Search: “model-releases”

arXiv:2602.14276v2 Announce Type: replace Abstract: Modern computer-use agents (CUA) must perceive a screen as a structured state, what elements are visible, where they are, and what text they contain

arXiv:2605.00218v1 Announce Type: cross Abstract: Mobile remote identity verification (RIdV) systems are exposed to attacks that manipulate or replace the facial video stream, including presentation a

arXiv:2603.08965v2 Announce Type: replace Abstract: Graph-structured knowledge systems -- from knowledge graphs to GraphRAG pipelines -- organize information into hierarchical communities, yet lack a

arXiv:2605.00176v1 Announce Type: cross Abstract: Double-machine-learning pipelines for the Average Dose-Response Function rely on kernel-weighted local-linear smoothers, which inherit unbounded funct

shipped Promptloop 🌀 Claude Code but for your prompts. a CLI agent that runs the full prompt-eval loop in one chat session: create test cases → run across models → generate reports → propose prompt →

arXiv:2605.00133v1 Announce Type: new Abstract: Modern crop advisory systems exhibit a critical limitation termed extit{economic blindness}. These systems primarily optimize for biological yield, ofte

Some awesome open models trending on HF right now, including models from @deepseek_ai, @Xiaomi, @OpenAI, @MistralAI, and @aipoolside. And of course Nemotron 3 Nano Omni from @NVIDIAAI So great to see!

arXiv:2605.00206v1 Announce Type: cross Abstract: Current transformers discard their rich latent residual stream between positions, reconstructing latent reasoning context at each new position and lea

arXiv:2605.00684v1 Announce Type: new Abstract: Temporal Video Grounding (TVG) aims to localize temporal moments in an untrimmed video that semantically correspond to given natural language queries. R

Google announced major AI infrastructure and platform advances at Google Cloud Next '26 in April 2026, including the Gemini Enterprise Agent Platform with new Agent Designer capabilities, and 8th Gene

arXiv:2605.00754v1 Announce Type: cross Abstract: Reward models (RMs) have become an indispensable fixture of the language model (LM) post-training playbook, enabling policy alignment and test-time sc

This is a very niche post, but they are good poems. I hadn't read Autopsychography until it came up from both Claude and Gemini. And if you haven't read Rilke, that poem, with its incredible end, is a

This would be a very good idea, especially if implemented well. Best thing the Trump administration has considered doing around AI. Breaking News: The Trump administration is discussing vetting new A.

arXiv:2605.00300v1 Announce Type: cross Abstract: Public inference benchmarks compare AI systems at the model and provider level, but the unit at which deployment decisions are actually made is the en

arXiv:2605.00390v1 Announce Type: new Abstract: We present extit{CluProp}, a novel framework that reimagines varied-density clustering in high-dimensional spaces as a label propagation process over ne

Research: TRE Python binding — ReDoS robustness demo If it's good enough for antirez to add to Redis I figured Ville Laurikari's TRE regular expression engine was worth exploring in a little more deta

Try Grok Grok 4.3 just became the smartest AI in the world at law and money It took #1 on TWO brutal private tests no other model could win on “Vals AI” benchmarks #1 CaseLaw (v2) - 79.31% accuracy Pr

arXiv:2510.21141v2 Announce Type: replace-cross Abstract: Internet speed tests are indispensable for users, ISPs, and policymakers, but their static flooding-based design imposes growing costs: a sing

arXiv:2312.12339v3 Announce Type: replace Abstract: Understanding visual inputs for a given task amidst varied changes is a key challenge posed by visual reinforcement learning agents. We propose exti

arXiv:2605.00538v1 Announce Type: new Abstract: Blood vessel segmentation and -tracing are essential tasks in many medical imaging applications. Although numerous methods exist, the prevailing segment

arXiv:2605.00116v1 Announce Type: new Abstract: In this article, we introduce ViLegalNLI, the first large-scale Vietnamese Natural Language Inference (NLI) dataset specifically constructed for the leg

arXiv:2505.03500v5 Announce Type: replace Abstract: Vision-language-action models (VLAs) often achieve high performance on demonstrated tasks but struggle significantly when required to extrapolate, c

Sam Altman announced on X that OpenAI would provide something special for applicants who couldn't attend the GPT-5.5 party due to space limitations. The post suggests OpenAI is offering a consolation

we're on an Open Model mission to help builders create world class agents >20x cheaper than what they have today a couple things have become evident recently: 1. The age of the token subsidy is being

arXiv:2605.00817v1 Announce Type: new Abstract: Large language models (LLMs) often achieve strong performance on reasoning benchmarks, but final-answer accuracy alone does not show whether they faithf

arXiv:2605.00796v1 Announce Type: cross Abstract: Background: Patient-facing medical chatbots based on retrieval-augmented generation (RAG) are increasingly promoted to deliver accessible, grounded he

arXiv:2605.00226v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly tasked with strategic decision-making under incomplete information, such as in negotiation and policymakin

This is a Wordle game result posted by Anthropic on X (formerly Twitter), showing that the puzzle was solved on the sixth and final attempt. The sequence of colored tiles indicates the letter feedback

This entry documents a Wordle game result where Anthropic solved puzzle #1,780 in three attempts, using emoji indicators to show letter positions (yellow for correct letters in wrong positions, green

NIST: An evaluation by NIST's CAISI says DeepSeek V4 Pro lags behind leading US AI models by about eight months and is the most capable Chinese AI model to date — In April 2026, the Center for AI Stan

Demis Hassabis says he plays chess with Gemini to trace the model's chain-of-thought. As a former chess prodigy, he can tell when the model starts reasoning itself into trouble. Sometimes it sees a bl

efficiency is back on the menu again boys https://x.com/jbhuang0604/status/2050686882653065496?s=46 Keep getting rate-limited by Claude, so I tried out DeepSeek V4 for the first time. After 10M+ token

SpaceX's Falcon 9 rocket successfully launched the CAS500-2 mission from a California spaceport, deploying 45 payloads into orbit. This mission demonstrates SpaceX's capability to conduct rideshare la

It's not hyperbole to call DualShot Recorder an overnight sensation. It took only 12 hours from the time it was released to hit number one on the App Store's list of top paid apps. It was a surprise s

I am not sure I would agree with all of this, but the relationship between Anthropic and Claude is quite different than the relationship between other labs and their models. And that shows up in lots

I have an utter respect for Richard Dawkins, for his brilliance, sheer intelligence, and his works. But @GaryMarcus has a valid critique [1]. [1] https://garymarcus.substack.com/p/richard-dawkins-and-

if even coding doesn’t make serious RoI for users, the jig is probably up. Economics of AI coding tools are crumbling. Cost per developer has doubled because cost of Claude code and microsoft copilot

I'm obsessed with running local LLMs. Been working with an engineer to build product(s) that are 100% local. A new model that came out recently instantly improved the quality of our product. We live i

it's always funny to me when these bot posts say we *just* launched deepagents... like nah man we've been carving this stone for close to a year now! Long-running agents almost always fail because the

Its getting hard to benchmark frontier agent performance on longer tasks. Repeated measurement is very expensive and there are differences between using models in harnesses versus via APIs. I suspect

Jessica Winter has been raising her children to detest A.I. Then her daughter’s public middle school began receiving Google Chromebooks, which came pre-installed with an all-ages version of Gemini, a

Meta bootstrapped China, reaped the positive PR for being “open”, and then went back to being closed. Meta abandons open-source Llama for proprietary Muse Spark https://thenewstack.io/meta-abandons-ll

David Keohane / Financial Times: Nintendo's share price has fallen by ~45% since August 2025, as rising memory chip costs drive investor concerns over profit margins for the Switch 2 — Higher memory c

our docs are a great place to get started! we try to make all conceptual guides applicable to a wide range of experience levels. if you need a more structured learning format, check out langchain acad

This work presents an explainability library for transformer models that provides tools for understanding transformer behavior through attributions and concept-based explanations . The resource likely

We used an automatic classifier which judged sycophancy by looking at whether Claude showed a willingness to push back, maintain positions when challenged, give praise proportional to the merit of ide