Speculative decoding is a technique that accelerates the inference speed of autoregressive large language models (LLMs) by sampling from a faster, lower quality draft model. Traditionally, a fundamental characteristic of speculative decodi…
The rapid growth of microdramas has increased demand for high-quality script production. Long-form microdrama script generation with LLMs requires both diverse plot progression and long-range narrative coherence. Our observations reveal th…
Recognizing task completion and failure enables robots to stop upon success and initiate recovery or replanning after failure. Existing methods augment Vision Language Action (VLA) policies with task status signal prediction to support the…
LLM memory is widely used in long-term conversation understanding. Agentic memory systems often use mutation, structural organization, learned retrieval strategies, or other complex operations. Is this complexity always necessary? We study…
Vision-language models (VLMs) can perform a broad range of tasks across diverse settings, yet their performance in agentic contexts remains poorly understood. Although online evaluations in simulators and real-world environments are essent…
Policy enforcement for LLM agents has shifted from single-turn content moderation to compound, application-specific policies evaluated over multi-turn transcripts and tool-call trajectories. Fine-tuned guardrail models are efficient but de…
Frontier coding agents are becoming increasingly adept at 3D modeling. Yet, they still face challenges when building objects meant to be assembled in the physical world, often creating invalid assemblies with floating, colliding, or discon…
Complex camera motion is central to visual storytelling, yet translating cinematographic intent into controllable, executable camera trajectories remains challenging. We introduce FilmFlow, an agentic framework that converts natural-langua…
The growth of time-series datasets and foundation models has made dataset comparison a central part of time-series workflows. Assessing source-target transfer before model adaptation requires similarity estimates that can summarize transfe…
Recent methods for injecting graph structure into LLM prompts include graph soft prompting, in which a graph neural network (GNN) learns graph-specific tokens that capture relational information among entities in textual prompts. G-Retriev…
Vision-language-action (VLA) models have become an important paradigm for robotic manipulation by unifying visual perception, language understanding, and action generation. Since reliable manipulation requires sufficient observation of obj…
Uber is rolling out ChatGPT Work to more than 30,000 employees, helping teams research, analyze data, create presentations, and complete complex workflows.
Today, we’re inviting members of the life sciences community to apply to work with us on special projects. We’re looking for proposals from principal investigators and their research groups at academic institutions, nonprofits, or governme…
Video foundation models have advanced rapidly in understanding and generating visual sequences, while video world models seek to capture the underlying dynamics of the world they depict. Despite their different objectives, both concern the…
Recent advances in video generation have made synthetic videos increasingly realistic, placing greater demands on reliable AI-generated video detection. Existing artifact-based detectors typically identify generation artifacts as evidence…
Masked diffusion language models generate tokens in parallel, but their efficiency depends on which predictions are committed. Learned unmasking policies improve the speed--accuracy trade-off, yet differ in supervision, inputs, and capacit…
Feed-forward models accurately estimate camera motion and 3D geometry from short video windows. However, computational and memory costs prevent direct inference on sequences containing thousands of frames. Long videos must therefore be pro…
The life-cycle of robotics foundation models crucially depends on data labels. Outcome reward labels are needed for monitoring real-world deployments. Process reward labels are needed during RL post-training. Timestamped captions are neede…
Deep research agents synthesize open-web evidence into long reports, but current benchmarks do not evaluate research centered on a source video. We introduce Video-Centered Deep Research Report Generation. Given a video and user request, a…
We examine how closely pretrained LeWorldModel (LeWM) reproduces the effects of small action changes. Using matched simulator and model responses, we measure action sensitivity with Gram matrices at three perturbation scales. Across nearly…