3,694 items tracked: 32 reported by two or more outlets, the rest by a single source. Most-corroborated first.
arXiv:2602.01683v2 Announce Type: replace-cross Abstract: Transitioning Multimodal Large Language Models (MLLMs) from offline to online streaming video understanding is essential for continuous perception.
arXiv:2602.04899v3 Announce Type: replace-cross Abstract: We present a data poisoning attack -- Phantom Transfer -- with the property that, even if you know precisely how the poison was placed into an otherwise benign da…
arXiv:2602.07535v2 Announce Type: replace-cross Abstract: Acute ischemic stroke requires rapid treatment decisions that are strongly guided by emergency imaging.
arXiv:2602.15397v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models leveraging the native autoregressive paradigm of Vision-Language Models (VLMs) have demonstrated superior instruction-followin…
arXiv:2602.19171v4 Announce Type: replace-cross Abstract: Sketch constraints specify geometric conditions for constructing and modifying parametric CAD models.
arXiv:2603.13228v3 Announce Type: replace-cross Abstract: Recent progress in text-conditioned human motion generation has been largely driven by diffusion models trained on large-scale human motion data.
arXiv:2603.25414v5 Announce Type: replace-cross Abstract: Concurrency, parallelism and distributed execution become truly fearless when the compiler tracks wait-for edges, proves multi-threaded work is sound and preserve…
arXiv:2604.03672v2 Announce Type: replace-cross Abstract: Government agencies must register, classify and route every citizen appeal within statutory time limits, and much of this work is still done by hand.
arXiv:2604.10166v2 Announce Type: replace-cross Abstract: Intelligent operation of thermal energy networks aims to improve energy efficiency, reliability, and operational flexibility through data-driven control, predicti…
arXiv:2604.12440v3 Announce Type: replace-cross Abstract: Industrial anomaly inspection requires complementary capabilities: explaining an observed defect, localizing its pixels, and synthesizing a controlled edit.
arXiv:2604.21231v3 Announce Type: replace-cross Abstract: Efficient inference for on-device Large Language Models (LLMs) remains challenging due to limited hardware resources and the high cost of the prefill stage, which…
arXiv:2605.07604v2 Announce Type: replace-cross Abstract: 3D animal reconstruction in the wild remains challenging due to large species variation, frequent occlusions, and the prevalence of multi-animal scenes, while exi…
arXiv:2605.11015v2 Announce Type: replace-cross Abstract: Software vulnerability detection plays a critical role in ensuring system security, where real-world auditing requires not only determining whether a function is…
arXiv:2605.22342v2 Announce Type: replace-cross Abstract: While 4D Gaussian Splatting (4DGS) has revolutionized high-fidelity dynamic reconstruction, safeguarding the intellectual property of these assets remains an open…
arXiv:2605.22737v4 Announce Type: replace-cross Abstract: Distillation attacks create a deployment trade-off for model providers: the same outputs that make a model more useful can also make it easier to imitate.
arXiv:2605.24911v2 Announce Type: replace-cross Abstract: Retrieval augmentation provides time series forecasters with historical continuations, yet even candidates that outperform the base forecast may fail to improve t…
arXiv:2605.27079v2 Announce Type: replace-cross Abstract: Off-policy reinforcement learning of pretrained flow policies remains challenging due to the instability of optimization arising from the multi-step sampling proc…
arXiv:2605.28510v3 Announce Type: replace-cross Abstract: Large language models (LLMs) for code completion and generation are increasingly used in software development, yet they may reproduce training examples verbatim a…
arXiv:2606.01833v2 Announce Type: replace-cross Abstract: Generative emulators of protein dynamics produce plausible trajectories at a fraction of the cost of molecular dynamics, but they inherit their training distribut…
arXiv:2606.05315v2 Announce Type: replace-cross Abstract: Implicit chain-of-thought (iCoT) methods aim to internalize reasoning in large language models, but often underperform explicit CoT prompting.
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).
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.
Isomorphic Labs Ltd., an Alphabet Inc.
TL;DR: A safety case for scheming must be able to substantiate these four key claims: scheming was not incentivized during training, strong evaluations and red teaming suggest that the model does not have a propensity to…