model releases

A Novel Global Context-aware Deep Neural Network for Enhanced Brain Tumor Segmentation using Magnetic Resonance Images

arXiv:2605.30510v1 Announce Type: cross Abstract: Brain cancer's severity necessitates precise brain tumor segmentation, which is crucial for effective brain tumor diagnosis. Manual identification, bu

Model Releases

A Visually Impaired Assistance Benchmark for VLM-as-a-Judge Evaluation

DGX agent

arXiv:2605.31351v1 Announce Type: new Abstract: AI-based Visually Impaired Assistance (VIA) remains challenging, largely due to the high cost of human evaluation. The VLM-as-a-Judge paradigm may offer

model-releasesarxiv-cs-cl

1 Jun 2026

AbstainGNN: Teaching Graph Neural Networks to Abstain for Graph Classification

arXiv:2605.30786v1 Announce Type: new Abstract: Graph classification is a core task in graph data mining with widespread real-world applications. Recent advances in graph neural networks (GNNs) have l

Adaptive NAD: Online and Self-adaptive Unsupervised Network Anomaly Detector

arXiv:2410.22967v5 Announce Type: replace Abstract: The widespread usage of the Internet of Things (IoT) has raised the risks of cyber threats; thus, developing Anomaly Detection Systems (ADSs) that c

Aggregation Buffer: Revisiting DropEdge with a New Parameter Block

arXiv:2505.20840v2 Announce Type: replace Abstract: We revisit DropEdge, a data augmentation technique for GNNs which randomly removes edges to expose diverse graph structures during training. While b

AMix-2: Establishing Protein as a Native Modality in Large Language Models

arXiv:2605.30963v1 Announce Type: cross Abstract: We present AMix-2, a protein-text foundation model that establishes protein as a native modality in large language models (LLMs), unifying protein und

AMNESIA: A Large Scale Medical Unlearning Benchmark Suite with Disease-Informed Analysis

arXiv:2605.30599v1 Announce Type: cross Abstract: Medical knowledge is continuously evolving. This creates a need to update or selectively forget information encoded in already-trained medical LLMs. M

An Odd Estimator for Shapley Values

arXiv:2602.01399v2 Announce Type: replace-cross Abstract: The Shapley value is a ubiquitous framework for attribution in machine learning, encompassing feature importance, data valuation, and causal i

Anchoring LLM Gender Bias to Human Baselines: A Cross-Lingual Audit

arXiv:2605.30804v1 Announce Type: new Abstract: We audit six large language models (LLMs) for gender stereotyping across English, Korean, Chinese, and Japanese. Three were developed primarily for Engl

Auditing LLM Benchmarks with Item Response Theory

arXiv:2605.30504v1 Announce Type: new Abstract: LLM benchmark labels are frozen at release and silently propagated into downstream benchmarks, errors and all. We introduce an Item Response Theory-base

Auto-Discovery-Bench: Diagnosing Structured State Tracking in Oracle-Guided Discovery

arXiv:2502.15224v2 Announce Type: replace-cross Abstract: Interactive discovery requires agents to maintain and update structured beliefs over many rounds of feedback. Before evaluating agents in nois

Automated Prediction of Postoperative Pancreatic Fistula Using Preoperative Computed Tomography

model-releasesarxiv-cs-cv

arXiv:2605.31539v1 Announce Type: new Abstract: Postoperative pancreatic fistula (POPF) is a serious complication after pancreatic resection, increasing morbidity, hospital stay, and healthcare costs.

Automating Formal Verification with Reinforcement Learning and Recursive Inference

arXiv:2605.30914v1 Announce Type: new Abstract: Automated formal verification remains challenging for large language models because data for proof assistants and verification-aware languages is scarce

Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence

arXiv:2605.31484v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) is the most widely adopted method for fine-tuning large language models. Notably, LoRA is inherently overparameterized: multi

Bandwidth Allocation with Device Partitioning for Federated Learning over Industrial IoT networks

arXiv:2605.30892v1 Announce Type: new Abstract: We consider a federated learning (FL) system in which Industrial Internet-of-Things (IIoT) devices collaboratively train a global model over wireless ch

been asking others at Anthropic how they stay in the loop with Claude and fully understand the work being done this is one of my favorites f…

I cannot provide an accurate summary as the title appears to be truncated and the full content is not accessible. Based on the available text, this likely discusses internal practices at Anthropic reg

model-releasesthariq--x

Benchmarking and Enhancing Text-to-Image Models for Generating Visual Representations in Early Arithmetic Education

arXiv:2605.31212v1 Announce Type: cross Abstract: AI systems are increasingly used to support educational content creation, yet it remains unclear whether they can generate outputs that faithfully rep

Benchmarking Uncertainty and its Disentanglement in multi-label Chest X-Ray Classification

arXiv:2508.04457v2 Announce Type: replace-cross Abstract: Reliable uncertainty quantification is crucial for trustworthy decision-making and the deployment of AI models in medical imaging. While prior

BenHalluEval: A Multi-Task Hallucination Evaluation Framework for Large Language Models on Bengali

arXiv:2605.31483v1 Announce Type: new Abstract: Despite Bengali being the sixth most spoken language in the world, no prior work has systematically evaluated hallucination in large language models (LL

Bernini released. Unified Video generation and editing model. Built on Wan-2.2

model-releasesr-stablediffusion

Bernini is a unified framework for video editing and video generation , built using Wan2.2-A14B as its renderer . The model covers complementary task families that demonstrate its capabilities as a un

Beyond Agreement: Scoring Panel-Surfaced Biomedical Entity Candidates for Curator Triage

arXiv:2605.30826v1 Announce Type: cross Abstract: Biomedical NER is deceptively simple for modern LLMs: plausible biomedical mentions are easy to surface, but corpus-convention correctness depends on

Beyond ReLU: Bifurcation, Oversmoothing, and Topological Priors

arXiv:2602.15634v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) learn node representations through iterative network-based message-passing. While powerful, deep GNNs suffer from overs

Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory

arXiv:2605.31086v1 Announce Type: new Abstract: In existing memory benchmarks for Large Language Models (LLMs), the evaluated dialogue sessions often lack long-term semantic consistency, and the under

Big day for American open models... Nemotron 3 Ultra is now the strongest US open-weight model tested, while apparently serving 300+ tok/s …

model-releasesharrison-chase--x

Big day for American open models... Nemotron 3 Ultra is now the strongest US open-weight model tested, while apparently serving 300+ tok/s 🤯 Comparable large DeepSeek/Kimi models are usually 50-100 to

BilliardPhys-Bench: Benchmarking Physical Reasoning and Visual Dynamics of Multimodal LLMs

arXiv:2605.30900v1 Announce Type: new Abstract: Current multimodal models handle static image recognition well, but intuitive physical reasoning remains a weakness. Predicting how objects will move an

Binance launches trading for 7,000+ US stocks and ETFs for non-US users, with zero commissions and fractional share purchases, as part of its 'super app' push (Jeff John Roberts/Fortune)

Jeff John Roberts / Fortune: Binance launches trading for 7,000+ US stocks and ETFs for non-US users, with zero commissions and fractional share purchases, as part of its “super app” push — Binance, t

model-releasestechmeme

BlueFin: Benchmarking LLM Agents on Financial Spreadsheets

arXiv:2605.30907v1 Announce Type: cross Abstract: We present BlueFin, a benchmark that tasks large language model (LLM) agents with synthesis, manipulation, and comprehension tasks over spreadsheet wo

BOKBO (Best of K Bad Options): Calibrated Abstention for VLA Policies

arXiv:2605.30660v1 Announce Type: new Abstract: Test-time scaling for vision-language-action (VLA) policies, methods such as RoboMonkey, SEAL, MG-Select, and V-GPS, samples K candidate action chunks a

Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies

arXiv:2512.19673v3 Announce Type: replace-cross Abstract: Existing reinforcement learning (RL) approaches treat large language models (LLMs) as a unified policy, overlooking their internal mechanisms.

Bounded Behavioral Indistinguishability for Black-Box LLM Distillation

arXiv:2605.30448v1 Announce Type: cross Abstract: Black-box LLM distillation is usually evaluated as an output-matching problem: a student is considered successful when its responses are semantically

Breaking the Simplification Bottleneck in Amortized Neural Symbolic Regression

arXiv:2602.08885v5 Announce Type: replace-cross Abstract: Symbolic regression (SR) aims to discover interpretable analytical expressions that accurately describe observed data. Amortized SR promises t

Building the infrastructure for the Intelligence Age in Michigan

OpenAI announced plans to build significant AI infrastructure in Michigan to support the growing computational demands of advanced AI systems. The project, referred to as Stargate, represents investme

model-releasesopenai

Calibrated Preference Learning: The Case of Label Ranking

arXiv:2605.30447v1 Announce Type: cross Abstract: Calibration, the alignment of predicted probabilities with true outcome frequencies, is essential for reliable decision-making. While extensively stud

Can LLM Teams Play What? Where? When?

arXiv:2605.30459v1 Announce Type: new Abstract: Large language models (LLMs) remain limited on tasks requiring indirect reasoning, cultural knowledge, and coordinated hypothesis testing. We investigat

Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks?

arXiv:2605.30470v1 Announce Type: new Abstract: Graph Machine Learning as a Service (GMLaaS) platforms increasingly implement explainability interfaces to meet regulatory transparency requirements. Ho

CanLegalRAGBench: Evaluating Retrieval-Augmented Generation on Canadian Case Law

arXiv:2605.30497v1 Announce Type: new Abstract: RAG-based legal assistants have been growing in popularity, but LLM hallucinations remain a key issue and potentially undermines justice. While benchmar

Caspar: CUDA Accelerator for Symbolic Programming with Adaptive Reordering

model-releasesarxiv-cs-ro

arXiv:2605.30583v1 Announce Type: new Abstract: We present Caspar, a library that makes the power of modern GPUs more accessible in robotics and provides a state-of-the-art nonlinear GPU solver that c

Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

arXiv:2503.08679v5 Announce Type: replace Abstract: Recent studies indicate that when faced with explicit biases in prompts, models often omit mentioning these biases in their Chain-of-Thought (CoT) o

Chinese AI developer MiniMax launches M3, a new coding model that it says rivals Opus 4.7, costing 0.12 per 1M input tokens, compared with 5 for Opus 4.7 (Juro Osawa/The Information)

Juro Osawa / The Information: Chinese AI developer MiniMax launches M3, a new coding model that it says rivals Opus 4.7, costing 0.12 per 1M input tokens, compared with 5 for Opus 4.7 — Chinese AI dev

model-releasestechmeme

CodeGolf Bench: A Multi-Language Benchmark for Evaluating Concise Code Generation Capabilities of Large Language Models

arXiv:2605.30394v1 Announce Type: cross Abstract: This paper introduces Code Bench, a benchmark capable of evaluating Large Language Models (LLMs) concise code generation abilities in 60 programming l

CoFiDA-M: Concept-Aware Feature Modulation for Cross-Domain Adaptation with Image-Only Inference

model-releasesarxiv-cs-cv

arXiv:2605.31591v1 Announce Type: new Abstract: Models for AI-based skin cancer screening suffer a severe performance drop when shifting from expert dermoscopic (source) images to consumer-grade clini

Coinbase launches direct Indian rupee deposit and withdrawal rails via the Immediate Payment Service, aiming to remove its reliance on P2P and intermediaries (Omkar Godbole/CoinDesk)

Omkar Godbole / CoinDesk: Coinbase launches direct Indian rupee deposit and withdrawal rails via the Immediate Payment Service, aiming to remove its reliance on P2P and intermediaries — Coinbase annou

model-releasestechmeme

Conditional Coverage Diagnostics for Conformal Prediction

arXiv:2512.11779v2 Announce Type: replace-cross Abstract: Evaluating conditional coverage remains one of the most persistent challenges in assessing the reliability of predictive systems. Although con

ConTrans: Learning Text-enhanced Local-global Temporal Representations for Zero-shot Temporal Action Localization

arXiv:2605.30689v1 Announce Type: cross Abstract: Zero-shot Temporal Action Localization (ZS-TAL) aims to detect and locate previously unseen actions in untrimmed videos. However, existing approaches

Convergence of Steepest Descent and Adam under Non-Uniform Smoothness

arXiv:2605.30648v1 Announce Type: new Abstract: Recent work has analyzed the convergence of first-order methods under non-uniform smoothness assumptions that better model the loss landscape in machine

Convergence of Two-Timescale Markovian Stochastic Approximations with Applications in Reinforcement Learning

arXiv:2605.31172v1 Announce Type: new Abstract: This work studies the convergence of two-timescale stochastic approximations (SA), a class of iterative algorithms that update two sets of parameters in

Count Anything

model-releasesarxiv-cs-cv

arXiv:2605.30846v1 Announce Type: new Abstract: Object counting remains fragmented across domain-specific datasets and task formulations, despite rapid progress in generalist vision models. Existing c

Counterfactual Trace Auditing of LLM Agent Skills

arXiv:2605.11946v2 Announce Type: replace Abstract: Large Language Model agents are increasingly augmented with agent skills. Current evaluation methods for skills remain limited. Most deployed benchm