Search: “model-releases”

Benchmarking Large Vision-Language Models on CFMME: A Comprehensive Chinese Financial Multimodal Evaluation Dataset

arXiv:2605.29462v1 Announce Type: cross Abstract: The emergence of Large Vision-Language Models (LVLMs) has substantially expanded model capabilities beyond text-only understanding, enabling unified i

Model Releases

Benchmarking LLM-Assisted Blue Teaming via Standardized Threat Hunting

DGX agent

arXiv:2509.23571v3 Announce Type: replace-cross Abstract: As cyber threats continue to grow in scale and sophistication, blue team defenders increasingly require advanced tools to proactively detect a

model-releasesarxiv-cs-ai

29 May 2026

Benchmarking Open-Source Safety Guard Models: A Comprehensive Evaluation

arXiv:2605.28830v1 Announce Type: cross Abstract: As Large Language Models (LLMs) are increasingly deployed in safety-critical applications, robust content moderation becomes essential. We present a c

Benchmarking Positional Encoding Strategies for Transformer-Based EEG Foundation Models

arXiv:2605.29754v1 Announce Type: new Abstract: Electroencephalography (EEG) is a widely used non-invasive technique for measuring brain activity in brain-computer interface (BCI) applications. Superv

Benchmarking Single-Factor Physical Video-to-Audio Generation

model-releasesarxiv-cs-cv

arXiv:2605.30339v1 Announce Type: new Abstract: Generative video-to-audio (V2A) models produce highly plausible soundtracks, but it remains unclear whether they capture the underlying physical process

BenchTrace: A Benchmark for Testing Reflection Ability and Controlled Evolution in LLM Agents

arXiv:2605.29225v1 Announce Type: new Abstract: Self-evolving agents improve over time by reflecting on past failures, but existing evaluation is limited in two ways: it measures only task scores, lea

Beyond English and Evasion: A Human-Annotated Multi-Domain Benchmark for High-Stakes LLM Safety Evaluation in Chinese

arXiv:2605.29667v1 Announce Type: new Abstract: When Large Language Models (LLMs) are deployed in Chinese-language settings, a troubling pattern emerges: safety systems that work well in English break

Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization

arXiv:2605.28969v1 Announce Type: cross Abstract: If an AI agent makes decisions on a person's behalf, those decisions must align with its user. We introduce representational accuracy to measure how f

BioRefusalAudit: Auditing Biosecurity Refusal Depth Using General and Domain-Fine-Tuned Sparse Autoencoders

arXiv:2605.30162v1 Announce Type: new Abstract: Biosecurity evaluations of language models typically ask whether models produce hazardous output. This paper asks a complementary question: when a model

Boston Children’s uses AI to unlock new diagnoses

Boston Children's Hospital has implemented AI technology to improve diagnostic accuracy and identify rare or complex medical conditions in pediatric patients that might otherwise go undiagnosed. The a

model-releasesopenai

BrahmicTokenizer-131K: An Indic-Capable Drop-In Replacement for o200k_base

arXiv:2605.29379v1 Announce Type: new Abstract: We present BrahmicTokenizer-131K, a 131,072-vocabulary byte-level BPE tokenizer that closes the Brahmic compression gap at the 131K-vocabulary class whi

Brain-IT-VQA: From Brain Signals to Answers

arXiv:2605.29588v1 Announce Type: cross Abstract: Decoding visual content from fMRI signals recorded while a person views images, and specifically answering questions about the seen images, is a long-

Bridging the Semantic Gap for Categorical Data Clustering via Large Language Models

arXiv:2601.01162v3 Announce Type: replace-cross Abstract: Qualitative data are widespread in domains such as healthcare, marketing, and bioinformatics, where clustering offers a fundamental tool for p

Building and Road Recognition in Dense Urban Informal Settlements: A Dataset and Benchmark

model-releasesarxiv-cs-cv

arXiv:2605.29856v1 Announce Type: new Abstract: As a widespread form of informal settlements, urban villages present significant challenges for sustainable urban development and governance. Precise ma

BullingerDB: A Dataset for Handwritten Text Recognition and Writer Retrieval

model-releasesarxiv-cs-cv

arXiv:2605.30235v1 Announce Type: new Abstract: We present BullingerDB, a large-scale benchmark dataset for historical document analysis based on the correspondence of Heinrich Bullinger (1504-1575).

CalArena: A Large-Scale Post-Hoc Calibration Benchmark

arXiv:2605.30188v1 Announce Type: cross Abstract: Reliable probability estimates are critical in many machine learning applications, yet modern classifiers are often poorly calibrated. Post-hoc calibr

Can AI Weather Models Predict Beyond Two Weeks? A Quantitative Benchmark and Analysis of Long Rollouts

arXiv:2605.30184v1 Announce Type: new Abstract: While AI weather models excel at short-to-medium range forecasts (up to 15 days), they frequently suffer from ill-defined 'instabilities' when rolled ou

Casual as an Anchor: Resolving Supervision Misalignment in Formality Transfer Dataset

arXiv:2605.29365v1 Announce Type: new Abstract: Formality transfer is commonly framed as a symmetric bidirectional task between informal and formal registers. We argue that this framing conceals a sup

Certified Causal Defense with Generalizable Robustness

arXiv:2408.15451v3 Announce Type: replace Abstract: While machine learning models have proven effective across various scenarios, it is widely acknowledged that many models are vulnerable to adversari

ChatGPT diagnosed 40 million people with a disease that was invented as a joke. Not a real disease. Not a misunderstood disease. A completel…

model-releasesgary-marcus--x

ChatGPT diagnosed 40 million people with a disease that was invented as a joke. Not a real disease. Not a misunderstood disease. A completely fictional condition with a fake name, fake papers, and fak

Chess-World-Model: A 10M-Game Benchmark for Exact State Tracking from Chess Move Sequences

arXiv:2605.30100v1 Announce Type: new Abstract: World models require state tracking, which is the ability to maintain a correct latent state across action sequences. Existing benchmarks are often synt

Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answering

arXiv:2605.29742v1 Announce Type: new Abstract: Deploying Large Language Models (LLMs) for regulatory compliance demands rigorous traceability via comprehensive citations across multi-tiered authority

CityGen: Structure-Guided City-Style Synthesis for Cross-City Autonomous Driving

arXiv:2605.29935v1 Announce Type: cross Abstract: Autonomous driving systems are commonly trained and evaluated within limited geographic regions, which hinders their scalability when deployed in new

Claude really can roleplay an economist. I love this little comment Claude made after some robustness checks on the paper it wrote: 'On a 1–…

model-releasesethan-mollick--x

Claude really can roleplay an economist. I love this little comment Claude made after some robustness checks on the paper it wrote: 'On a 1–10 identification scale, I'd now put the paper at about 4.5

Cloud CISO Perspectives: How to build an AI-ready security program for the public sector

model-releasesgoogle-cloud-ai

Welcome to the second Cloud CISO Perspectives for May 2026. Today, Usman Chaudhary, Field CISO, Google Public Sector, offers a guide for CISOs protecting government agencies and critical infrastructur

CLUBench: A Clustering Benchmark

arXiv:2605.29933v1 Announce Type: new Abstract: Clustering is a fundamental problem in data science with a long-standing research history, yielding numerous insightful algorithms. Despite this progres

CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization

arXiv:2510.14150v5 Announce Type: replace Abstract: We introduce CodeEvolve, an open-source framework that couples large language models with island-based evolutionary search for end-to-end algorithmi

Combating Data Laundering in LLM Training

arXiv:2604.01904v2 Announce Type: replace-cross Abstract: Data rights owners can detect unauthorized data use in large language model (LLM) training by querying with proprietary samples. Often, superi

Command A+ sets a new high for Cohere's machine translation capabilities. Opening a clear gap over open source peers Mistral Medium 3.5, Dee…

Command A+ sets a new high for Cohere's machine translation capabilities. Opening a clear gap over open source peers Mistral Medium 3.5, DeepSeek, & OpenAI's gpt-oss, as well as Claude Opus 4.6. A+ al

model-releasescohere--x

CommunityFact: A Dynamic, Multilingual, Multi-domain Benchmark for Misinformation Detection in the Wild

arXiv:2605.30241v1 Announce Type: new Abstract: Misinformation verification increasingly occurs in public, fast-moving, and multilingual online settings, where static benchmarks provide an incomplete

Comparative Evaluation of Machine Translation Systems on Images with Text

arXiv:2605.29476v1 Announce Type: new Abstract: This work presents a comparative evaluation of machine translation systems applied to images containing textual information, a task that lies at the int

COMPOSE: Composing Future Theorems from Citations and Formal Structure

arXiv:2605.30333v1 Announce Type: new Abstract: A plausible future mathematical claim must satisfy two constraints: it should follow the direction of prior work and respect the formal dependencies tha

Composing Non-Conjugate Factor Graphs with Closed-Form Variational Inference

arXiv:2605.29467v1 Announce Type: cross Abstract: Stacking probabilistic building blocks into deeper architectures typically breaks closed-form inference. We show that closed-form inference can be pre

ConMoE: Expert-Pool Consolidation via Prototype Reassignment for MoE Compression

arXiv:2605.29350v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models reduce per-token computation but still require storing and serving all experts, making deployment memory-intens

Connecting Independently Trained Modes via Layer-Wise Connectivity

arXiv:2505.02604v5 Announce Type: replace Abstract: Empirical studies have shown that continuous low-loss paths can be constructed between independently trained neural network models. This phenomenon,

Contrastive Representation Regularization for Vision-Language-Action Models

arXiv:2510.01711v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have shown strong capabilities in robot manipulation by leveraging rich representations from pre-trained V

Converted, Not Equivalent: Benchmarking Codebase Conversion via Observational Equivalence

arXiv:2605.29054v1 Announce Type: cross Abstract: Coding agents increasingly act as codebase-scale collaborators that can assist with codebase conversion, but this progress has exposed a critical weak

Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation

arXiv:2605.30000v1 Announce Type: new Abstract: Front-end web code has become a core product surface for every frontier LLM release, yet evaluating these interactive applications at development speed

CosmicFish-HRM: Adaptive Reasoning via Hierarchical Recurrent Mechanisms in Compact Language Models

arXiv:2605.28919v1 Announce Type: cross Abstract: Large language models have achieved strong reasoning capabilities, though often at the cost of massive parameter counts and expensive inference. In th

CriticalKV: Optimizing KV Cache Eviction from an Output Perturbation Perspective

arXiv:2502.03805v2 Announce Type: replace Abstract: Large language models have revolutionized natural language processing but face significant challenges of high storage and runtime costs, due to the

CrystalXRD-Bench: Benchmarking Vision-Language Models for XRD Peak Indexing Across Diverse Crystalline Materials

arXiv:2605.29446v1 Announce Type: new Abstract: Miller-index identification from powder XRD patterns requires capabilities untested by existing multimodal benchmarks: the model must read a narrow peak

Deep Adaptive Dimension Reduction for Bayesian Inference in Inverse Problems

arXiv:2605.29373v1 Announce Type: new Abstract: Solving high-dimensional PDE-governed inverse problems is often challenging due to complex non-Gaussian posterior distributions, expensive forward model

Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning

arXiv:2508.19202v3 Announce Type: replace Abstract: Scientific problem solving poses unique challenges for LLMs, requiring both deep domain knowledge and the ability to apply such knowledge through co

DenseSteer: Steering Small Language Models towards Dense Math Reasoning

arXiv:2605.29247v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate strong chain-of-thought (CoT) reasoning abilities, while smaller models (<= 3B parameters) significantly underp

Developer's guide to Gemini Enterprise and A2UI integration

model-releasesgoogle-cloud-ai

If you've built a chatbot, you know this conversation: User: 'Book a table for two tomorrow at 7pm.' Agent: 'Okay, for what day?' User: 'Tomorrow.' Agent: 'What time?' A date picker would have ended t

Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking

arXiv:2605.30107v1 Announce Type: new Abstract: Creating spoken dialogue datasets is methodologically challenging, and these challenges are amplified when the goal is to build multilingual, multi-para

Differentiable Belief-based Opponent Shaping

arXiv:2605.29042v1 Announce Type: new Abstract: Human coordination often relies on the ability to influence the beliefs of others through strategic action. In multi-agent reinforcement learning, oppon

DiffSpot: Can VLMs Spot Fine-Grained Visual Differences in Web Interfaces?

arXiv:2605.29615v1 Announce Type: cross Abstract: Vision-language models (VLMs) have made strong progress on high-level image-text alignment, yet their ability to perceive subtle visual differences re