Does conversational memory need LLM-extracted facts, or is selecting the right raw turns enough? Published results disagree. Extraction-based systems report gains from distilled fa...
Learned image compression achieves competitive rate-distortion performance, but very-low-bitrate reconstruction remains challenging because the transmitted representation cannot pr...
Long-running LLM agents compress past interactions into persistent memories that may be reused as premises for later tasks. This creates a distinct derivation problem: whether the ...
Host-resident layer streaming enables full-parameter LLM fine-tuning beyond GPU memory, but data-parallel ranks compete for shared host resources. Replicated transfers amplify traf...
An activation-steering coefficient sets intervention strength, but requesting a particular degree of persona expression requires a behavioral scale. We study persona dosing: contro...
Reinforcement learning has helped AI agents solve increasingly difficult tasks, but high rewards do not always reflect the work users intended. In recent incidents and controlled e...
Physical trajectories contain more than snapshots of a system: they also reveal how its states evolve under governing conditions. However, representation learning for parametric pa...
Mobile manipulation extends robot interaction beyond a fixed kinematic workspace by making the reachable region itself controllable. This flexibility introduces two central challen...
Frontier models can now perform well on individual embodied navigation tasks through multi-round multimodal reasoning with simple tools. Across successive tasks, however, an agent ...
Test-time reinforcement learning (TTRL) enables models to improve their reasoning without relying on labeled training data, but existing approaches typically optimize a large fract...
Native 3D texture generation synthesizes colors directly in 3D space for a given geometry, conditioned on multi-view reference images. It is generally believed that training such m...
As language models take a growing role in AI development, a natural aspiration is for them to reflect on their own learning process, as humans do, and use that reflection to improv...
Multi-vector retrievers built on vision-language models lead visual document retrieval (VDR), but they run a multi-billion-parameter query encoder on every search. Distilling this ...
Most modern multimodal large language models (MLLMs) build on a pretrained visual encoder that provides a strong visual prior. Encoder-free MLLMs instead learn visual representatio...
Reliable AI safeguards require both control mechanisms that reduce unsafe behavior and monitoring mechanisms that detect safety risks during model interactions. Established behavio...
World-space hand motion estimation from egocentric video requires recovering 3D articulated hand geometry while tracking camera egomotion. Existing approaches heavily rely on casca...
Video world models achieve long-range temporal consistency by storing KV cache during generation, but the growing cache makes KV cache memory a major deployment bottleneck, which m...
Novel view synthesis from sparse images must reconcile faithful reconstruction of observed regions with plausible completion of unseen content, while maintaining world consistency ...
Long visual token sequences often account for a substantial fraction of the computational overhead in multimodal large language models~(MLLMs). Existing approaches reduce this cost...
Chunked KV-cache compression reduces the memory and attention costs of long-context inference by compressing windows of consecutive tokens into fewer cache entries at a fixed strid...
How much of a running workflow should a language model agent revise? ControlScope compares continuing generated code, editing the next tool call's data arguments, and replacing the...
Language model agents serving organizations must coordinate requests from multiple users while using knowledge distributed across their interactions. We identify two complementary ...
Recent gains in language model capability have come more from data than from architecture. Frontier labs and data companies produce verifiable agentic tasks, which supervised finet...
RLVR provides reliable trajectory-level credit, while OPSD offers dense supervision for token-level credit. This exposes a fundamental coupling when updating step-level credit dire...