All entries

arXiv:2605.07325v1 Announce Type: cross Abstract: Deploying massive large language models (LLMs) as continuous cognitive engines for robotics is bottlenecked by the time-to-first-token (TTFT) latency

arXiv:2605.07724v1 Announce Type: cross Abstract: Recursive retraining of generative models poses a critical representation challenge: when synthetic outputs are curated based on a fixed reward signal

Daniel Stenberg / daniel.haxx.se: curl founder Daniel Stenberg says Mythos identified five vulnerabilities in curl, but a manual review found three were false positives and one was “just a bug” — yes,

Cursor, an AI coding assistant, has been integrated into Microsoft Teams, allowing users to mention @Cursor in channels to delegate tasks to an AI agent or retrieve information. This integration enabl

Cursor is an AI-powered code editor that analyzes entire conversation threads to understand context before generating solutions and automatically creating pull requests for team review. This feature s

arXiv:2605.07902v1 Announce Type: new Abstract: Submodular functions -- functions exhibiting diminishing returns -- are central to machine learning. When the objective is monotone and non-negative, th

arXiv:2605.07830v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents in offensive cybersecurity. In this paper, we reveal an interesting phenom

A data center campus in north-central Georgia consumed more than 29 million gallons of water without the local utility company initially realizing it, triggering low-pressure water flow to the host co

arXiv:2605.07453v1 Announce Type: new Abstract: Ancient and endangered languages pose a unique challenge for NLP: their datasets are inherently scarce, difficult to expand, and built from formulaic co

arXiv:2605.06865v1 Announce Type: new Abstract: Large language models (LLMs) are pre-trained and post-trained on vast amounts of loosely curated data, raising the possibility that these models may hav

arXiv:2605.07314v1 Announce Type: cross Abstract: Knowledge Graphs (KGs) have proven highly effective for recommendation systems by capturing latent item relationships, while recent integration of Lar

Dealing with quirks introduced by switching models doesn't have to be hard -- we recently introduced a 'harness profile' API in Deep Agents as a solution. Profiles adjust system prompts, tool descript

Dear @geoffreyhinton, I literally never said that AI systems “JUST regurgitate”; that’s plainly false. I don’t believe it, and I didn’t say it. (They do *sometimes* regurgitate, and the evidence for t

arXiv:2605.07665v1 Announce Type: cross Abstract: Estimating counterfactual distributions under interventions is central to treatment risk assessment and counterfactual generation tasks. Existing appr

arXiv:2605.06971v1 Announce Type: cross Abstract: Classical optimization theory largely focuses on fixed objective functions, whereas many modern learning systems operate in dynamic environments where

arXiv:2604.02753v2 Announce Type: replace Abstract: Open-vocabulary Object Detection (OVOD) enables models to recognize objects beyond predefined categories, but existing approaches remain limited in

arXiv:2510.18516v3 Announce Type: replace-cross Abstract: Neural recordings exhibit a distinctive form of heterogeneity rooted in differences in cell types, intrinsic circuit dynamics, and stochastic

arXiv:2603.04676v2 Announce Type: replace-cross Abstract: Multi-image reasoning remains a significant challenge for vision-language models (VLMs). We investigate a previously overlooked phenomenon: du

arXiv:2605.07074v1 Announce Type: new Abstract: Detecting AI-generated images across unseen architectures remains challenging, as existing models often overfit to generator-specific fingerprints and s

arXiv:2601.15127v3 Announce Type: replace-cross Abstract: Deploying federated learning across heterogeneous IoT device fleets requires tailored neural network architectures for each device class, yet

arXiv:2508.01994v2 Announce Type: replace Abstract: As the application of deep learning in dermatology continues to grow, the recognition of melanoma has garnered significant attention, demonstrating

DeepSeek V4 Flash is ~90% cheaper than GPT 5.4 Mini and ~70% cheaper than Gemini 3.1 Flash Lite For devs pushing ~500M tok/month, this is the difference between: GPT 5.4 Mini: ~394/mo Gemini 3.1 Flash

DeepSeek V4 Pro brings long-context reasoning and SOTA coding performance to Together AI serverless. The next layer is serving it efficiently: KV cache, prefix reuse, hybrid attention, batching, kerne

arXiv:2605.07940v1 Announce Type: new Abstract: Exemplar-based image editing applies a transformation defined by a source-target image pair to a new query image. Existing methods rely on a pair-of-pai

arXiv:2605.07024v1 Announce Type: new Abstract: Large Language Models for code generation frequently produce hallucinations in Fill-in-the-Middle (FIM) tasks -- plausible but incorrect completions suc

arXiv:2603.28113v2 Announce Type: replace Abstract: The global Lipschitz constant of a neural network is related to robustness and generalization, yet unlike in many classical models, it is not plainl

arXiv:2605.07694v1 Announce Type: cross Abstract: Single-channel speaker distance estimation has recently achieved centimeter-level accuracy in simulated environments, yet it remains unclear which com

arXiv:2510.04850v3 Announce Type: replace-cross Abstract: Reasoning distillation has emerged as a prevailing paradigm for transferring reasoning capabilities from large reasoning models to small langu

arXiv:2512.17129v2 Announce Type: replace Abstract: Biological systems can form complex three-dimensional structures through the collective behavior of agents that share a common update rule and opera

arXiv:2605.07781v1 Announce Type: new Abstract: Explicit neural representations such as 3D Gaussian Splatting (3DGS) enable high-fidelity and real-time novel view synthesis, yet optimize for alpha-com

arXiv:2605.07674v1 Announce Type: cross Abstract: Regulatory audits of AI systems increasingly rely on differential privacy (DP) to protect training data and model internals. We study audit design whe

arXiv:2605.07210v1 Announce Type: cross Abstract: PromptReps showed that an autoregressive language model can be used directly as a retriever by prompting it to generate dense and sparse representatio

arXiv:2605.07503v1 Announce Type: new Abstract: Efficiently aligning large-scale video diffusion models with human intent requires a scalable and trajectory-aware pathway that bridges the inherent dis

arXiv:2601.21951v2 Announce Type: replace-cross Abstract: We develop diffusion-based samplers for target distributions known up to a normalising constant. To this end, we rely on the well-known diffus

Sarah Perez / TechCrunch: Digg relaunches as an aggregator of AI news and social media commentary, with plans to expand to other topics; its previous reboot shut down in March — Digg is back from the

arXiv:2605.07494v1 Announce Type: new Abstract: Continual learning enables vision-language models to accumulate knowledge and adapt to evolving tasks without retraining from scratch. However, in multi

arXiv:2605.07221v1 Announce Type: new Abstract: Adapting foundation models to medical segmentation typically requires either backbone fine-tuning or high-capacity task-specific decoders, both of which

arXiv:2508.20909v2 Announce Type: replace Abstract: Foundation models pre-trained on large-scale natural image datasets offer a powerful paradigm for medical image segmentation. However, effectively t

arXiv:2506.13351v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) training of large language models (LLMs) on unverifiable tasks is challenging even when a reasonable-quality refer

arXiv:2602.22831v2 Announce Type: replace-cross Abstract: Moral benchmarks for LLMs typically score models on context-free prompts, implicitly treating the measured choice rate as stable. We test this

arXiv:2412.11194v2 Announce Type: replace-cross Abstract: Security vulnerabilities in software can have severe consequences; however, manual vulnerability detection is costly and does not scale, espec

arXiv:2605.07662v1 Announce Type: new Abstract: Low-precision number formats are widely used in modern machine learning systems due to their efficiency. Accurate direction representation is key to the

arXiv:2605.07551v1 Announce Type: new Abstract: Standard Importance Sampling (IS) collapses under label corruption because high-norm examples, prioritized for variance reduction, are often adversarial

arXiv:2605.07351v1 Announce Type: new Abstract: While Gaussian Splatting-based Feature Fields (GSFFs) have shown promise for visual localization, this paper highlights that photometrically optimized G

Amanda Silberling / TechCrunch: Discord launches Nitro Rewards, giving Nitro subscribers access to offers from gaming services like Xbox Game Pass and hardware like Logitech G at no extra cost — Disco

arXiv:2506.23875v4 Announce Type: replace-cross Abstract: Sequential computation via autoregressive generation can make difficult tasks learnable, but the generation order of intermediate states stron