Pristine Models
Training on broad, unfiltered data enables high-quality image generation, but can also teach models concepts that should not be generated; restricting the training data ensures saf...
Papers
When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better
On-policy distillation (OPD) has become increasingly popular for transferring teacher capabilities to student models. In this work, we ask a critical research question: Is on-polic...
GATOR: Generative and Agentic 3D Object Reconstruction From Casual Images
Reconstructing complete, scene-aligned 3D objects from casual images requires integrating sparse, uncertain observations and inferring surfaces hidden by occlusions. We present GAT...
Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models
Humans perceive far more in a scene than what is explicitly depicted: a single glance captures past causes and future trajectories; a quick peek determines if a vehicle can fit bet...
WOVEN: Weaving Visual World Modeling into Multimodal LLMs
Multimodal large language models (MLLMs) struggle with spatial, embodied, physical, and temporal reasoning. We hypothesize that these failures reflect a shared deficit in visual tr...
Clinician use of language models diverges from how the models are evaluated
Large language model (LLM) assistants are being deployed to clinicians across health systems, and judgments about their readiness rest largely on benchmark scores, most of them der...
Few-Step Generation via Data-Space Iteration
Flow matching has emerged as a scalable paradigm for training high-quality generative models, but sampling from the learned probability flow requires many network evaluations. Dist...
Super-Resolution in The Right Latent Space: A Frozen Vision-Foundation Substrate
In an image latent space, the embeddings of high-resolution, natural, and sharp images form a manifold. Degradation of high-resolution images pushes their embeddings off this manif...
SWEeper-Bench: Can Agents Discover Bugs in Interactive Software?
Coding agents increasingly interact with users by generating interactive software on the fly rather than replying in text, yet many bugs in such software reveal themselves only aft...
Self-Preservation in Language Models
Continual learning (CL) seeks to adapt pretrained models while preserving prior capabilities. Yet the tasks supplied for preservation cover only part of what a model knows, while f...
Mental-Models for Multi-Agent Systems
Large foundation models have accelerated progress toward general-purpose agents that interact with humans and other agents through language and multimodal signals. However, robust ...
The Lattice of Transition Laws
Diffusion and autoregression (AR) have long been seen as different categories of generative models, with diffusion specialising in continuous fields and AR specialising in discrete...
Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving Compression
Reward modeling often requires jointly representing and reasoning over multiple evaluation criteria, yet verbalizing this process token by token can incur substantial inference cos...
Contextual Correction of Parallel Draftsfor Speculative Decoding
Speculative decoding accelerates large language model inference by using a lightweight drafter to propose multiple tokens that are subsequently verified in parallel by the target m...
One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
In this work, we show that a single Transformer block, applied recurrently, can match the accuracy of a full-depth vision encoder at comparable inference FLOPs without intermediate...
SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments
Computer-use agents (CUAs) are rapidly improving, yet synthesizing diverse and reliable software environments at scale remains challenging. Native application environments require ...
A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization
Black-box optimization (BBO) arises in many scientific and engineering problems where objective evaluations are expensive and limited. Recent large language model (LLM) agents offe...
ForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video Diffusion
Autoregressive video diffusion models have become a leading approach to real-time interactive video generation and video world modeling. However, existing methods typically allocat...
FlowState: Execution State as Memory for Long-Horizon LLM Agents
Long-horizon tasks require LLM agents to continually draw on information from earlier interactions. However, retaining the full history increases context costs, while compressing i...
WorldCast: Distributed Multiplayer World Models
Multiplayer world models must generate independently controlled views with consistent representations of both players and their shared environment. Most existing approaches coordin...
SpaceFlow: Locally Controllable 3D Generation
Current 3D generation methods lack explicit local control: geometric adherence is often defined by a global control strength, and appearance cannot be specified locally. We present...
REMORY: Learning Residual Memory for Context Compaction
Long-horizon agents compact their history to continue within a finite context window, but a textual summary alone may not support every subsequent decision. We introduce REMORY, a ...
BrickBench: Evaluating Agentic Brick Design
We propose BrickBench, a benchmark for agentic text-conditioned LEGO-set design. Given a prompt, an agent is tasked with producing an assembly that not only satisfies semantic and ...
Predicting Cable Dynamics with Physical Attention Bias
Learned simulators for deformable linear objects (DLOs) such as cables have to predict the motion of cables they were not trained on and stay stable over long rollouts. Most of the...