Knowledge catalogue
arXiv:2604.14781v1 Announce Type: new Abstract: Obstacle detection in railway environments is crucial for ensuring safety. However, very few studies address the problem using a complete, modular, and
arXiv:2604.13047v1 Announce Type: cross Abstract: In recent years, the spread of fake news has triggered a growing interest in Information Disorders (ID) on social media, a phenomenon that has become
arXiv:2604.14180v1 Announce Type: new Abstract: We train a 318M-parameter Transformer language model from scratch on a curated corpus of 1.56 billion tokens of pure Classical Chinese, with zero Englis
ICLR 2026 is a major international conference on machine learning and deep learning where Apple's research team will present their latest work and innovations in representation learning. The conferenc
arXiv:2604.14240v1 Announce Type: cross Abstract: The simulation of complex systems increasingly relies on sophisticated but fundamentally opaque computational black-box simulators. Surrogate models p
arXiv:2604.14329v1 Announce Type: new Abstract: Non-violent street robberies (snatch-and-run) are difficult to detect automatically because they are brief, subtle, and often indistinguishable from ben
Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude. Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on t
Introducing expanded coverage for image generation models in Hermes Agent and Nous Portal Tool Gateway! Choose models from ChatGPT Image, Nano Banana, z-Image, FLUX, and more! Access now with `hermes
We are launching Flagship, a native feature flag service built on Cloudflare’s global network to eliminate the latency of third-party providers. By using KV and Durable Objects, Flagship allows for su
Databricks introduced Genie Agent Mode, a feature that enables autonomous AI agents to perform tasks within the Databricks platform by interpreting natural language instructions and executing data ope
Amazon Bedrock now supports cost allocation by IAM principal (users and roles) in AWS Cost and Usage Report 2.0 and Cost Explorer, enabling customers to understand and attribute inference costs across
Introducing “Is It Poison?” Our new reality show where contestants are given identical bottles. Some are safe. Some are not. With limited information, they decide: drink, pass, or persuade someone els
The Agent Readiness score can help site owners understand how well their websites support AI agents. Here we explore new standards, share Radar data, and detail how we made Cloudflare’s docs the most
arXiv:2603.03897v3 Announce Type: replace-cross Abstract: Foundation models have demonstrated impressive capabilities across diverse domains, while imitation learning provides principled methods for r
Simon Willison discusses the perception that LLMs and coding agents are primarily useful for greenfield development (starting new projects from scratch) rather than for maintaining and modifying large
This post by Harrison Chase (LangChain creator) discusses the importance of timing in updating information systems or memory mechanisms in AI applications, comparing real-time updates ('in the loop')
It's never been easier for your agent to harness the power of Hugging Face, from account creation to getting your own finetuned model, with everything in between, without any manual action on your end
arXiv:2604.15109v1 Announce Type: new Abstract: Despite the rapid advancement of Large Language Models (LLMs), uncertainty quantification in LLM generation is a persistent challenge. Although recent a
This post describes how creators achieved over 10 million organic impressions using vibecoded videos created with Replit Animation, a tool for programmatically generating animated content. The author
This year's PyCon US is coming up next month from May 13th to May 19th, with the core conference talks from Friday 15th to Sunday 17th and tutorial and sprint days either side. It's in Long Beach, Cal
arXiv:2411.09209v5 Announce Type: replace Abstract: Audio-driven portrait animation has made significant advances with diffusion-based models, improving video quality and lipsync accuracy. However, th
just dropped my first video in a 5 part series where we build a full travel planner app on Replit and i am so excited 🌍✈️ as a software engineer, design has always felt a little out of reach for me. l
arXiv:2604.05158v2 Announce Type: replace Abstract: Large language models encode extensive world knowledge valuable for zero-shot named entity recognition. However, their causal attention mechanism, w
arXiv:2604.14795v1 Announce Type: new Abstract: Visual Geometry Foundation Models (VGFMs) demonstrate remarkable zero-shot capabilities in local reconstruction. However, deploying them for kilometer-l
arXiv:2407.00809v3 Announce Type: replace Abstract: This paper introduces the Kernel Neural Operator (KNO), a provably convergent operator-learning architecture that utilizes compositions of deep kern
Maxwell Zeff / Wired: Kevin Weil, OpenAI's former CPO who became VP of OpenAI for Science, is leaving the company; Prism, a web app for scientists launched in Jan., will be shuttered — The former Inst
arXiv:2604.14799v1 Announce Type: new Abstract: Effective abstention (EA), recognizing evidence insufficiency and refraining from answering, is critical for reliable multimodal systems. Yet existing e
arXiv:2506.19807v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs), particularly slow-thinking models, often exhibit severe hallucination, outputting incorrect content due to an in
arXiv:2604.15141v1 Announce Type: new Abstract: Higher-order learning is fundamentally rooted in exploiting compositional features. It clearly hinges on enriching the representation by more elaborate
arXiv:2604.00313v2 Announce Type: replace Abstract: Automated species classification from underwater imagery is bottlenecked by the cost of expert annotation, and supervised models trained on one data
arXiv:2510.05486v2 Announce Type: replace Abstract: LLMs have been widely used in planning, either as planners to generate action sequences end-to-end, or as formalizers to represent the planning doma
arXiv:2502.16761v2 Announce Type: replace Abstract: Large language models (LLMs) present novel opportunities in public opinion research by predicting survey responses in advance during the early stage
arXiv:2601.11227v2 Announce Type: replace Abstract: Output diversity is crucial for Large Language Models as it underpins pluralism and creativity. In this work, we reveal that controlling the languag
arXiv:2603.17512v4 Announce Type: replace Abstract: Large language models (LLMs) exhibit strong general intelligence, yet their multilingual performance remains highly imbalanced. Although LLMs encode
arXiv:2604.14034v1 Announce Type: cross Abstract: Recent advances in Generative Artificial Intelligence, particularly Large Language Models (LLMs), have stimulated growing interest in automating or as
arXiv:2604.00998v2 Announce Type: replace Abstract: Ground roll is a common type of coherent noise in seismic records, and its attenuation remains challenging due to its substantial overlap with usefu
Last week, Anthropic announced Project Glasswing alongside Claude Mythos Preview, a model they described as so powerful at finding vulnerabilities they couldn't release it. The announcement featured A
arXiv:2506.00433v4 Announce Type: replace Abstract: High-resolution image synthesis remains a core challenge in generative modeling, particularly in balancing computational efficiency with the preserv
arXiv:2604.14717v1 Announce Type: cross Abstract: Persistent language-model agents increasingly combine tool use, tiered memory, reflective prompting, and runtime adaptation. In such systems, behavior
arXiv:2509.23638v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) models face memory and PCIe latency bottlenecks when deployed on commodity hardware. Offloading expert weights to CPU memor
arXiv:2604.13243v1 Announce Type: cross Abstract: Gaze event detection is fundamental to vision science, human-computer interaction, and applied analytics. However, current workflows often require spe
arXiv:2604.15311v1 Announce Type: new Abstract: This paper focuses on the alignment of flow matching models with human preferences. A promising way is fine-tuning by directly backpropagating reward gr
arXiv:2604.14811v1 Announce Type: new Abstract: Ad hoc wireless networks exhibit complex, innate and coupled dynamics: node mobility, energy depletion and topology change that are difficult to model a
arXiv:2604.14568v1 Announce Type: cross Abstract: Visual reasoning models (VRMs) have recently shown strong cross-modal reasoning capabilities by integrating visual perception with language reasoning.
arXiv:2604.01197v2 Announce Type: replace-cross Abstract: Learning quantum states from measurement data is a central problem in quantum information and computational complexity. In this work, we study
arXiv:2601.18675v2 Announce Type: replace Abstract: We investigate whether temporal embedding models trained on longitudinal electronic health records can learn clinically meaningful representations w
arXiv:2604.14931v1 Announce Type: cross Abstract: Concatenating quantum error correction codes scales error correction capability by driving logical error rates down double-exponentially across levels
arXiv:2512.17091v2 Announce Type: replace Abstract: We propose a new approach for solving planning problems with a hierarchical structure, fusing reinforcement learning and MPC planning. Our formulati
arXiv:2604.15210v1 Announce Type: cross Abstract: Humor is one of the few cognitive tasks where getting the reasoning right matters as much as getting the answer right. While recent work evaluates hum
arXiv:2604.15065v1 Announce Type: new Abstract: Transformer-based detectors have advanced small-object detection, but they often remain inefficient and vulnerable to background-induced query noise, wh
Let's talk content faithfulness. Four days ago, we launched ParseBench, the first document OCR benchmark for AI agents. Its most fundamental metric asks: did the parser capture all the text, in order,
arXiv:2501.11711v2 Announce Type: replace Abstract: The COVID-19 pandemic has claimed millions of lives, spurring the development of diverse forecasting models. In this context, the true utility of co
arXiv:2512.04578v3 Announce Type: replace Abstract: Legal general intelligence (GI) refers to artificial intelligence (AI) that encompasses legal understanding, reasoning, and decision-making, simulat
arXiv:2604.14177v1 Announce Type: new Abstract: Grammatical error correction (GEC) and explanation (GEE) have made rapid progress, but real teaching scenarios also require learner-friendly pedagogical
Listen to the OpenAI Podcast on— Spotify https://open.spotify.com/show/0zojMEDizKMh3aTxnGLENP Apple https://podcasts.apple.com/us/podcast/openai-podcast/id1820330260 YouTube https://youtu.be/UZyH0nx5z
arXiv:2604.13348v1 Announce Type: new Abstract: We introduce CONCORD, a privacy-aware asynchronous assistant-to-assistant (A2A) framework that leverages collaboration between proactive speech-based AI
LLM agents loop, drift, and get stuck on hard reasoning tasks up to 30% of the time. Current fixes are either too blunt (hard step limits) or too expensive (LLM-as-judge adding 10-15% overhead per ste
arXiv:2604.14321v1 Announce Type: new Abstract: We tasked GPT-4.1 to read what baseball fans wrote about their game-day experience and predict the overall experience rating each fan gave on a 0-10 sur
arXiv:2601.14053v2 Announce Type: replace-cross Abstract: The field of artificial intelligence has undergone a revolution from foundational Transformer architectures to reasoning-capable systems appro
arXiv:2604.15149v1 Announce Type: new Abstract: As reinforcement Learning with Verifiable Rewards (RLVR) has become the dominant paradigm for scaling reasoning capabilities in LLMs, a new failure mode