AI research papers.

While learning dexterous manipulation from a single human video offers a promising alternative to costly robot demonstrations, many recent methods predominantly imitate demonstrated motions.

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 safety, but reduces quality because example…

On-policy distillation (OPD) has become increasingly popular for transferring teacher capabilities to student models.

Reconstructing complete, scene-aligned 3D objects from casual images requires integrating sparse, uncertain observations and inferring surfaces hidden by occlusions.

Long-horizon tasks require LLM agents to continually draw on information from earlier interactions.

In an image latent space, the embeddings of high-resolution, natural, and sharp images form a manifold.

Work agents operate over digital artifacts to execute professional knowledge-intensive work, requiring training environments that support long-horizon interaction and trustworthy verification.

Learning from experience is essential for LLM agents to adapt to unfamiliar and dynmaic environments.

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 between two parked cars; a few seconds of v…

Reward modeling often requires jointly representing and reasoning over multiple evaluation criteria, yet verbalizing this process token by token can incur substantial inference cost.

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 derived from examination questions or curat…

Geometrically faithful and functional articulated 3D assets are essential for real-to-sim robot manipulation, where policies trained in simulation must transfer to physical objects.

A 4D audio-visual scene comprises a video, the dynamic geometry it depicts, and the sound sources that populate it, each with its own position and trajectory.

Spatial coding agents significantly improve spatial reasoning in Multimodal Large Language Models (MLLMs) by using external tools to generate verified execution traces.

In this paper, we argue that looped Transformers need their own residual connections to prevent performance degradation as the number of iterations grows.

Large Language Models (LLMs) increasingly ship with explicit "thinking modes", yet their counterpart, "no-thinking", has received far less attention.

Dense retrievers have made significant progress on text and image corpora, but whether these capabilities extend reliably to mixed corpora containing text, image, and fused text-image documents remains unclear.

Data video is a media form that integrates data visualization with video narrative, widely adopted in news reporting and business analysis.

World action models (WAMs) aim to answer a coupled physical question: given a task instruction, what motion should the robot execute, and how will that motion change the surrounding world?

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.

Knowledge distillation (KD) transfers knowledge from stronger Teacher models to weaker Student models, but most methods require training the Student parameters, thereby binding the distilled knowledge to a specific archi…

General-purpose service robots need navigation systems that can handle diverse human requests in unfamiliar environments, combining task generality with scene generality.

In text-guided image editing, describing the desired change is often straightforward, but identifying the intended object or region can be cumbersome, especially when several objects look alike.

Text prompting is an indirect interface for poster generation, requiring users to encode inherently two-dimensional composition intent into a one-dimensional sequence of words.

Large language model (LLM) routing distributes inference work across different models, advancing the cost-quality Pareto frontier of LLM serving.

Large language model (LLM) coding agents have advanced test generation across diverse programming tasks.

Egocentric world models predict first-person observations conditioned on an agent's actions, but most focus on a single agent.

Most image generation models rely on uniform tokenization, allocating the exact same computational budget to equally-sized image patches.

The memory-bound nature of the decoding stage of large language model (LLM) inference incurs significant latency.

Adversarial games have driven advances from heuristic search to reinforcement learning, yet learning and adapting strategies from limited samples remain challenging.

Large Multi-modality Models (LMMs) have made significant progress in visual understanding and generation, but still face challenges in visual editing, particularly in following complex instructions, preserving appearance…

Spatial reasoning remains a persistent weakness of vision-language models (VLMs), because RGB inputs do not directly provide geometric evidence.

When retrieved evidence contradicts an agent's prior beliefs, does it revise its answer, acknowledge uncertainty, or persist with an incorrect conclusion?

Most robot policies keep a model in the control loop: a VLA maps observations to actions, and an Agent Harness, such as Agent-as-Policy or Harness VLA queries a VLM for decision making at run time.

Interactive virtual worlds allow agents to learn through exploration and interaction.

Existing spatial reasoning benchmarks mainly test spatial perception: reading off relations already visible in the input.

Skill-augmented agents improve sample efficiency by distilling successful trajectories into reusable strategies.

Multiplayer world models must generate independently controlled views with consistent representations of both players and their shared environment.

Generating realistic human-object interactions (HOI) in complex 3D scenes requires two complementary capabilities: reasoning about interaction feasibility in the environment and synthesizing realistic human-object motion…

Multimodal large language models (MLLMs) struggle with spatial, embodied, physical, and temporal reasoning.

Single-image, multi-image, and video deep research require different visual operations but share a workflow of visual grounding, external retrieval, and fact composition.

Generating an egocentric video from a single exocentric recording is a challenging case of novel view synthesis, as the two cameras share little overlap and much of the target view is unobserved.

We propose BrickBench, a benchmark for agentic text-conditioned LEGO-set design.

Large foundation models have accelerated progress toward general-purpose agents that interact with humans and other agents through language and multimodal signals.

Multimodal large language models (MLLMs) are rapidly evolving toward continuous audio--visual reasoning, creating an urgent need for evaluations that expose their capability limits.

We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physically plausible video prediction.

Static coding benchmarks are fixed at release.

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 model.

Online reinforcement learning (RL) fine-tunes diffusion models with black-box rewards, but reverse-process methods such as Flow-GRPO are limited in efficiency by poor credit assignment, while forward-process methods such…