All entries

Artemis II sent four astronauts on a lunar flyby in 2026, becoming the first crewed flight beyond low Earth orbit since the Apollo program. The successful mission appears to have generated significant

arXiv:2605.15706v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have catalyzed the development of multi-agent systems (MAS) for complex reasoning tasks. However, existi

arXiv:2605.15460v1 Announce Type: cross Abstract: Cross-modal hashing enables efficient retrieval by encoding images and text into compact binary codes. State-of-the-art methods rely on semantic simil

arXiv:2605.15352v1 Announce Type: new Abstract: Opening heavy, self closing doors, especially those that require pulling remains a long standing challenge in robotics. Humans naturally employ both arm

arXiv:2605.15519v1 Announce Type: cross Abstract: Visual active search (VAS) has been introduced as a modeling framework that leverages visual cues to direct aerial (e.g., UAV-based) exploration and p

arXiv:2605.15725v1 Announce Type: cross Abstract: Latent Action Models (LAMs) enable the learning of world models from unlabeled video by inferring abstract actions between consecutive frames. However

arXiv:2605.15759v1 Announce Type: new Abstract: Large language model (LLM) agents require long-term memory to leverage information from past interactions. However, existing memory systems often face a

arXiv:2605.15456v1 Announce Type: cross Abstract: Solving imaging inverse problems has usually been addressed by designing proper prior models of the underlying signal. However, minimizing the data fi

arXiv:2605.15304v1 Announce Type: new Abstract: The relations connecting propositions in discourse such as cause (A because B) or concession (A although B) are a subject of intense interest in Computa

arXiv:2605.15368v1 Announce Type: new Abstract: Group-convolutional neural networks (GCNNs) are among the most important methods for introducing symmetry as an inductive bias in deep learning: In each

arXiv:2508.18167v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and generating human-like text, yet they largely operate as

Distributed training is hard. We adopted DTensor at Runway to prevent silent gradient bugs and it delivered. But we traded performance for correctness, hitting dispatch overhead, recompilation storms,

arXiv:2605.15225v1 Announce Type: cross Abstract: Biologically-inspired AI agent frameworks claim reliability benefits through structural guarantees adapted from gene regulatory networks, immune syste

arXiv:2504.00289v3 Announce Type: replace-cross Abstract: The release of top-performing open-weight LLMs has cemented China's role as a leading force in AI development. Do these models support languag

arXiv:2605.15855v1 Announce Type: new Abstract: Despite strong image-generation performance, diffusion models' reconstruction objectives limit alignment with human preferences. RL enables such alignme

Do we have to look at a billion of these Yann LeCun saying things Gary Marcus said all along videos, @haider1, or might you run some where I said the same things? He might have more press than I do bu

arXiv:2605.15205v1 Announce Type: new Abstract: Improving the Theory of Mind (ToM) capability of Large Language Models (LLMs) is crucial for effective social interactions between these AI models and h

arXiv:2605.15543v1 Announce Type: cross Abstract: Many games of interest in the real world are often intractably large, thereby necessitating the use of game abstraction to shrink them in size, typica

The rise of agentic AI is reshaping what enterprise partnerships must deliver — and domain-specific AI is proving to be the real differentiator between systems that advise and systems that act. As AI

arXiv:2605.15459v1 Announce Type: new Abstract: The minima of modern neural network loss functions are typically not isolated, rather they form connected components of reparameterization invariant sol

arXiv:2511.19399v3 Announce Type: replace-cross Abstract: Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are tr

arXiv:2512.09673v3 Announce Type: replace-cross Abstract: Equivariant neural networks encode the intrinsic symmetry of data as an inductive bias, which has achieved impressive performance in wide doma

arXiv:2605.15682v1 Announce Type: new Abstract: Large-scale pre-trained diffusion models have been extensively adopted for real-world image Super-Resolution because of their powerful generative priors

arXiv:2605.15952v1 Announce Type: cross Abstract: Teleoperation promises to extend the operational envelope of automated vehicles, yet it critically depends on network latency and video quality. We re

arXiv:2605.15542v1 Announce Type: new Abstract: GUI agents powered by Multimodal Large Language Models (MLLMs) have demonstrated impressive capability in understanding and executing user instructions.

arXiv:2605.15461v1 Announce Type: cross Abstract: Building state-of-the-art (SOTA) predictive models for drug discovery requires expensive search over tools, architectures, and training strategies. Cu

arXiv:2605.15422v1 Announce Type: new Abstract: Modern RL post-training methods such as GRPO and DAPO train on N response sequences of R tokens sampled from a shared prompt of P tokens, but standard F

arXiv:2508.17034v2 Announce Type: cross Abstract: Noisy, partially overlapping data and the need for real-time processing pose major challenges for rigid registration. Considering that feature-based m

Chris Metinko / Axios: Dust, which helps enterprises design and deploy specialized AI agents that work alongside humans, raised a 40M Series B led by Abstract and Sequoia — Dust, a human-agent collabo

arXiv:2605.15676v1 Announce Type: new Abstract: Block discrete diffusion language models factorize a sequence autoregressively over fixed-size positional blocks, decoupling within-block parallel denoi

arXiv:2605.15935v1 Announce Type: new Abstract: Plasma shape control in tokamaks requires a real-time controller that tracks dynamically changing shape targets while tolerating diagnostic failures. Cl

arXiv:2509.23352v3 Announce Type: replace-cross Abstract: The integration of Reinforcement Learning (RL) into flow matching models for text-to-image (T2I) generation has driven substantial advances in

arXiv:2605.16239v1 Announce Type: new Abstract: We introduce a dynamics-level approach to watermarking generative models. Rather than embedding signals into model weights or outputs, we embed the wate

The World Health Organization declared an Ebola outbreak in the Democratic Republic of Congo and Uganda caused by the Bundibugyo virus a 'public health emergency of international concern,' with the ou

arXiv:2605.16003v1 Announce Type: new Abstract: Autoregressive video diffusion models enable open-ended generation through local attention and KV caching. However, existing training-free long-video op

arXiv:2603.03066v2 Announce Type: replace Abstract: Existing AI-generated video quality assessment (AIGVQA) methods mainly focus on global perceptual realism and coarse text-video alignment, while ove

arXiv:2605.15221v1 Announce Type: cross Abstract: AlphaEvolve and FunSearch have demonstrated the potential of combining large language models (LLMs) with evolutionary search for automated algorithm d

arXiv:2605.15592v1 Announce Type: new Abstract: Few-step image generation has seen rapid progress, with consistency and meanflow-based methods significantly reducing the number of sampling steps. Desp

arXiv:2602.01568v2 Announce Type: replace-cross Abstract: Multi-robot coordination often exhibits hierarchical structure, with some robots' decisions depending on the planned behaviors of others. Whil

arXiv:2510.04930v2 Announce Type: replace Abstract: Grokking is the phenomenon whereby, unlike the training performance, which peaks early in the training process, the test/generalization performance

arXiv:2605.15477v1 Announce Type: new Abstract: Egocentric world models present a promising direction for enabling agents to predict and plan, but their performance is constrained by the limited avail

arXiv:2605.15684v1 Announce Type: new Abstract: The Diffusion Transformer (DiT) architecture is the state-of-the-art paradigm for high-fidelity image generation, underpinning models like Stable Diffus

arXiv:2605.15397v1 Announce Type: new Abstract: Illegal gold mining in the Amazon rainforest causes deforestation, water contamination, and long-term ecosystem disruption, yet remains difficult to mon

Elon Musk in new interview: '10 years from now, probably 90% of all distance driven will be driven by the AI in a self-driving car. It will be quite a niche thing in 10 years to actually be driving yo

After around two hours of deliberation, the jury has reached a unanimous verdict in Musk v. Altman, the tech trial of the year. The group found that two claims were barred by the statute of limitation

A California jury unanimously ruled that Elon Musk's lawsuits against Sam Altman and OpenAI were filed too late under the statute of limitations . Musk had sought up to $134 billion in damages and Alt