AI research papers.

We study language-conditioned local navigation, where a robot must navigate to a text-specified target visible in its initial observation and stop at the described location.

Experience generated during deployment offers an opportunity for robots to improve policy reliability through learning from their own executions.

Accurate inpatient risk prediction requires modeling heterogeneous clinical evidence that accumulates irregularly over time.

Training high-quality diffusion models is computationally expensive, and inference-time guidance often adds further sampling cost.

Game world models have made rapid progress toward real-time interactive generation.

Robotic manipulation is not merely observation-to-action generation, but the realization of task-specified state changes in the physical world.

Large Language Model (LLM) agents are increasingly deployed in unfamiliar and evolving environments, requiring them to proactively explore, understand, and adapt to environmental dynamics.

We set out to reproduce a recent hallucination-mitigation result on the POPE benchmark.

Generalizing real-time physics-based animation across diverse 3D shapes and spatial discretizations remains challenging.

Video overlay removal aims to recover scenes obscured by subtitles, titles, and logos while preserving surrounding content.

Graphical User Interface (GUI) agents increasingly act over streaming omni-modal observations spanning screenshots, audio, video, interaction history, and device states.

An effective visual tokenizer must preserve image fidelity while producing latents that downstream diffusion models can learn efficiently.

Tool-using voice agents often leave users waiting after speech ends, even when actionable information arrives earlier in the request.

Expanding the vocabulary of conditional text-to-speech (TTS) models typically requires extensive fine-tuning with paired audio, creating a major bottleneck for low-resource and cross-lingual adaptation.

Rubric-based reinforcement learning (RL) trains policies for open-ended generation with natural-language criteria as rewards, but these rewards can become ineffective as training progresses.

Lifelong agents continually accumulate and reuse experience to improve after deployment, yet in practice they often operate under tight generation, interaction, and memory budgets.

Drafting an answer allows a reasoning model to reconsider each decision in the context of the others.

Human egocentric experience offers a rich foundation for learning how the world is organized and how it changes through interaction.

Reconstructing human activity from egocentric video requires more than recovering individual 3D components: the observer's motion, surrounding geometry, and hand-object interactions must fit together in a consistent worl…

Robotic value models assess task execution from visual observations and instructions, providing feedback for policy learning and execution monitoring.

Video face swapping transfers the reference identity to a target video while preserving its other attributes and motion.

Recent video generation models produce visually compelling outputs, yet their physical plausibility remains poorly measured.

Expert human readers process large inputs (e.g., code repositories and long documents) by skimming to closely read only what matters.

General-purpose manipulation requires reliable behavior across embodiments, objects, and task demands.

Harness development plays a crucial role in building capable AI agents.

Brain encoding models aim to predict neural responses to stimuli.

Existing world models can generate action-conditioned video from a single image.

Matryoshka Representation Learning (MRL) is designed to support flexible representation sizes by jointly optimizing nested prefixes.

Memory-native evolution requires making memory an intrinsic capability of foundation models, enabling them to continuously accumulate and utilize information.

Agent learning is shifting from learning from human data toward learning through interaction with the world.

Many modern language models have adopted hybrid architectures that incorporate both linear-time recurrence and softmax attention.

We propose KronLSTM, a linear attention architecture based on the Kronecker Delta Rule, a novel update rule for associative matrix memories.

LLM agents that compute the right answer can still answer wrongly.

Diffusion Transformers (DiTs) achieve high-fidelity image and video generation, but they suffer from substantial inference costs due to repeated transformer evaluations across many denoising steps.

The goal of a world model is to capture the dynamics of an environment.

In this paper, we systematically investigate the mechanisms, scaling behavior, and generalization of physical Recursive self-improvement.

Adapting existing manga into coherent animation that stays faithful to the source is a valuable yet challenging task.

Procedural generation plays a key role in synthetic data creation and game development, offering greater controllability, editability, and diversity than static mesh representations.

World models enable embodied agents to anticipate action consequences, yet jointly modeling locomotion and manipulation across diverse embodiments remains challenging due to heterogeneous action spaces and limited multim…

Diffusion-based video matting has recently emerged as a leading approach, leveraging video diffusion priors from internet-scale pretraining to achieve strong zero-shot generalization from limited synthetic data.

Multimodal large language models (MLLMs) have made rapid progress on visual reasoning, yet many tasks require evidence that is difficult to obtain through internal reasoning alone: our controlled study on 22 benchmarks s…

Modern text-to-image (T2I) systems use internet-scale language pretraining for text-conditioned image generation.

General-purpose multimodal models, including GPT-6 Astra and Claude Opus 5.5, demonstrate broad capabilities in embodied manipulation.

Realistic market impact is essential for generative limit order book (LOB) models to serve as world models for trading agents.

Recent Omni LLMs (OLLMs) have demonstrated remarkable capabilities in joint audio-visual reasoning, yet cross-modal hallucinations remain a major challenge.

As language-model agents grow more capable, they can carry more of a task without asking anyone for help.

Modern language models are increasingly asked to handle several tasks within a single prompt.

Cooperative language-model agents can improve without weight updates by revising reusable skills, but only if a shared team reward is traced to the responsible agent and skill.

Medical workflows often require multiple interdependent analyses, but existing specialist and generalist AI models are not designed to coordinate them.

Coding agents can answer analytical questions over a data lake by discovering, cleaning, and joining the relevant data.