AI research papers.

The rise of large language models (LLMs) has opened a path toward generalist embodied AI, raising the question of how LLMs can act in the physical world.

Conditional memory expands language-model capacity through selective lookup, but the full embedding table must remain available for every possible input.

Large language model (LLM) agents have shown promising potential in coding tasks, and their performance is jointly determined by the policy model and the harness that mediates their interaction with the environment.

Recent advances in large language models (LLMs) have brought impressive performance across diverse tasks; however, shortcomings remain in logical reasoning, including inconsistencies under linguistic variation.

Vision-language-action (VLA) models have shown strong promise for generalist robotic manipulation, but their inference cost remains a major bottleneck for real-time control.

Computer-use agents (CUAs) are commonly evaluated against fixed task specifications, but users may omit requirements, add constraints, or require approval before consequential actions.

The physical world has continuous state and action spaces, yet robot planning often benefits from hybrid discrete-continuous formulations that explicitly expose combinatorial structure, such as contact modes or discrete…

Looped language models reuse physical Transformer blocks across logical depth, but established architectures entangle recurrence placement, input injection, and recurrent state organization.

Generating complete, coherent, and usable 3D indoor scenes from natural language requires strong design intelligence: the ability to design high-quality scenes and critique their quality.

Reinforcement learning with verifiable rewards has become a scalable post-training paradigm for large language models.

AI agents increasingly use files and software tools to produce professional deliverables.

Multimodal large language models (MLLMs) answer questions about whole images well, yet they still struggle with fine-grained region understanding.

Large language models (LLMs) are increasingly used to automate AI research, including language-model (LM) development, offering a potential path toward recursive self-improvement.

Recent closed-source image generation systems can produce diverse visual content from simple compositions to information-dense graphics, yet open-weight text-to-image models still struggle with dense text and intricate l…

Large language models often answer factual questions incorrectly in closed-book settings, and such errors are usually attributed to missing knowledge.

Open-ended search combined with foundation models has produced advances such as faster algorithms, new results on open mathematical problems, and self-improving agents.

Agents built on vision language models (VLMs) now compete with learned policies on robot manipulation leaderboards.

A memory test for a video world model should say whether the scene was set, whether the asked change was carried out, and whether the last frame shows the result.

Self-supervised monocular depth estimation is appealing for its potential to scale with unlabeled data, yet existing methods often degrade when trained on diverse scenes.

End-to-end visual generation with pixel-space loss has recently achieved competitive performance without the need for learned image tokenizers.

Blockchain forensics is adversarial and open-ended: money launderers split, swap, and bridge funds, cut their trail at mixers or custodial services, and change tactics from one incident to the next.

Multi-turn image editing aims to modify an image according to a sequence of instructions, making it better aligned with human-AI collaborative creation than single-turn editing.

Speculative decoding has become a mainstream technique for accelerating large language model (LLM) inference by using a lightweight draft model to generate candidate tokens that are subsequently verified by the target mo…

Video world models that generate and explore environments at scale need a persistent 3D memory of what they have produced.

Scientific discovery requires developing worthwhile hypotheses into practical investigations, yet learning from this evolving research process remains challenging.

Pretrained VLMs bring rich world knowledge and semantic priors to object-goal navigation, and fine-tuning a VLM into a navigation policy has become a common recipe.

Can large language model (LLM) agents deliver expert-level operations research (OR) solutions directly from original client materials, without prior expert reformulation?

We ask how much an autoregressive transformer retains of its prompt after generating t tokens.

Introducing the Rosalind Academic Plan, offering eligible academic labs sponsored access to GPT-Rosalind and tools to advance life sciences research.

Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data.

Language models are increasingly trained against several verifiable rewards at once, such as the correctness and the format of a tool call, or the individual constraints of a complex instruction.

arXiv:2605.16428v4 Announce Type: replace-cross Abstract: Search engines traditionally complement online content platforms by directing users seeking information to external websites.

arXiv:2610.04296v2 Announce Type: replace-cross Abstract: Learning-based models for radio resource management (RRM) are typically built for a single function and deployment, so each new setting repeats the development pi…

arXiv:2610.11355v2 Announce Type: replace Abstract: Researchers increasingly use ChatGPT to revise their papers, and when asked to make a paper hold up under review, recent GPT versions often narrow or even retract the a…

arXiv:2610.15750v1 Announce Type: new Abstract: Google Earth AI is a family of geospatial AI models, together with an agent that orchestrates them.

arXiv:2610.16042v1 Announce Type: cross Abstract: The increasing use of artificial intelligence (AI) in mental health applications raises concerns about its potential to internalize and perpetuate societal biases.

arXiv:2610.17090v1 Announce Type: cross Abstract: On 6 October 2026 OpenAI published an initial 722 AI-written mathematical manuscripts, organized into 372 problem families, in the public repository github.com/openai/mat…

arXiv:2610.19210v1 Announce Type: cross Abstract: Transformers are efficient to pre-train at scale because attention permits parallel computation across sequence positions, but long-context inference requires increasingl…

Lean verifies that a generated declaration is well typed, but cannot check whether it states what the user intended.

Industrial manipulation in flexible manufacturing, e.g., high-mix, low-volume (HMLV) electronics assembly, requires robot policies to adapt to changing products and production conditions.

Time-series foundation models provide strong zero-shot forecast, but deployment for real-world applications still requires task-specific designs for model inputs and outputs.

Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from a terminal scalar reward, leaving the supervision in intermediate step…

Peer review is under strain from the growth of submissions, and review comments written by humans or AI can misstate what a paper says.

Recursive self-improvement, in which AI systems build stronger AI systems, is one promising route to superintelligence.

A coding agent works on repositories that can be far larger than its context window can hold.

Large language model (LLM) agents can keep scientific experiments running for months with little human supervision, but reliable autonomous research also requires scientific judgment.

World and action modeling are closely related, yet their reciprocal benefits under unified causal training remain unclear.

When humans collaborate with AI agents on long-horizon tasks, what happens to the agents' contributions?

Post-hoc image explanations usually show where a model looks using spatial heatmaps or indicate which channels matter using global channel scores.

Spoken Dialogue Models (SDMs) typically share a speech-token space for generation and synthesis, leading to long autoregressive sequences and costly inference.