model releases

RefAerial: A Benchmark and Approach for Referring Detection in Aerial Images

arXiv:2604.20543v1 Announce Type: new Abstract: Referring detection refers to locate the target referred by natural languages, which has recently attracted growing research interests. However, existin

Model Releases

Relative Entropy Estimation in Function Space: Theory and Applications to Trajectory Inference

DGX agent

arXiv:2604.20775v1 Announce Type: new Abstract: Trajectory Inference (TI) seeks to recover latent dynamical processes from snapshot data, where only independent samples from time-indexed marginals are

model-releasesarxiv-cs-lg

23 Apr 2026

RespondeoQA: a Benchmark for Bilingual Latin-English Question Answering

arXiv:2604.20738v1 Announce Type: new Abstract: We introduce a benchmark dataset for question answering and translation in bilingual Latin and English settings, containing about 7,800 question-answer

Rethinking Where to Edit: Task-Aware Localization for Instruction-Based Image Editing

arXiv:2604.20258v1 Announce Type: new Abstract: Instruction-based image editing (IIE) aims to modify images according to textual instructions while preserving irrelevant content. Despite recent advanc

retinalysis-vascx: An explainable software toolbox for the extraction of retinal vascular biomarkers

arXiv:2602.08580v2 Announce Type: replace-cross Abstract: Automatic extraction of retinal vascular biomarkers from color fundus images (CFI) is crucial for large-scale studies of the retinal vasculatu

REVNET: Rotation-Equivariant Point Cloud Completion via Vector Neuron Anchor Transformer

arXiv:2601.08558v2 Announce Type: replace Abstract: Incomplete point clouds captured by 3D sensors often result in the loss of both geometric and semantic information. Most existing point cloud comple

RExBench: Can coding agents autonomously implement AI research extensions?

arXiv:2506.22598v3 Announce Type: replace Abstract: Agents based on Large Language Models (LLMs) have shown promise for performing sophisticated software engineering tasks autonomously. In addition, t

RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-N Ranking

arXiv:2604.20623v1 Announce Type: cross Abstract: Traditional change detection identifies where changes occur, but does not explain what changed in natural language. Existing remote sensing change cap

Scaling Self-Play with Self-Guidance

model-releasesarxiv-cs-lg

arXiv:2604.20209v1 Announce Type: new Abstract: LLM self-play algorithms are notable in that, in principle, nothing bounds their learning: a Conjecturer model creates problems for a Solver, and both i

SceneOrchestra: Efficient Agentic 3D Scene Synthesis via Full Tool-Call Trajectory Generation

arXiv:2604.19907v1 Announce Type: new Abstract: Recent agentic frameworks for 3D scene synthesis have advanced realism and diversity by integrating heterogeneous generation and editing tools. These to

SciCoQA: Quality Assurance for Scientific Paper--Code Alignment

arXiv:2601.12910v3 Announce Type: replace-cross Abstract: Discrepancies between scientific papers and their code undermine reproducibility, a concern that grows as automated research agents scale scie

SegEarth-OV3: Exploring SAM 3 for Open-Vocabulary Semantic Segmentation in Remote Sensing Images

arXiv:2512.08730v2 Announce Type: replace Abstract: Most existing methods for training-free open-vocabulary semantic segmentation are based on CLIP. While these approaches have made progress, they oft

Self-Aware Vector Embeddings for Retrieval-Augmented Generation: A Neuroscience-Inspired Framework for Temporal, Confidence-Weighted, and Relational Knowledge

arXiv:2604.20598v1 Announce Type: cross Abstract: Modern retrieval-augmented generation (RAG) systems treat vector embeddings as static, context-free artifacts: an embedding has no notion of when it w

Self-Awareness before Action: Mitigating Logical Inertia via Proactive Cognitive Awareness

arXiv:2604.20413v1 Announce Type: new Abstract: Large language models perform well on many reasoning tasks, yet they often lack awareness of whether their current knowledge or reasoning state is compl

Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation

arXiv:2604.19777v1 Announce Type: cross Abstract: Large Language Models (LLMs) exhibit a well-documented positional bias when processing long input contexts: information in the middle of a context win

Semi-Supervised Flow Matching for Mosaiced and Panchromatic Fusion Imaging

arXiv:2604.20128v1 Announce Type: new Abstract: Fusing a low resolution (LR) mosaiced hyperspectral image (HSI) with a high resolution (HR) panchromatic (PAN) image offers a promising avenue for video

Separately, we’ve also heard reports of issues with Opus 4.7 in Claude Code. The team is working on those and we’ll share more as we roll ou…

model-releasesboris-cherny--x

Claude's Opus 4.7 model was experiencing issues when used within Claude Code, and Anthropic's team was actively investigating the problems with plans to provide updates as they continued the rollout.

SGAP-Gaze: Scene Grid Attention Based Point-of-Gaze Estimation Network for Driver Gaze

arXiv:2604.19888v1 Announce Type: new Abstract: Driver gaze estimation is essential for understanding the driver's situational awareness of surrounding traffic. Existing gaze estimation models use dri

Sign of the future: GPT-5.5

model-releasesethan-mollick

This article by Ethan Mollick likely discusses emerging capabilities and implications of GPT-5.5, OpenAI's next-generation language model, exploring how it represents advancement in AI technology and

SkillGraph: Graph Foundation Priors for LLM Agent Tool Sequence Recommendation

arXiv:2604.19793v1 Announce Type: new Abstract: LLM agents must select tools from large API libraries and order them correctly. Existing methods use semantic similarity for both retrieval and ordering

SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks

arXiv:2604.20087v1 Announce Type: new Abstract: Skills have become the de facto way to enable LLM agents to perform complex real-world tasks with customized instructions, workflows, and tools, but how

SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models

arXiv:2509.15174v3 Announce Type: replace-cross Abstract: WARNING: This paper contains examples of offensive materials. To address the proliferation of toxic content on social media, we introduce SMAR

Snow Flurries: How UNC6692 Employed Social Engineering to Deploy a Custom Malware Suite

model-releasesgoogle-cloud-ai

Written by: JP Glab, Tufail Ahmed, Josh Kelley, Muhammad Umair Introduction Google Threat Intelligence Group (GTIG) identified a multistage intrusion campaign by a newly tracked threat group, UNC6692,

So right now basically anyone with a 16GB VRAM card can go on @huggingface and download a model which BEATS Claude Sonnet 4.5, all running l…

model-releasesclem-delangue--x

So right now basically anyone with a 16GB VRAM card can go on @huggingface and download a model which BEATS Claude Sonnet 4.5, all running locally 🤯 LOOK AT THE WATER PARTICLES?? What are they doing i

Soft-Label Governance for Distributional Safety in Multi-Agent Systems

arXiv:2604.19752v1 Announce Type: cross Abstract: Multi-agent AI systems exhibit emergent risks that no single agent produces in isolation. Existing safety frameworks rely on binary classifications of

Sources: DeepSeek is fundraising to keep its researchers, some of whom have left for rivals whose valuations have soared; it is targeting a $20B valuation (Zijing Wu/Financial Times)

Zijing Wu / Financial Times: Sources: DeepSeek is fundraising to keep its researchers, some of whom have left for rivals whose valuations have soared; it is targeting a $20B valuation — Chinese AI sta

model-releasestechmeme

Spatio-temporal modelling of electric vehicle charging demand

model-releasesarxiv-cs-lg

arXiv:2604.19841v1 Announce Type: cross Abstract: Accurate forecasting of electric vehicle (EV) charging demand is critical for grid management and infrastructure planning. Yet the field continues to

SpeechParaling-Bench: A Comprehensive Benchmark for Paralinguistic-Aware Speech Generation

arXiv:2604.20842v1 Announce Type: cross Abstract: Paralinguistic cues are essential for natural human-computer interaction, yet their evaluation in Large Audio-Language Models (LALMs) remains limited

Super Apriel: One Checkpoint, Many Speeds

model-releasesarxiv-cs-lg

arXiv:2604.19877v1 Announce Type: new Abstract: We release Super Apriel, a 15B-parameter supernet in which every decoder layer provides four trained mixer choices -- Full Attention (FA), Sliding Windo

Supplement Generation Training for Enhancing Agentic Task Performance

arXiv:2604.20727v1 Announce Type: cross Abstract: Training large foundation models for agentic tasks is increasingly impractical due to the high computational costs, long iteration cycles, and rapid o

SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmark

arXiv:2604.20319v1 Announce Type: new Abstract: Fine-grained spatiotemporal reasoning on surgical videos is critical, yet the capabilities of Multi-modal Large Language Models (MLLMs) in this domain r

Survival of the Cheapest: Cost-Aware Hardware Adaptation for Adversarial Robustness

arXiv:2409.07609v2 Announce Type: replace-cross Abstract: Deploying adversarially robust machine learning systems requires continuous trade-offs between robustness, cost, and latency. We present an au

SweRank: Software Issue Localization with Code Ranking

arXiv:2505.07849v2 Announce Type: replace-cross Abstract: Software issue localization, the task of identifying the precise code locations (files, classes, or functions) relevant to a natural language

Taint-Style Vulnerability Detection and Confirmation for Node.js Packages Using LLM Agent Reasoning

arXiv:2604.20179v1 Announce Type: cross Abstract: The rapidly evolving Node.js ecosystem currently includes millions of packages and is a critical part of modern software supply chains, making vulnera

Text-to-Distribution Prediction with Quantile Tokens and Neighbor Context

arXiv:2604.20216v1 Announce Type: new Abstract: Many applications of LLM-based text regression require predicting a full conditional distribution rather than a single point value. We study distributio

Thanks @lennysan for a great conversation about how Claude Code maintains product velocity, how the product management role is shifting in t…

Thanks @lennysan for a great conversation about how Claude Code maintains product velocity, how the product management role is shifting in the AI era, and the future of work! https://open.spotify.com/

model-releasesthariq--x

That browser version of LiteParse is available here: https://simonw.github.io/liteparse/ Detailed notes on how I built it using Claude Code …

model-releasessimon-willison--x

That browser version of LiteParse is available here: https://simonw.github.io/liteparse/ Detailed notes on how I built it using Claude Code (running for an hour) on my blog: https://simonwillison.net/

The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models

arXiv:2604.20225v1 Announce Type: new Abstract: Evaluating the multilingual and multicultural capabilities of Large Language Models (LLMs) is essential for their global utility. However, current bench

The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning

arXiv:2603.29025v2 Announce Type: replace-cross Abstract: Large language models systematically fail when a salient surface cue conflicts with an unstated feasibility constraint. We study this through

The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents

arXiv:2511.03690v2 Announce Type: replace-cross Abstract: Agents are now used widely in the process of software development, but building production-ready software engineering agents is a complex task

The Ratchet Effect in Silico through Interaction-Driven Cumulative Intelligence in Large Language Models

arXiv:2507.21166v2 Announce Type: replace-cross Abstract: Human intelligence scales through cumulative cultural evolution (CCE), a ratchet process in which innovations are retained against entropic dr

The Role and Relationship of Initialization and Densification in 3D Gaussian Splatting

arXiv:2603.20714v2 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) has become the method of choice for photo-realistic 3D reconstruction of scenes, due to being able to efficiently and a

ThermoQA: A Three-Tier Benchmark for Evaluating Thermodynamic Reasoning in Large Language Models

arXiv:2604.19758v1 Announce Type: new Abstract: We present ThermoQA, a benchmark of 293 open-ended engineering thermodynamics problems in three tiers: property lookups (110 Q), component analysis (101

Things have been degrading super fast in Claude Code. I still use Claude Code, but my default is now Codex. I still prefer Opus models for c…

Things have been degrading super fast in Claude Code. I still use Claude Code, but my default is now Codex. I still prefer Opus models for coding, and so I will try again with the fixes. I appreciate

model-releasesdair-ai--x

Three shifts in the AI stack today: - OpenAI ships GPT-5.5 as a mid-cycle drop before its IPO - Hugging Face's ML Intern beats Claude Code a…

model-releasesclem-delangue--x

Three shifts in the AI stack today: - OpenAI ships GPT-5.5 as a mid-cycle drop before its IPO - Hugging Face's ML Intern beats Claude Code and Codex on research - Pliny used Claude Opus 4.7 to jailbre

tldr: claude code changed some harness settings which degraded perf. these small harness tweaks can matter a lot! 1. default reasoning high …

model-releasesharrison-chase--x

tldr: claude code changed some harness settings which degraded perf. these small harness tweaks can matter a lot! 1. default reasoning high -> medium 2. bug that accidentally evicted thinking blocks o

To Know is to Construct: Schema-Constrained Generation for Agent Memory

arXiv:2604.20117v1 Announce Type: new Abstract: Constructivist epistemology argues that knowledge is actively constructed rather than passively copied. Despite the generative nature of Large Language

Tokenised Flow Matching for Hierarchical Simulation Based Inference

arXiv:2604.20723v1 Announce Type: cross Abstract: The cost of simulator evaluations is a key practical bottleneck for Simulation Based Inference (SBI). In hierarchical settings with shared global para