AI research papers.

Single-image scene generation aims to produce a complete 3D scene mesh from a single image, including surfaces the camera did not observe.

Video world models can produce visually convincing yet physically inconsistent sequences, raising concerns about their reliability for prediction and planning in embodied AI systems.

A declared task can sometimes certify a reduced source before a downstream encoder, codebook, rate, distortion target, or optimizer is chosen.

AI agents increasingly operate in environments where they can diagnose failures and improve through experience, yet existing evaluations largely measure what an agent can do at a fixed point in time rather than how effec…

Asynchronous reinforcement learning (RL) for large language model (LLM) agents trains one policy on trajectories generated by another: rollouts come from stale checkpoints, and the inference engine's probabilities differ…

Astra can act, yet reliable manipulation depends on the system through which it observes and controls the world.

Vision-language-action (VLA) models map visual observations and language instructions to continuous robot actions.

Human videos provide rich motion targets for humanoid learning, yet visually plausible references can still produce persistent failures under physics-based execution.

The rapid growth of 3D Gaussian Splatting (3DGS) research demands significant effort to reimplement papers before building on them.

Reconstructing an editable CAD model from a 3D shape remains a challenging engineering task.

Flow and diffusion models suffer from slow inference due to computationally expensive numerical integration.

Vision-language-action (VLA) policies trained on large datasets are capable within their training domains, yet they still fail to generalize to the variety of situations a robot meets in real-world deployment.

Reward post-training of flow models either reweights the model's own samples under a KL penalty or a frozen reference, often for thousands of updates, or backpropagates the reward and moves every sample without checking…

Site-specific fertilizer recommendation systems adapt nutrient advice to location, soil properties, crop type, and production targets, but scientific reuse is constrained when recommendation functions remain accessible m…

arXiv:2605.14021v2 Announce Type: replace-cross Abstract: Google AI Overviews (AIOs) are arguably the most widely encountered deployment of generative AI, reaching over 2 billion users who may not realize the answers the…

Selective state space models (SSMs), such as Mamba, achieve strong per-token expressivity by making the time discretization step TildeΔ a learned function of the input.

Large language models (LLMs) are highly sensitive to the prompts used to specify task objectives and behavioral constraints.

Autoregressive video diffusion supports streaming generation and interactive control, but its KV cache grows continuously with the generated history.

Massive activations, residual-stream coordinates with magnitudes far larger than typical activations, are associated with attention sinks in transformers, but how their scale is regulated during training remains incomple…

Omni-modal large language models (OmniLLMs) unify text, images, audio, and video, yet hallucinate when generation relies on the wrong evidence.

Vision-language models (VLMs) are increasingly trained to generate structured outputs like points and bounding boxes that downstream interfaces, agents, and robots can act on, yet safety alignment of this output channel…

Vision-Language-Action (VLA) models serve as unified policies for robotic manipulation, yet their expensive inference forces robots to pause between policy calls, resulting in stop-and-go execution that interrupts smooth…

Long-horizon video world models require persistent memory to preserve scene consistency over extended rollouts.

Modern information systems, including many agentic workflows, use dense retrieval to explore large amounts of unstructured data.

Remote sensing foundation models (RSFMs) are commonly evaluated using aggregate metrics, which can hide systematic performance disparities across ecological regions.

Linear attention enables efficient long-context autoregressive decoding by compressing history into recurrent states, but this compression can make selective access to sparse and distant information difficult.

Generative models can synthesize high-quality inauthentic multimedia content that is already being misused at scale.

We present the Prior-Fitted Language Model (PFLM), a 300M-parameter byte-level transformer pretrained only on samples from a synthetic non-linguistic prior.

Masked diffusion language models (dLLMs) generate text by iteratively denoising masked positions, re-predicting each token multiple times before it is committed.

Real-world users often exhibit highly heterogeneous preferences over multiple objectives for LLM responses.

The last mile toward enterprise AGI is a company that runs itself.

Domain adaptation aims to turn a general-purpose large language model (LLM) into an expert for a target domain.

Image compression, restoration, and generation all require a way to measure how different two images look to a person.

Continuous asynchronous replanning is essential for real-time generative robot policies, but independent stochastic initialization can cause mode switching and inconsistent continuation across action chunks.

Realistic environment replicas are increasingly valuable for training and evaluating LLM agents, yet the original systems may be inaccessible or impractical to reproduce.

Multimodal imitation learning requires diverse executable futures under the same observation and consistent behavior across replanning cycles.

Generalization in multi-arm collaboration can be studied as composing familiar atomic skills in new ways across arms.

An agent whose tool keeps returning nothing useful should stop relying on it.

Multimodal Large Language Models (MLLMs) have demonstrated remarkable potential in video understanding, yet their reliance on retrospective summarization and text-centric priors often limits their ability to bridge unobs…

Memory self-evolution uses task feedback to iteratively improve executable memory programs that store and retrieve information from past interactions.

As agents take on long-horizon tasks, users shift from making individual decisions to overseeing autonomous execution.

A semantic decision engine such as Jev can return a valid answer and still miss a network deadline, select an infeasible action or leave the service unverified.

We present Empirical Variational Autoencoder, a general generative framework for continuous-valued (i.e., non-vector-quantized) sequences.

Large language model (LLM) agents are increasingly capable of acting in complex tool-use environments, yet they often fail to recognize when tasks are infeasible and no valid solution exists.

Geometry optimization is a major cost in many quantum-chemical workflows: each optimization step requires one force evaluation, and at the density-functional level that evaluation dominates the wall time.

Action-conditioned robot world models must respond precisely to robot trajectories while preserving realistic visual dynamics, yet learning both from heterogeneous robot videos remains challenging.

World Action Models (WAMs) incorporate visual representations from video generation backbones to guide action prediction.

Reinforcement learning (RL) has greatly advanced the capabilities of large language models (LLMs), but its memory demands remain a barrier to broader adoption.

We introduce a post-training method for diffusion language models (DLMs) that minimizes Maximum Mean Discrepancy (MMD) between generated and reference distributions in the feature space of a frozen pretrained DLM.

Latent reasoning lets a large language model (LLM) think in a continuous space and verbalize only the answer.