Process reward models (PRMs) have become a key component for LLMs, as their step-level feedback supports both post-training and test-time reasoning. However, training strong PRMs r...
Video understanding agents acquire evidence through an executable harness that controls what they observe and how they use those observations. However, execution traces contain onl...
Self-driving laboratories (SDLs) aim to automate the full experimental loop, from scientific decision-making to physical execution. Ideally, AI-generated plans could be carried out...
On-policy distillation (OPD) has recently emerged as a promising post-training paradigm in which the student learns from trajectories generated by its own policy under dense teache...
Teaching humanoids loco-manipulation skills, such as carrying diverse objects, via visual imitation is a promising path toward generalist robots. However, collecting diverse, high-...
How many tokens from its context does a language model actually use, and what determines that number? We study this question through self-attention. Without retraining, we retain o...
Transferring human motion to humanoid robots requires adapting the demonstrated motion to the robot morphology while preserving interactions with the environment. This is particula...
Transformer language models build predictions through successive residual updates, but how their representations become specific to an eventual outcome remains unclear. We study th...
Reproducibility is essential for scientific research, yet prior work shows that LLM outputs vary with hardware and batching. We identify an overlooked factor: the hidden injection ...
Pretrained transformers use little of their depth to follow references in context. Thirteen base models reliably follow only 1.4-3.6 lines, and extra pretrained loops add little. A...
We introduce Context Language Models (CLMs), language models that natively manage their own context. We implement this by treating the context as a file and allowing the model to m...
Manipulation behaviors vary widely across objects and scenes, but they share a small set of reusable skills, and planning with these skills helps embodied agents generalize to new ...
Embodied agents now take on ever longer tasks. For long tasks, knowing only whether a task finally succeeds or fails says little; the steps along the way matter. Progress Reward Mo...
Natural language autoencoders translate a language model's internal activations into readable explanations. Explaining every token position is costly. Which positions should an aud...
Skills equip LLM agents with professional knowledge and guidance to complete long-horizon and complex tasks. Although skills have been widely adopted in recent agent paradigms and ...
Linear attention replaces growing KV caches with fixed-size recurrent states, yet these persistent states can become a substantial memory bottleneck under concurrent serving. Direc...
Long-form subtitle translation requires reasoning over discourse and cultural context spanning episodes or entire series, while maintaining consistent terminology and style. Existi...
Text-conditioned full-body human-object interaction (HOI) generation requires synthesizing human motion and object trajectories that match the input text while remaining precisely ...
We introduce modal kinetic typography, which animates a vector glyph to express a semantic concept while keeping it legible. Our key idea is to build motion from the glyph's natura...
We present AREX-2, an effort to advance the self-improving capability of LLM agents, which we define as the ability to iteratively refine a solution at test time. This ability rest...
Multi-agent systems (MAS) based on large language models (LLMs) have become a powerful way to address complex problems, and their effectiveness depends critically on the collaborat...
This work evaluates the direct transfer of a co-evolved communication protocol from a 2D simulation to a 3D physical environment, without retraining the network weights. Two e-puck...
Tabular machine learning typically relies on per-dataset workflows, fitting tree ensembles or running AutoML searches from scratch for every task. We present TabFM, a 400M-paramete...
Evaluating the physical consistency of generated videos remains a fundamental challenge. Existing approaches rely on off-the-shelf vision-language models, which can often be myopic...