3,698 items tracked: 33 reported by two or more outlets, the rest by a single source. Most-corroborated first.
arXiv:2606.12590v2 Announce Type: replace-cross Abstract: Preference optimization is increasingly used to post-train medical large vision-language models (LVLMs), yet it operates at a much coarser granularity than the on…
arXiv:2606.17924v2 Announce Type: replace-cross Abstract: Current Vision-Language-Action (VLA) models face a trade-off between efficient action generation and explicit deliberation.
arXiv:2606.18810v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative methods such as GRP…
arXiv:2606.22200v2 Announce Type: replace-cross Abstract: We study regression-based data fusion under uncertainty, where multiple noisy and biased measurement sources are available but ground-truth labels are absent duri…
arXiv:2607.11808v4 Announce Type: replace-cross Abstract: This paper proposes a human-centered artificial intelligence (HCAI) framework for AI-assisted lexicography.
arXiv:2608.00013v3 Announce Type: replace-cross Abstract: Choosing the right large language model (LLM) backbone is the most consequential decision when building a vision-language model (VLM), yet it remains fundamentall…
arXiv:2608.11704v2 Announce Type: replace-cross Abstract: Dynamic Time Warping (DTW)-based Nearest-Neighbor (NN) classifiers are effective for time-series classification but are vulnerable to mislabeled training samples…
arXiv:2608.19776v3 Announce Type: replace-cross Abstract: Current dexterous grasp planners primarily optimize for physical stability, focusing on whether an object can be grasped rather than how it should be grasped to s…
arXiv:2609.10739v2 Announce Type: replace-cross Abstract: Linear probes that decode the truth from a language model's activations have been proposed as deception monitors, and a truth probe scoring below chance on a mode…
arXiv:2609.12544v2 Announce Type: replace-cross Abstract: Clinical de-identification relies on accurately identifying personally identifiable information (PII).
Firmus said it had made the decision due to "recent market volatility and prevailing market conditions".
AI inference is fast becoming the workload that decides the economics of the AI boom.
Phyraxis AI reported $3bn
Technology stocks fell lower today following a report that artificial intelligence giant OpenAI Group PBC’s annualized revenue this year is about $20 billion less than what was previously reported by the media, sending s…
Gallatin AI Inc., a developer of military logistics software, today announced that it has raised $50 million in funding.
New Western open-weight models could give enterprises an alternative to Chinese and proprietary AI, but greater control also brings new responsibilities.
Fewer latent tokens promise cheaper diffusion.
Understanding and tracking a dynamic world are fundamental to visual intelligence.
World-action models inherit broad visual and physical priors from video pre-training.
Terminal agents solve tasks in software engineering and scientific research by executing commands in a terminal.
Creativity benchmarks for large language models (LLMs) vary widely in task and metric design.
Terminal agents are moving beyond local operations toward completing real-world professional tasks.
Attention Residuals (AttnRes) enables content-dependent retrieval over network depth, which can be viewed as single-stream softmax attention along the depth axis.
Power sampling improves large language model (LLM) reasoning at test time by sampling from a sharpened version of the base model's distribution.
Drag-based image editing provides an intuitive interface for spatially controlled image manipulation by allowing users to specify handle and target points.
We study when communication emerges between autonomous agents and what role an innate action selection architecture plays.
Efficient visual tokenization requires balancing representation compactness with the preservation of fine-grained image content.
Diffusion/flow models have emerged as the de facto paradigms for image generation, giving rise to a diverse family of modern generators with increasingly heterogeneous architectures and representations.
In this paper, we study physically grounded articulated 3D asset generation---moving the goal from reproducing how objects look to capturing how they move and function.
Large language models (LLMs) are increasingly explored for graph understanding and decision-making, while System One models such as Jev select directly from supplied options.
Visual representations are largely developed for understanding, yet what makes them useful for generation remains unclear.
On-policy distillation (OPD) trains a target policy on its own rollouts using token-level supervision from a stronger teacher, but typically relies on the teacher being substantially more capable than the target.
Recursive self-improvement (RSI) aims to transform interaction experience into persistent improvements, yet external feedback is costly and world-model predictions may become unreliable as policies evolve.
Evaluating large language models (LLMs) on AMLworld's smallest test splits is costly because each of over a million targets requires a separate graph prompt.
Anthropic says for the next two years, attackers will have the advantage
Veir series_c reported $110m
Anthropic is offering open-source projects a new way to check for vulnerabilities with its OSS Scanner.
This post was crossposted to the EA Forum TL;DR: If you enjoy LessWrong (and/or do EA/AI safety field building), you should consider starting a rationality reading group at your university.
Bitwise determinism makes large-scale pretraining easier to debug, validate, and resume reproducibly.
Isomorphic Labs Ltd., an Alphabet Inc.
Commitment comes as GPUzilla prepares to fortify Uncle Sam's arsenal with at least seven AI-optimized supers
Before there were cute little guys, there was Instinct.
Enterprises racing to put agents into production are learning that the AI improvement loop never really ends.
Under the program, the vendor provides enterprises with models that can defend against bad actors.
Bloom seed reported $3.6m
Turning a simulation idea into a working application means assembling assets, connecting physics and rendering, and checking that the scene behaves as intended.
Preparing CAD assets for robotics simulation requires more than converting geometry to OpenUSD: developers must configure and validate materials, collision...
It’s not always better to be more capable.
Manus, the creator of the eponymous artificial intelligence agent, has raised more than $500 million in funding.
The Chocolate Factory proposes a single universal agent for work