model releases

Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection

arXiv:2605.30344v1 Announce Type: new Abstract: Recent advances in Vision-Language Models (VLMs) have achieved impressive performance across many tasks, yet prior studies report unsatisfactory perform

Model Releases

Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection

DGX agent

arXiv:2605.30189v1 Announce Type: cross Abstract: We show that LoRA adapters, the dominant distribution format for fine-tuned LLMs, can be reliably backdoored through training data poisoning while pre

model-releasesarxiv-cs-ai

29 May 2026

Took me a while to figure out what all the ESMFold2 rage was about. At first, the benchmarking data didn't look super remarkable to me but i…

model-releasesyann-lecun--x

Took me a while to figure out what all the ESMFold2 rage was about. At first, the benchmarking data didn't look super remarkable to me but it turns there are many impressive aspects: - Fully open sour

Toward Ethical Facial Age Estimation: A Generalized Zero-Shot Benchmark Without Training on Children's Data

arXiv:2605.29230v1 Announce Type: cross Abstract: Age estimation from facial images typically relies on training data that includes images of minors, a practice that raises serious ethical, legal, and

TRACE: Toulmin-based Reasoning Assessment through Constructive Elements for LLM CoT Evaluation

arXiv:2605.29656v1 Announce Type: new Abstract: Evaluating open-ended outputs from large language models (LLMs) remains challenging due to the absence of ground truth. Existing metrics rely on final-a

Training Deliberative Monitors for Black-Box Scheming Detection

arXiv:2605.29601v1 Announce Type: cross Abstract: As autonomous agents become more capable of performing real-world tasks, distinguishing scheming behavior from benign task pursuit may become a centra

Trends in AI and Human-AI Interaction in Clinical Trials -- A Hybrid Human-AI Exploration

arXiv:2605.29096v1 Announce Type: new Abstract: This paper examines records retrieved from the ClinicalTrials.gov registry to characterize temporal trends in AI terminology and the geographical distri

UA-Legal-Bench: A Benchmark for Evaluating Large Language Models on Ukrainian Legal Reasoning

arXiv:2605.29170v1 Announce Type: cross Abstract: Legal NLP benchmarks are overwhelmingly English-centric, leaving failure modes in morphologically rich, non-Latin-script languages undetected. We intr

Uncertainty-Aware Transfer Learning for Cross-Building Energy Forecasting: Toward Robust and Scalable District-Level Energy Management

arXiv:2605.29733v1 Announce Type: new Abstract: Scaling data-driven energy forecasting to district level requires models that can be re-used across buildings with minimal target-domain data and honest

Understanding Safety-Sensitive Expert Behavior in Mixture-of-Experts LLMs

arXiv:2605.29708v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) LLMs rely on sparse, router-driven expert activation, yet how safety alignment interacts with routed expert specialization rema

VE2VF: Vision-Enabled to Vision-Free Distillation via Real-world Reinforcement Learning for Robust Contact-Rich Manipulation

model-releasesarxiv-cs-ro

arXiv:2605.29564v1 Announce Type: new Abstract: When using reinforcement learning (RL) for contact-rich robotic manipulation, vision can provide task-relevant information that accelerates learning bey

Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question Answering

arXiv:2605.29648v1 Announce Type: new Abstract: Applying reinforcement learning to improve factual accuracy in knowledge-intensive question answering faces a reward design dilemma. Response-level rewa

VIDEO: @BlueOrigin major New Glenn static fire anomaly at Launch Complex-36 📷 @JerryPikePhoto/@NASASpaceflight

model-releasesanthropic--x

VIDEO: @BlueOrigin major New Glenn static fire anomaly at Launch Complex-36 📷 @JerryPikePhoto/@NASASpaceflight Media ANOMALY: @BlueOrigin have suffered a CATASTROPHIC EXPLOSION AT LAUNCH COMPLEX-36 📷

Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods

arXiv:2601.12500v2 Announce Type: replace Abstract: Counting and tracking dense crowds in large-scale scenes is a highly practical yet challenging problem. Existing methods mostly rely on fixed-camera

VideoFDB: Evaluating Full-Duplex Vision-Speech Capabilities in Conversational Agents

arXiv:2605.30256v1 Announce Type: cross Abstract: Natural human conversation is full-duplex and audio-visual: people simultaneously speak and listen while continuously interpreting and producing nonve

VitalAgent: A Tool-Augmented Agent for Reactive and Proactive Physiological Monitoring over Wearable Health Data

arXiv:2605.29483v1 Announce Type: new Abstract: Wearable devices enable continuous monitoring of physiological signals such as ECG and PPG, but existing mHealth systems are largely limited to task-spe

VLAConf: Calibrated Task-Success Confidence for Vision-Language-Action Models

model-releasesarxiv-cs-ro

arXiv:2605.29605v1 Announce Type: new Abstract: Confidence estimation for Vision-Language-Action (VLA) models is essential for robots to perform manipulation tasks in the open world, providing crucial

VPG: Visual Prefix Guidance for Autoregressive Image and Video Generation

arXiv:2605.30317v1 Announce Type: new Abstract: Autoregressive image and video generators are trained with teacher-forced histories but must sample from their own generated prefixes at inference time,

WASHH: An Anchor-Aware Whale-Guided Selection Hyper-Heuristic for Continuous Optimization and SVC Configuration

arXiv:2605.28844v1 Announce Type: cross Abstract: Learning-assisted algorithm design often has to make reliable search decisions under small evaluation budgets, where committing to a single metaheuris

Watch your avatar speak Spanish, English and Japanese https://x.com/DotCSV/status/2059676610400231599?s=20

model-releasesgoogle-ai--x

Watch your avatar speak Spanish, English and Japanese https://x.com/DotCSV/status/2059676610400231599?s=20 Sigo jugando con Omni! Efectivamente el modelo desbloquea un montón de casos de uso (e.g. tra

We’re taking steps to accelerate defensive progress in biology: - Launching Rosalind Biodefense to help trusted builders develop new biodefe…

We’re taking steps to accelerate defensive progress in biology: - Launching Rosalind Biodefense to help trusted builders develop new biodefense and pandemic preparedness capabilities. - Expanding trus

model-releasesopenai--x

What drives performance in molecular MPNNs? An operator-level factorial benchmark

arXiv:2605.30195v1 Announce Type: cross Abstract: Message-passing neural networks (MPNNs) are widely used for molecular property prediction, but their deployment as monolithic architectures makes it d

When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL

arXiv:2605.28918v1 Announce Type: new Abstract: For sparse, structured reinforcement-learning tasks with semantic reward-function interfaces, LLM-generated reward shaping is better framed as debugging

When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making

arXiv:2603.16673v4 Announce Type: replace-cross Abstract: Embodied robotic systems increasingly rely on large language model (LLM)-based agents to support high-level reasoning, planning, and decision-

When Should Models Change Their Minds? Contextual Belief Management in Large Language Models

arXiv:2605.30219v1 Announce Type: new Abstract: Long-horizon interactions require language models to manage accumulating information: when to update their state, when to preserve their state, and what

When the Same Coefficients Reach Different Places: Asymmetric Realizability in Transplanting Tokenizers across Large Language Models

arXiv:2601.00065v3 Announce Type: replace-cross Abstract: Tokenizer transplant in cross-vocabulary model composition reconstructs donor-only embedding rows as weighted combinations over shared lexical

When we say “LiteParse runs everywhere,” we mean it. Our WASM package is lightweight, minimal, and built for browser and edge runtimes, whic…

model-releasesjerry-liu--x

When we say “LiteParse runs everywhere,” we mean it. Our WASM package is lightweight, minimal, and built for browser and edge runtimes, which makes it a perfect fit for @cloudflare Workers. Using WebA

When you are talking to an LLM, you are speaking to a synthesized work of interactive fiction, not a real being.

model-releasesgary-marcus--x

When you are talking to an LLM, you are speaking to a synthesized work of interactive fiction, not a real being. ChatGPT, Claude, and Sydney are not their neural networks. If any LLM claims to be cons

Who can we trust? LLM-as-a-jury for Comparative Assessment

arXiv:2602.16610v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly applied as automatic evaluators for natural language generation assessment often using pairwise

Why Far Looks Up: Probing Spatial Representation in Vision-Language Models

arXiv:2605.30161v1 Announce Type: new Abstract: Vision-language models (VLMs) achieve strong performance on spatial reasoning benchmarks, yet it remains unclear whether this reflects structured 3D und

Why Specialist Models Still Matter: A Heterogeneous Multi-Agent Paradigm for Medical Artificial Intelligence

arXiv:2605.29744v1 Announce Type: new Abstract: The impressive performance of generalist large language models (LLMs) such as GPT and Claude in healthcare raises a critical question: will domain-speci

Windows users, this one’s for you. Computer use now works on Windows, so Codex can take action on your Windows computer. And with Windows su…

Windows users, this one’s for you. Computer use now works on Windows, so Codex can take action on your Windows computer. And with Windows support for Codex in the ChatGPT mobile app, you can start, re

model-releasesopenai--x

Wordle 1,804 4/6 ⬛🟨⬛⬛⬛ ⬛🟩⬛⬛🟨 ⬛🟩🟩🟩🟩 🟩🟩🟩🟩🟩

model-releasesanthropic--x

This entry documents a Wordle game result where Anthropic solved puzzle #1,804 in 4 attempts, using color-coded feedback (⬛ = incorrect letter, 🟨 = correct letter wrong position, 🟩 = correct letter co

World Models in Words: Auditing Physical State-Transition Commitments in Vision-Language Models

arXiv:2605.29585v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used to answer questions about physical scenes, yet most evaluations reduce performance to a final answer

YoCausal: How Far is Video Generation from World Model? A Causality Perspective

arXiv:2605.30346v1 Announce Type: new Abstract: As video diffusion models (VDMs) advance toward world models, a key question arises: do they truly understand causality, or merely overfit to statistica

$65B private round More than double the size of the largest IPO ever

model-releasesjeremy-howard--x

65B private round More than double the size of the largest IPO ever We've raised 65 billion in Series H funding at a $965 billion post-money valuation, led by @AltimeterCap, Dragoneer, @Greenoaks, and

A Bayesian Nonparametric Perspective on Mahalanobis Distance for Out of Distribution Detection

arXiv:2502.08695v2 Announce Type: replace-cross Abstract: Bayesian nonparametric methods are naturally suited to the problem of out-of-distribution (OOD) detection. However, these techniques have larg

A Broader View of Thompson Sampling

arXiv:2510.07208v2 Announce Type: replace Abstract: Thompson Sampling is one of the most widely used and studied bandit algorithms, known for its simple structure, low regret performance, and solid th

A Fresh Look at Lamarckian Evolution and the Baldwin Effect

arXiv:2605.28703v1 Announce Type: cross Abstract: Baldwinian and Lamarckian evolution have existed for a long time in evolutionary algorithms (EAs) without ever dominating the academic literature or p

A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks

arXiv:2605.28556v1 Announce Type: new Abstract: As agent capabilities advance, existing benchmarks, such as au^2-Bench, are becoming increasingly saturated. Yet constructing new benchmark tasks remain

A Multi-dimensional Framework for Evaluating Generalization in EEG Foundation Models

arXiv:2605.28563v1 Announce Type: cross Abstract: Evaluating foundation models under appropriate adaptation settings is essential for understanding the quality and transferability of the learned repre

A Query Engine for the Agents

arXiv:2605.27785v1 Announce Type: new Abstract: The fastest-growing data in production today is unstructured text: agent traces, chat logs, reasoning chains, model outputs. People want to analyze it,

A Simple State Space Model Excels at Multivariate Time Series Classification

arXiv:2605.27406v1 Announce Type: new Abstract: Structured state space models (SSMs) have recently emerged as a promising foundation for sequence modeling, with Mamba-based architectures demonstrating

A Unified Framework for the Evaluation of LLM Agentic Capabilities

arXiv:2605.27898v1 Announce Type: new Abstract: As LLMs are increasingly deployed as agents, reliable assessment of their agentic capabilities has become essential. However, reported benchmark scores

AdaDPO: Self-Adaptive Direct Preference Optimization with Balanced Gradient Updates

arXiv:2605.28440v1 Announce Type: new Abstract: DPO has become a widely adopted alternative to RLHF for aligning LLMs with human preferences, eliminating the need for a separate reward model or RL loo

Adaptive Bandit Algorithms for Contextual Matching Markets

arXiv:2605.28290v1 Announce Type: new Abstract: We study bandit learning in matching markets, where players and arms constitute the two market sides, and the players' utilities are linear in the arm c

Adaptive Cost-Efficient Evaluation for Reliable Patent Claim Generation

arXiv:2604.04295v3 Announce Type: replace Abstract: Automated patent claim validation demands low error tolerance. However, existing approaches face a rigidity-resource dilemma: lightweight encoders c

Adaptive Reservoir Computing for Multi-Scenario Chaotic System Forecasting

arXiv:2605.28145v1 Announce Type: new Abstract: We present an adaptive reservoir computing framework for the CTF-4-Science Lorenz benchmark, which evaluates machine learning models across twelve disti