Long-horizon compositional manipulation has become increasingly important for real-world robot deployment, where a single task involves multiple coordinated subtasks. Existing worl...
Multimodal RAG retrieves text, tables, images, and videos, but choosing a retrieval granularity does not determine how much context to retain within each item. Coarse units include...
Vision-language-action models benefit from the understanding and reasoning capabilities of pretrained vision-language models, but action-only supervision provides limited grounding...
The executable harness surrounding a GUI model determines how observations are assembled, actions are executed, and verification, recovery, and termination are controlled. Compared...
Large language models (LLMs) increasingly construct multi-agent workflows that decompose a complex task and assign specialist agents from a pool. However, building such a workflow ...
How can a world model continuously observe regions beyond the actor's current view? Video world models simulate how an environment evolves from an agent's actions, yet remain actor...
Multimodal agents commonly generate free-form reasoning before each action. For small models, limited model capacity can result in lengthy reasoning that provides little useful gui...
Typed decision models answer schema-constrained questions about a text in one forward pass and return probabilities meant to be thresholded. We ask whether biomedical sentence enco...
Distribution Matching Distillation (DMD) trains a few-step student from the difference between separately estimated target and student scores, so it must keep an auxiliary diffusio...
Diffusion language models (DLMs) offer a promising alternative to autoregressive (AR) language generation. Recent advances in continuous DLMs, which apply latent diffusion to conti...
What makes great scientists great? Even as AI systems start to make progress on open problems, scientists remain far ahead of them at sensing which prior idea, buried in an ever-gr...
LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into tool invocations. However, existing evaluations focus on knowle...
Predicting the future evolution of a scene is a fundamental capability for world modeling. Recent work has shown that operating in the feature space of Vision Foundation Models (VF...
On-policy self-distillation has recently emerged as an effective approach for improving language-model reasoning by supervising students with a frozen or EMA version of themselves ...
Large language model (LLM) agents increasingly rely on persistent external sources to solve sequences of knowledge-intensive tasks. Existing methods improve how source content is a...
Generalization in large language models (LLMs) is the ability to produce consistent and semantically stable outputs when the same input is expressed in different ways. Existing wor...
Enterprises adopting retrieval-augmented generation (RAG) face a recurring operational decision: promote, revise, or block a system version. The evidence is incomplete and the metr...
Multi-agent systems (MAS) built from large language models coordinate specialized agents to tackle complex tasks, but effective workflows are difficult to design in advance. Test-t...
A typed decision model answers a fixed question about an input by returning a probability for each of several caller-defined options. Each option carries a short label and a writte...
Recovering executable CAD programs from 3D meshes is challenging due to the compositional nature of CAD construction and the interaction between discrete modeling choices and conti...
Reinforcement learning based post training of diffusion models, such as Denoising Diffusion Policy Optimization (DDPO), optimizes a reverse diffusion process under a reward functio...
While Large Language Models (LLMs) have demonstrated striking capabilities on frontier mathematical problems, it remains unclear whether they possess the structural mathematical un...
Computer-use agents need to reliably ground action targets in complex desktop scenes, where multiple applications, overlapping windows, and visually similar controls compete for at...
3D editing methods are usually tested on a single edit, yet an asset is built through a long sequence of revisions, each of which must implement the requested change while leaving ...