Knowledge catalogue
arXiv:2603.03756v3 Announce Type: replace-cross Abstract: While large language models (LLMs) show promise in scientific discovery, existing research focuses on inference or feedback-driven training, l
arXiv:2605.03601v1 Announce Type: new Abstract: We study the realization map of deep ReLU networks, focusing on when a function determines its parameters up to scaling and permutation. To analyze hidd
arXiv:2605.02971v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit severe multilingual safety misalignment: they possess strong safeguards in high-resource languages but remain hig
arXiv:2605.01189v1 Announce Type: new Abstract: Clinical AI adoption is hindered by the black-box/grey-box nature of high-performing models, which lack the ontological grounding and narrative transpar
omg @bcherny with banger quotes “the future is more async agents… this is why we emphasize verification” “if you’re familiar with higher order functions, routines are higher order prompts” “default is
arXiv:2511.11362v2 Announce Type: replace-cross Abstract: On-device fine-tuning is a critical capability for edge AI systems, which must support adaptation to different agentic tasks under stringent m
arXiv:2511.08717v4 Announce Type: replace-cross Abstract: Optimal control of the future is the next frontier for AI. Current approaches to this problem are typically rooted in reinforcement learning (
arXiv:2605.03490v1 Announce Type: new Abstract: The clinical integration of deep learning models for brain tumor diagnosis in neuro-oncology is severely constrained by limited expert-annotated MRI dat
arXiv:2605.03848v1 Announce Type: new Abstract: Estimating how well a person performs an action, rather than which action is performed, is central to coaching, rehabilitation, and talent identificatio
arXiv:2410.09457v2 Announce Type: replace Abstract: Modern cryptographic methods for implementing privacy-preserving LLMs such as gls{HE} require the LLMs to have a polynomial form. Forming such a rep
Claude Code on desktop includes a preview feature that allows users to provide context to Claude by attaching DOM elements or drawing directly with a pencil tool. This functionality streamlines the pr
arXiv:2605.03434v1 Announce Type: new Abstract: Reinforcement learning is one of the most challenging learning paradigms where efficacy and efficiency gains are extremely valuable. Hierarchical reinfo
arXiv:2605.03999v1 Announce Type: new Abstract: Vision Transformers (ViTs) achieve state-of-the-art segmentation accuracy but require large training datasets because each layer has unique parameters t
arXiv:2605.03824v1 Announce Type: new Abstract: Complex information needs may involve set-compositional queries using conjunction, disjunction, and exclusion, yet it remains unclear whether current re
arXiv:2603.18196v3 Announce Type: replace-cross Abstract: Investigating cybersecurity incidents requires collecting and analyzing evidence from multiple log sources, including intrusion detection aler
arXiv:2605.03269v1 Announce Type: cross Abstract: While Vision-Language-Action models (VLAs) have shown remarkable progress toward human-like generalist robotic policies through the versatile intellig
arXiv:2507.00435v2 Announce Type: replace-cross Abstract: We introduce RoboEval, a structured evaluation framework and benchmark for robotic manipulation that augments binary success with principled b
arXiv:2605.03919v1 Announce Type: cross Abstract: Reservoir geomodeling is central to subsurface characterization, but it remains challenging because conditioning data are sparse, geological heterogen
arXiv:2602.22575v2 Announce Type: replace Abstract: Attention scales quadratically with sequence length, fundamentally limiting long-context inference. Existing block-granularity sparsification can re
arXiv:2605.03788v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly explored as high-level reasoning engines for cyber-physical systems, yet their application to real-time
arXiv:2510.08150v3 Announce Type: replace Abstract: Unsupervised multi-source domain adaptation (UMDA) leverages labeled data from multiple source domains to generalize to an unlabeled target. While f
This OpenAI social media post highlights how young builders and developers are leveraging AI tools to create projects and applications now that AI development has become more accessible to non-experts
SenseNova U1 is an open-source unified multimodal model that integrates understanding, reasoning, and generation within a single architecture, with particular strength in creating complex infographics
arXiv:2605.03666v1 Announce Type: new Abstract: This work proposes a novel control and estimation approach for aerial manipulation of a cable-suspended load using Unmanned Aerial Vehicles (UAVs). Comm
arXiv:2605.03701v1 Announce Type: new Abstract: Event Causality Identification (ECI) requires models to determine whether a given pair of events in a context exhibits a causal relationship. While Larg
so cute! It's pretty magical how kids interact with tech. They just expect it to work for them. Here's mine talking to Reachy Mini via Gemini Live API. I didn't tell them how, they just did it. That's
SpaceXAI will provide @AnthropicAI with access to Colossus 1, one of the world’s largest and fastest-deployed AI supercomputers, to provide additional capacity for Claude → http://x.ai/news/anthropic-
arXiv:2510.24211v2 Announce Type: replace Abstract: Autoregressive (AR) modeling has recently emerged as a promising new paradigm in visual generation, but its practical adoption is severely constrain
arXiv:2603.03251v3 Announce Type: replace Abstract: Autoregressive decoding is bottlenecked by its sequential nature. Speculative decoding has become a standard way to accelerate inference by using a
arXiv:2605.03303v1 Announce Type: new Abstract: Graph unlearning remains a critical technique for supporting privacy-preserving and sustainable multimodal graph learning. However, we observe that exis
arXiv:2605.03849v1 Announce Type: new Abstract: Distillation-based acceleration has become foundational for making autoregressive streaming video diffusion models practical, with distribution matching
arXiv:2605.03534v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) grounds answers in retrieved passages, but retrieval is not verification: a passage can be topical and still fail t
@swyx @maheshmurag deep dive on the new dreaming feature in beta today https://x.com/claudeai/status/2052067400690851842?s=46 Dreaming reviews your agent's past sessions, extracts patterns, and curate
arXiv:2602.21204v3 Announce Type: replace-cross Abstract: Test-time training (TTT) with KV binding as sequence modeling layer is commonly interpreted as a form of online meta-learning that memorizes a
arXiv:2605.03073v1 Announce Type: new Abstract: Niche-domain Indic ASR -- digit strings, currency amounts, addresses, brand names, English/Indic codemix -- is under-served by both open-source SOTA and
this deepagents deploy https://docs.langchain.com/oss/python/deepagents/deploy (or at least directionally where we want to take it) what's missing? give us feedback! can someone PLEASE launch OS claud
This week made something clear: you shouldn't take what most tech ceos are saying publicly seriously! From “Anthropic is Misanthropic” to “Claude is good for humanity and was impressed.” Most ironic o
arXiv:2605.03789v1 Announce Type: cross Abstract: We propose Conformal Seasonal Pools (CSP), a training-free probabilistic time-series forecaster that mixes same-season empirical draws with signed res
Two frontier labs. One accelerated computing platform. Congrats to @SpaceX and @AnthropicAI on the new compute partnership, powered by 220,000+ NVIDIA GPUs inside Colossus 1. The future of AI runs on
Two weeks after release, Hy3 preview is #1 on @OpenRouter's weekly leaderboard with 3.66T tokens processed, up 298% week-over-week. #1 in overall usage, tool calls, and coding. 15.4% market share acro
Uber has integrated OpenAI's technology to enhance its platform, helping drivers optimize earnings through intelligent features and enabling users to book rides more efficiently. This partnership like
arXiv:2605.03950v1 Announce Type: new Abstract: Although recent LMMs have become much stronger at visual perception, they remain unreliable on problems that require multi-step reasoning over visual ev
arXiv:2605.03614v1 Announce Type: new Abstract: Visual affordances identify regions in an image with potential interactions, offering a novel paradigm for scene understanding. Recognizing affordances
arXiv:2502.04419v3 Announce Type: replace-cross Abstract: Generating synthetic datasets via large language models (LLMs) has emerged as a promising approach to improve LLM performance. However, LLMs i
arXiv:2605.03716v1 Announce Type: new Abstract: Multimodal visual object tracking can be divided into to several kinds of tasks (e.g. RGB and RGB+X tracking), based on the input modality. Existing met
arXiv:2505.16208v2 Announce Type: replace-cross Abstract: We apply Echo-State Networks to predict time series and statistical properties of the competitive Lotka-Volterra model in the chaotic regime.
arXiv:2605.01392v1 Announce Type: cross Abstract: Recent advancements in Large Language Models (LLMs) have demonstrated significant potential across a wide range of software engineering tasks, includi
arXiv:2605.03752v1 Announce Type: new Abstract: Multi Armed Bandit (MAB) algorithms are a cornerstone of reinforcement learning and have been studied both theoretically and numerically. One of the mos
@vasuman We've been saying this for months. The best compliment you can give an AI system is that it behaves exactly as expected. Every time. We built a campaign around it. It's called Boring AI: http
Harrison Chase expresses enthusiasm about collaborating with Harvey on their Long Horizon Legal Agent Benchmark, highlighting the value of developing industry-specific benchmarks for AI evaluation. Th
This article from Hugging Face discusses an approach to reinforcement learning (RL) that prioritizes ensuring model correctness as a foundational step before applying corrections or refinements. The p
We're winding back our peak hours limit reduction and doubling 5 hour limits. Excited to partner with SpaceX to bring you more compute and we'll keep pushing to bring you the best coding agent in the
We’ve agreed to a partnership with @SpaceX that will substantially increase our compute capacity. This, along with our other recent compute deals, means that we’ve been able to increase our usage limi
What if you could extract text from any photo on your phone? We built LlamaParse Mobile, an @expo + @reactnative app for iOS & Android, powered by the LlamaParse TypeScript SDK 📱 Three steps, that’s i
arXiv:2605.02187v1 Announce Type: cross Abstract: Bring-Your-Own-Key (BYOK) agent architectures let users route LLM traffic through third-party relays, creating a critical integrity gap: a malicious r
Anthropic shared their Wordle game result for puzzle #1,781, solved in 3 attempts with a final correct answer shown by five green squares (all letters in correct positions). The emoji grid represents
xAI and SpaceXAI have just made Colossus 1 available to Anthropic to support Claude. This means more than 220,000 NVIDIA GPUs in one of the world’s largest and fastest-built AI superclusters are now h
arXiv:2605.02836v1 Announce Type: new Abstract: We introduce PLACE (Persistence-Landmark Analytic Classification Engine), a closed-form pipeline for classifying point clouds and graphs through their p
arXiv:2605.02777v1 Announce Type: new Abstract: Offline safe reinforcement learning often requires policies to adapt at deployment time to safety budgets that vary across episodes or change within a s
A few days ago i wrote a post about how we use the LangGraph checkpointer to optimize storage. Today, LangGraph released v1.2 with a really nice feature: DeltaChannel, a new channel type that stores o