Personal AI agents are increasingly capable of handling long-horizon tasks across applications, yet users often need to invest substantial effort in specifying goals, resolving amb...
Research taste, the judgment of what to read, which problems to pursue, and which methods to try, increasingly shapes the work of AI scientists, yet it remains far less understood ...
Foundation models in changing environments can encounter unfamiliar domain knowledge that their original training did not cover. However, new domains rarely provide large amounts o...
Speculative decoding accelerates memory-bound LLM decoding with a lightweight drafter, and parallel drafters extend this speedup by drafting a whole block in one forward pass. Howe...
Long-term memory enables large language model (LLM) agents to provide continuous personalized assistance by retaining user information across interactions. Existing systems support...
Long-form multi-shot video editing requires an intended edit to remain coherent across abrupt changes in scene, viewpoint, and subject appearance, while processing substantially lo...
3D generation, editing, and completion are typically treated as regenerating the complete 3D asset under task-specific constraints, even when only a local region needs modification...
General-purpose robot policies must work across robots, tasks, and environments, yet the variation that makes physical trials informative also makes them difficult to reproduce. We...
This paper studies retrieval-augmented generation (RAG), which leverages external knowledge to improve the performance of language models. Despite the remarkable progress, current ...
Tool-using language-model agents often execute actions that their domain policies forbid. We present LeanGuard, a runtime that checks every proposed tool call against a policy writ...
Most image-based 3D reconstructors primarily recover visible surfaces, producing partial point clouds with large holes and leaving unobserved geometry unresolved. To address this l...
Streaming digital humans produce detailed video while continuing speech as new text arrives. High-resolution denoising is costly, and text updates can cause repeated or interrupted...
Generative AI is billed per token, yet tokens are not equally expensive. Each token enters the KV-cache and raises the cost of those that follow, so energy grows non-linearly along...
Traditional image cropping assumes the photograph already contains the composition worth keeping, and asks only where to crop. A full 360^{circ} scene offers no such guarantee: the...
**Purpose:** Ultrasound biometry is widely used across various clinical applications, including prenatal and cardiac examinations, to obtain quantitative measurements by placing ca...
Natural Language Processing (NLP) has been widely applied in financial domains, enabling automated analysis and retrieval of stock market information. However, traditional NLP-base...
Sparse attention cuts the cost of long-context inference by making the attention matrix sparse: each query attends only a subset of the sequence, chosen by a fixed pattern or, in r...
Speculative decoding (SD) accelerates large language model inference by reducing the sequential cost of token-by-token generation. Advanced SD methods reduce proposal cost with par...
Complex documents such as scientific papers contain rich information in tables, figures, and equations; however, existing deep research (DR) agents typically reduce papers to OCR-e...
GUI web agents require realistic and interactive environments that remain stable during both evaluation and training. Live website evaluation suffers from changing content, access ...
LLM-based agentic systems are increasingly combined with CoT reasoning to solve tasks that require accurate reasoning, external knowledge, and multi-step deliberation. Yet, explici...
Prediction errors from video world models are often treated as physical surprise, but they can also reflect appearance, static content, motion, or ordinary prediction difficulty. W...
Most robot policies, whether trained by imitation learning (IL) or reinforcement learning (RL), map observations to action values at discrete control steps and leave the continuity...
As coding agents achieve increasingly high success rates on software engineering benchmarks, recent efforts have sought to increase task complexity through longer horizons and more...