AI research papers.

3D diffusion policies are strong at generating geometrically grounded actions from current observations, but successful manipulation requires not only knowing what motion is feasible now, but also anticipating where the…

Agent trajectories record what an agent does and what happens next.

Video diffusion models repeatedly process long spatiotemporal token sequences during denoising, making attention a major computational bottleneck.

Evaluating an AI system requires disaggregated assessment, as performance varies across domains such as benchmark task types or conversation types in deployed agents.

Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivates self on-policy distillation (OPD) to supply dense token-level supervision from a self-teacher with…

World modeling enables intelligence to anticipate consequences, guide interventions, and learn from interaction.

Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering performance, yet existing work typically evaluates harnesses as monolithic systems, leaving the effe…

Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex value for image generation and editing.

Modeling articulated objects from sparse monocular views is challenging because each observation reveals only partial geometry and motion evidence.

Large language models (LLMs) increasingly participate in scientific evaluation, both as automated reviewers and as assistants to human reviewers.

Induced pluripotent stem cell (iPSC) culture increasingly relies on segmentation foundation models, yet deployment on laboratory CPUs and edge hardware requires compression schemes that are both efficient and auditable.

Large Language Models (LLMs) are increasingly deployed in applications that must weigh clashing moral values, yet even strong models exhibit hidden biases and brittle instruction-following across languages.

OpenAI shares a framework for tracking, investigating, and disclosing model misalignment, alongside six reports of unexpected or concerning model behavior.

In collaborative tasks with asymmetric information, participants coordinate their understanding through interaction.

Mixture-of-experts (MoE) inference on consumer hardware is bounded by weight memory: a 35B-class model is 19.5GB at 4-bit, and sparsity shrinks the compute per token, not the bytes that must be held.

Autonomous research loops such as AutoResearch show that one coding agent can improve a training setup unattended.

Recent Omni-Modal Generative Models (Omni-Models) have advanced content generation toward unified modeling of text, images, video, and audio.

Action tokenizers play a central role in autoregressive vision-language-action (VLA) models, determining both the targets for policy training and the executable commands recovered from predicted tokens.

As corporate AI adoption continues to grow, enterprise-grade LLM agents are being deployed into sensitive contexts such as hiring, healthcare, and finance.

Preparing high quality training data for foundation models requires scalable pipelines that transform heterogeneous documents and videos into structured records.

In reinforcement learning for large language models, Proximal Policy Optimization (PPO) commonly uses a critic to estimate state values and reduce the variance of policy updates.

Large audio-language models have shown promise for anti-fraud detection by directly processing speech and reasoning over fraud-related evidence.

Current Mixture-of-Agents (MoA) paradigms generally treat query routing and agent fine-tuning as separate processes, limiting their ability to respond to evolving agent capabilities.

Coding agents are typically evaluated with desired behavior specified through issues or instructions.

Scientific code repositories encode decades of human knowledge in executable models, methods, and tools.

Enabling robots to adapt to unfamiliar environments as readily as humans remains a moonshot goal of embodied AI.

Intelligent systems that act in the world require image understanding that is both comprehensive and spatially grounded.

Direct preference alignment methods are widely used to align large language models (LLMs) with human preferences because of their computational and memory efficiency.

Large language models (LLMs) provide a flexible interface for long-horizon robot planning, but generated plans often fail to respect embodiment constraints, recover from planning errors, or reason effectively under parti…

Test-time scaling can improve large language model reasoning by generating and combining multiple candidate responses.

Business intelligence (BI) is a cornerstone of enterprise decision-making and is widely used by enterprise users in software such as Power BI and Tableau.

Few-shot learning research is predominantly evaluated on accuracy alone, with limited attention to the parameter and training-sample budgets required to reach that accuracy - a real constraint for practitioners without l…

Traditional multimodal representation learning and generation are two stages: a contrastive or self-supervised visual encoder is trained first, followed by a separate downstream generative model.

Language model-generated rubrics are increasingly used as reward signals for rubric-based reinforcement learning, LLM-as-a-judge evaluation, and automated grading.

Platform abuse campaigns conceal redirection instructions with emojis, homophones, character decomposition, and redundant symbols, then route users through disguised links to services associated with pornography, fraud,…

A walking robotic hand must use the same fingers to move its body, support its weight, and interact with the environment.

3D hand mesh reconstruction is a challenging yet essential task for downstream applications, including human-robot interaction and AR/VR.

We introduce LimiX-2, a new model in the LimiX family, developed through model and data scaling guided by our previously established scaling laws.

LLM assistants are widely used for daily social advice, yet evaluating their social reasoning in such consultation settings remains challenging since (i) it requires setups where the assistant learns about social situati…

Large language model (LLM) trading agents can combine market data, news, and executable analysis, but their behavior is often controlled by static hand-written tool-use policies that are fixed before deployment.

When agentic sessions run to a million tokens with many sessions resident at once, the KV cache and the index that ranks it live in host memory, and the scan that ranks all n keys for a top-k step becomes the traffic tha…

GUI agents execute long-horizon tasks on dynamic graphical user interfaces, where pop-ups, delayed loads, and relocated widgets routinely invalidate plans fixed before execution.

Reliable confidence estimation is increasingly central to the trustworthy deployment of language models: a calibrated estimate of the probability that an output is correct decides what to ship, what to escalate, and what…

We introduce Zing-0.5, a 5B autoregressive world model designed for playability: users can explore generated worlds, influence unfolding events, and respond to the resulting feedback through joint keyboard and online tex…

We present TAPe+ML v3, a compact computer vision system based on TAPe (Theory of Active Perception), a structured representation that encodes relations among perceptual elements before recognition.

The rapid progress of artificial intelligence is reshaping robotics and accelerating the adoption of learning-based approaches.

Face Image Quality Assessment determines the suitability of captured face images for automated face recognition (FR), a critical capability for reliable biometric systems.

We present NanoForecast v0.5, a 6.5M-parameter forecaster that competes with models 31x its size (TimesFM, 200M parameters) after training pipeline fixes and no architecture change.

Chain-of-thought reasoning has revolutionized natural language processing by enabling large language models (LLMs) to decompose problems into intermediate steps before answering.