Zero-shot detection of machine-generated text is vital for mitigating the risks of large language models (LLMs) misuse. While the state-of-the-art dual-model detectors and resampling-based detectors outperform single-mod...
-
Deploying a language-guided navigation policy in a new building usually means watching it fail. Public-benchmark VLAs degrade scene by scene as layout, appearance, and language drift, and the standard fix of teleoperatin...
-
Language-model agents must adapt as users revise their requirements and priorities during complex tasks. We introduce IntentDelta, a human-constructed multi-turn benchmark with 638 trajectories and 3,766 turns across Web...
-
What is the round complexity of Hessian-similar optimization when each round can contact at most $s$ of $m$ clients? Prior rates permit a free master or full participation and do not characterize strict caps. We count ev...
-
Can LLM agents carry a hard real-world problem from raw data to a system that holds its own against people? We study this in Hearthstone Battlegrounds, an eight-player auto-battler with stochastic shops and battles, hidd...
-
Repeated attempts at interactive tasks uncover facts, useful operations, and failures that can inform subsequent execution. We introduce ReGE, a framework for turning this recorded experience into guidance for a fresh at...
-
Vision-language-action (VLA) models enable robots to follow instructions in typed text, limiting broader deployment in natural speech. The traditional solution by prepending a speech recognition before VLA to convert spe...
-
Interactive world models hold immense potential for high-stakes applications in robotics, game engines, and immersive digital twins, yet existing benchmarks primarily focus on perceptual similarity rather than the physic...
-
Computer-using agents are increasingly capable of performing complex tasks in the digital world. However, high-quality interaction trajectories remain scarce for specialized desktop applications, where limited applicatio...
-
Mapping CVEs to MITRE ATT&CK techniques helps defenders translate vulnerability information into hypotheses about adversary behavior. Automating this mapping is challenging because relevant evidence is fragmented across ...
-
Reduced-order models simplify fluid simulation by representing complex flows with a small number of spatial modes. Building on Laplacian Eigenfluids, we introduce Neural Eigenfluid Bases (NEB), a neural representation wh...
-
Continual learning is the ability of LLM agents to improve over time by acquiring, refining, and applying knowledge from experience while retaining useful prior knowledge. It is essential for agents learning over long ti...