Search: “models”

Does Machine Unlearning Preserve Clinical Safety? A Risk Analysis for Medical Image Classification

arXiv:2604.23854v1 Announce Type: new Abstract: The application of Deep Learning in medical diagnosis must balance patient safety with compliance with data protection regulations. Machine Unlearning e

Model Releases

Don't just reset Codex rate limits for fun, it costs money. Don't just reset Codex rate limits for fun, it costs money. ... but the vibes ar…

DGX agent

Don't just reset Codex rate limits for fun, it costs money. Don't just reset Codex rate limits for fun, it costs money. ... but the vibes are good ... I have reset Codex rate limits for ALL paid plans

model-releasessam-altman--x

28 Apr 2026

EAD-Net: Emotion-Aware Talking Head Generation with Spatial Refinement and Temporal Coherence

arXiv:2604.23325v1 Announce Type: cross Abstract: Emotionally talking head video generation aims to generate expressive portrait videos with accurate lip synchronization and emotional facial expressio

Earlier this month, an Erdős problem that had been open for 60 years was solved with help from GPT-5.4 Pro. What happens now that AI is gett…

Earlier this month, an Erdős problem that had been open for 60 years was solved with help from GPT-5.4 Pro. What happens now that AI is getting good at math? OpenAI researchers @SebastienBubeck and @E

model-releasesopenai--x

ELSA: Exact Linear-Scan Attention for Fast and Memory-Light Vision Transformers

model-releasesarxiv-cs-cv

arXiv:2604.23798v1 Announce Type: cross Abstract: Existing attention accelerators often trade exact softmax semantics, depend on fused Tensor Core kernels, or incur sequential depth that limits FP32 t

Enterprises are not running out of AI ambition — they are running out of time to act on it

model-releasessiliconangle

Enterprise AI transformation has a new home: the boardroom. Across financial services, CEOs are now demanding results, not more roadmaps. As Google Cloud Next 2026 packed Las Vegas with announcements

Evaluating CUDA Tile for AI Workloads on Hopper and Blackwell GPUs

arXiv:2604.23466v1 Announce Type: cross Abstract: NVIDIA's CUDA Tile (CuTile) introduces a Python-based, tile-centric abstraction for GPU kernel development that aims to simplify programming while ret

Event-based SLAM Benchmark for High-Speed Maneuvers

model-releasesarxiv-cs-ro

arXiv:2604.24033v1 Announce Type: new Abstract: Event-based cameras are bio-inspired sensors with pixels that independently and asynchronously respond to brightness changes at microsecond resolution,

FDIM: A Feature-distance-based Generic Video Quality Metric for Versatile Codecs

model-releasesarxiv-cs-cv

arXiv:2604.24123v1 Announce Type: new Abstract: Video technology is advancing toward Ultra High Definition (UHD) and High Dynamic Range (HDR), which intensifies the need for higher compression efficie

Fix Initial Codes and Iteratively Refine Textual Directions Toward Safe Multi-Turn Code Correction

arXiv:2604.23989v1 Announce Type: cross Abstract: Recent work on large language models (LLMs) has emphasized the importance of scaling inference compute. From this perspective, the state-of-the-art me

Agents

FormalScience: Scalable Human-in-the-Loop Autoformalisation of Science with Agentic Code Generation in Lean

arXiv:2604.23002v1 Announce Type: new Abstract: Formalising informal mathematical reasoning into formally verifiable code is a significant challenge for large language models. In scientific fields suc

agentsarxiv-cs-ai

Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control

arXiv:2603.17834v2 Announce Type: replace-cross Abstract: Diffusion models and flow matching have become a cornerstone of robotic imitation learning, yet they suffer from a structural inefficiency whe

Generative Synthetic Data for Causal Inference: Pitfalls, Remedies, and Opportunities

arXiv:2604.23904v1 Announce Type: cross Abstract: Synthetic data offers a promising tool for privacy-preserving data release, augmentation, and simulation, but its use in causal inference requires pre

researcharxiv-cs-ai

GLM 5.1 from @Zai_org is now available on @FireworksAI_HQ Training Platform across the Managed and Training API workflows. Try SFT and DPO w…

model-releasesfireworks-ai--x

GLM 5.1 from @Zai_org is now available on @FireworksAI_HQ Training Platform across the Managed and Training API workflows. Try SFT and DPO with smart defaults or your own custom loss function with a 2

Google Cloud und das BSI C3A-Framework: Wie wir Digitale Souveränität in Deutschland konkret machen

model-releasesgoogle-cloud-ai

In unseren Gesprächen mit Führungskräften aus Wirtschaft und öffentlichem Sektor in Deutschland und Europa taucht immer wieder dieselbe Frage auf: Wie lassen sich modernste Innovationen mit zuverlässi

Google launches Ask YouTube, a conversational AI search 'experiment' that generates pages with videos and text summaries, for Premium users in the US aged 18+ (Jay Peters/The Verge)

Jay Peters / The Verge: Google launches Ask YouTube, a conversational AI search “experiment” that generates pages with videos and text summaries, for Premium users in the US aged 18+ — ‘Ask YouTube’ i

model-releasestechmeme

GSC-QEMit: A Telemetry-Driven Hierarchical Forecast-and-Bandit Framework for Adaptive Quantum Error Mitigation

model-releasesarxiv-cs-lg

arXiv:2604.24551v1 Announce Type: cross Abstract: Quantum error mitigation (QEM) is essential for extracting reliable results from near-term quantum devices, yet practical deployments must balance mit

HalalBench: A Multilingual OCR Benchmark for Food Packaging Ingredient Extraction

model-releasesarxiv-cs-cl

arXiv:2604.22754v1 Announce Type: cross Abstract: No standardized benchmark exists for evaluating OCR on food packaging, despite its critical role in automated halal food verification. Existing benchm

Hardware-Efficient Softmax and Layer Normalization with Guaranteed Normalization for Edge Devices

arXiv:2604.23647v1 Announce Type: cross Abstract: In Transformer models, non-GEMM (non-General Matrix Multiplication) operations -- especially Softmax and Layer Normalization (LayerNorm) -- often domi

researcharxiv-cs-lg

High-Dimensional Private Linear Regression with Optimal Rates

model-releasesarxiv-cs-lg

arXiv:2505.16329v2 Announce Type: replace-cross Abstract: Differentially private (DP) linear regression has received significant attention in the recent theoretical literature, with several approaches

I have been playing with the new Outlook agent, and it is fine, but really awkward to use, since you have to ask for things in a chatbot win…

model-releasesethan-mollick--x

I have been playing with the new Outlook agent, and it is fine, but really awkward to use, since you have to ask for things in a chatbot window, then go to your drafts, etc. And Claude Cowork does the

I pulled 3,182 tweets analyzing @NousResearch Hermes Agent versus Claude Code to understand exactly why developers are choosing one or the o…

model-releasesnous-research--x

I pulled 3,182 tweets analyzing @NousResearch Hermes Agent versus Claude Code to understand exactly why developers are choosing one or the other I want to figure out why people use Hermes vs Claude/ C

i think openai called it fear based marketing but mythos didn't get released because it's too dangerous, which was shortly after the whole d…

model-releasesyohei-nakajima--x

i think openai called it fear based marketing but mythos didn't get released because it's too dangerous, which was shortly after the whole dod thing, and i think trump said something like 'it's possib

ImmerIris: A Large-Scale Dataset and Benchmark for Off-Axis and Unconstrained Iris Recognition in Immersive Applications

model-releasesarxiv-cs-cv

arXiv:2510.10113v3 Announce Type: replace Abstract: Recently, iris recognition is regaining prominence in immersive applications such as extended reality as a means of seamless user identification. Th

Implicit Humanization in Everyday LLM Moral Judgments

arXiv:2604.22764v1 Announce Type: cross Abstract: Recent adoption of conversational information systems has expanded the scope of user queries to include complex tasks such as personal advice-seeking.

researcharxiv-cs-ai

In-depth Analysis of Graph-based RAG in a Unified Framework

arXiv:2503.04338v2 Announce Type: replace-cross Abstract: Graph-based Retrieval-Augmented Generation (RAG) has proven effective in integrating external knowledge into large language models (LLMs), imp

researcharxiv-cs-cl

In the last four Claude Code CLI releases, we’ve shipped 50+ stability and performance fixes. Faster resume, stable auth, lower memory, fewe…

model-releasesboris-cherny--x

Claude Code CLI has released over 50 stability and performance improvements in its last four updates, including faster resume functionality, more stable authentication, reduced memory usage, and fewer

IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Review

arXiv:2604.22861v1 Announce Type: cross Abstract: Scientific research relies on accurate information retrieval from literature to support analytical decisions. In this work, we introduce a new task, I

I've been trying to make transformers more agent-friendly: agentic CLI, a skill, doc rewrites, canonical examples. It felt a bit like shooti…

model-releasesclem-delangue--x

I've been trying to make transformers more agent-friendly: agentic CLI, a skill, doc rewrites, canonical examples. It felt a bit like shooting in the dark: hard to measure progress, and hard to ensure

I've been working on a side project for the last few weeks... what if you could have a Gemma powered app that would let you have a personal …

I've been working on a side project for the last few weeks... what if you could have a Gemma powered app that would let you have a personal assistant that could browse the internet with you, do resear

model-releasesollama--x

Latency and Cost of Multi-Agent Intelligent Tutoring at Scale

arXiv:2604.24110v1 Announce Type: cross Abstract: Multi-agent LLM tutoring systems improve response quality through agent specialization, but each student query triggers several concurrent API calls w

Applications

LatentStealth: Unnoticeable and Efficient Adversarial Attacks on Expressive Human Pose and Shape Estimation

arXiv:2505.12009v2 Announce Type: replace Abstract: Expressive human pose and shape estimation (EHPS) plays a central role in digital human generation, particularly in live-streaming applications. How

applicationsarxiv-cs-cv

Applications

Lattice-to-Total Thermal Conductivity Ratio: A Phonon-Glass Electron-Crystal Descriptor for Data-Driven Thermoelectric Design

arXiv:2511.21213v2 Announce Type: replace-cross Abstract: Thermoelectrics (TEs) are promising candidates for energy harvesting with performance quantified by figure of merit, ZT. To accelerate the dis

applicationsarxiv-cs-lg

LearnAlign: Data Selection for LLM Reinforcement Learning with Improved Gradient Alignment

arXiv:2506.11480v4 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a key technique for enhancing LLMs' reasoning abilities, yet its data ineffic

Learning in Blocks: A Multi Agent Debate Assisted Personalized Adaptive Learning Framework for Language Learning

arXiv:2604.22770v1 Announce Type: cross Abstract: Most digital language learning curricula rely on discrete-item quizzes that test recall rather than applied conversational proficiency. When progressi

Learning Latent Graph Geometry via Fixed-Point Schrodinger-Type Activation: A Theoretical Study

model-releasesarxiv-cs-lg

arXiv:2507.20088v3 Announce Type: replace Abstract: We study neural architectures in which each hidden layer is defined by the stationary state of a dissipative Schrodinger-type dynamics on a learned

Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows

arXiv:2604.23855v1 Announce Type: new Abstract: We present a deployed system that automates end-to-end customer support workflows inside an enterprise Business Process Management (BPM) platform. The a

safetyarxiv-cs-cl

Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs

arXiv:2509.00084v2 Announce Type: replace-cross Abstract: Test-time scaling (TTS) has gained widespread attention for enhancing LLM reasoning. Existing approaches such as Best-of-N and majority voting

Let's talk document formatting. Bold. Italics. Superscripts. Strikethroughs. The visual cues humans rely on every time we read a doc, and on…

model-releasesjerry-liu--x

Let's talk document formatting. Bold. Italics. Superscripts. Strikethroughs. The visual cues humans rely on every time we read a doc, and ones existing OCR benchmarks completely ignore. 😱'199' struck

LLM-Guided Agentic Floor Plan Parsing for Accessible Indoor Navigation of Blind and Low-Vision People

arXiv:2604.23970v1 Announce Type: new Abstract: Indoor navigation remains a critical accessibility challenge for the blind and low-vision (BLV) individuals, as existing solutions rely on costly per-bu

Looking for the Bottleneck in Fine-grained Temporal Relation Classification

model-releasesarxiv-cs-cl

arXiv:2604.24620v1 Announce Type: new Abstract: Temporal relation classification is the task of determining the temporal relation between pairs of temporal entities in a text. Despite recent advanceme

Lost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrieval

arXiv:2604.23396v1 Announce Type: cross Abstract: Generative retrieval (GR) ranks documents by autoregressively generating document identifiers. Because many GR methods rely on trie-constrained beam s

Lovable launches its AI coding app on iOS and Android, letting users code via voice or text AI prompts, and allowing them to switch between a PC and mobile (Sarah Perez/TechCrunch)

Sarah Perez / TechCrunch: Lovable launches its AI coding app on iOS and Android, letting users code via voice or text AI prompts, and allowing them to switch between a PC and mobile — Apple's recent c

model-releasestechmeme

MarketBench: Evaluating AI Agents as Market Participants

arXiv:2604.23897v1 Announce Type: new Abstract: Markets are a promising way to coordinate AI agent activity for similar reasons to those used to justify markets more broadly. In order to effectively p

MIPIC: Matryoshka Representation Learning via Self-Distilled Intra-Relational and Progressive Information Chaining

arXiv:2604.24374v1 Announce Type: new Abstract: Representation learning is fundamental to NLP, but building embeddings that work well at different computational budgets is challenging. Matryoshka Repr

safetyarxiv-cs-cl

Applications

MOCA: A Transformer-based Modular Causal Inference Framework with One-way Cross-attention and Cutting Feedback

arXiv:2604.23107v1 Announce Type: cross Abstract: Causal effect estimation from observational data requires careful adjustment for confounding. Classical estimators such as inverse probability weighti

applicationsarxiv-cs-lg

MotionHiFlow: Text-to-motion via hierarchical flow matching

arXiv:2604.23264v1 Announce Type: new Abstract: Text-to-motion generation aims to generate 3D human motions that are tightly aligned with the input text while remaining physically plausible and rich i

safetyarxiv-cs-cv

MultiDx: A Multi-Source Knowledge Integration Framework towards Diagnostic Reasoning

arXiv:2604.24186v1 Announce Type: cross Abstract: Diagnostic prediction and clinical reasoning are critical tasks in healthcare applications. While Large Language Models (LLMs) have shown strong capab