model releases

mdok-style at SemEval-2026 Task 9: Finetuning LLMs for Multilingual Polarization Detection

arXiv:2605.02695v1 Announce Type: new Abstract: SemEval-2026 Task 9 is focused on multilingual polarization detection. Specifically, it covers the identification of multilingual, multicultural and mul

Model Releases

Mean-Field Path-Integral Diffusion: From Samples to Interacting Agents

DGX agent

arXiv:2605.00007v1 Announce Type: cross Abstract: Independent sample generation is the prevailing paradigm in modern diffusion-based generative models of AI. We ask a different question: can samples c

model-releasesarxiv-cs-ai

5 May 2026

Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks

arXiv:2605.01417v1 Announce Type: new Abstract: Evaluating large language models (LLMs) for medical applications remains challenging due to benchmark saturation, limited data accessibility, and insuff

MedMosaic: A Challenging Large Scale Benchmark of Diverse Medical Audio

arXiv:2605.00969v1 Announce Type: cross Abstract: We present MedMosaic, a medical audio question-answering dataset designed to benchmark language and audio reasoning models under realistic clinical co

Meta-learning Structure-Preserving Dynamics

arXiv:2508.11205v2 Announce Type: replace Abstract: Structure-preserving approaches to dynamics discovery have demonstrated great potential for modeling physical systems due to their use of strong ind

Metric Unreliability in Multimodal Machine Unlearning: A Systematic Analysis and Principled Unified Score

arXiv:2605.02206v1 Announce Type: new Abstract: Machine unlearning in Vision-Language Models (VLMs) is required for compliance with the General Data Protection Regulation (GDPR), yet current evaluatio

Mextsuperscript{4}Fuse: Lightweight State-Space MoE with a Cross-Scale Gating Bridge for Brain Tumor Segmentation

arXiv:2605.02444v1 Announce Type: new Abstract: Encoder-decoder imbalance and the reliance on large input volumes make many 3D brain tumor segmentation models both compute-heavy and brittle. We presen

Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models

model-releasesarxiv-cs-ai

arXiv:2605.00123v1 Announce Type: new Abstract: Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts. Because we lack a robust understa

Minimum Specification Perturbation: Robustness as Distance-to-Falsification in Causal Inference

arXiv:2605.01579v1 Announce Type: cross Abstract: Empirical causal claims depend on many analyst decisions, from selecting covariates to choosing estimators. Existing robustness tools summarize how re

Model-Dowser: Data-Free Importance Probing to Mitigate Catastrophic Forgetting in Multimodal Large Language Models

arXiv:2602.04509v4 Announce Type: replace Abstract: Fine-tuning Multimodal Large Language Models (MLLMs) on task-specific data is an effective way to improve performance on downstream applications. Ho

Model Merging: Foundations and Algorithms

arXiv:2605.01580v1 Announce Type: new Abstract: Modern deep learning usually treats models as separate artifacts: trained independently, specialized for particular purposes, and replaced when improved

MOGO: Residual Quantized Hierarchical Causal Transformer for High-Quality and Real-Time 3D Human Motion Generation

arXiv:2506.05952v4 Announce Type: replace Abstract: Recent advances in transformer-based text-to-motion generation have led to impressive progress in synthesizing high-quality human motion. Neverthele

Molecular Representations for Large Language Models

arXiv:2605.01822v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly being used to support scientific discovery. In chemistry, tasks such as reaction prediction and structure

MolmoAct2: Action Reasoning Models for Real-world Deployment

model-releasesarxiv-cs-ro

arXiv:2605.02881v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models aim to provide a single generalist controller for robots, but today's systems fall short on the criteria that matter

MolViBench: Evaluating LLMs on Molecular Vibe Coding

arXiv:2605.02351v1 Announce Type: new Abstract: Molecular Vibe Coding, a paradigm where chemists interact with LLMs to generate executable programs for molecular tasks, has emerged as a flexible alter

MorphIt: Flexible Spherical Approximation of Robot Morphology for Representation-driven Adaptation

model-releasesarxiv-cs-ro

arXiv:2507.14061v2 Announce Type: replace Abstract: What if a robot could rethink its own morphological representation to better meet the demands of diverse tasks? Most robotic systems today treat the

MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding

arXiv:2510.08804v3 Announce Type: replace Abstract: We present MOSAIC, a multi-agent Large Language Model (LLM) framework for solving challenging scientific coding tasks. Unlike general-purpose coding

MPCS: Neuroplastic Continual Learning via Multi-Component Plasticity and Topology-Aware EWC

arXiv:2605.02509v1 Announce Type: new Abstract: Continual learning systems face a fundamental tension between plasticity -- acquiring new knowledge -- and stability -- retaining prior knowledge. We in

Multi-fidelity surrogates for mechanics of composites: from co-kriging to multi-fidelity neural networks

arXiv:2605.02871v1 Announce Type: cross Abstract: Composite materials exhibit strongly hierarchical and anisotropic properties governed by coupled mechanisms spanning constituents, plies, laminates, s

Multi-Perspective Transformers in ARC-AGI-2 Challenge

arXiv:2605.01154v1 Announce Type: new Abstract: ARC-AGI-2 is a benchmark of human-intuitive visual puzzles that measures a machine's ability to generalize from limited examples, interpret symbolic mea

MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety

arXiv:2605.01687v1 Announce Type: new Abstract: We present MultiBreak, a scalable and diverse multi-turn jailbreak benchmark to evaluate large language model (LLM) safety. Multi-turn jailbreaks mimic

Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident, Especially When They are Wrong

arXiv:2501.09775v3 Announce Type: replace Abstract: Multiple Choice Question (MCQ) tests are among the most used methods for evaluating large language models (LLMs). Besides checking the correctness o

NAKUL-Med: Spectral-Graph State Space Models with Dynamics Kernels for Medical Signals

arXiv:2605.00871v1 Announce Type: cross Abstract: State space models (SSMs) achieve linear-time complexity but struggle with multi-channel physiological signals due to three limitations: fixed kernels

Neighbor2Inverse: Self-Supervised Denoising for Low-Dose Region-of-Interest Phase Contrast CT

arXiv:2605.01075v1 Announce Type: new Abstract: Propagation-based X-ray phase-contrast imaging (PBI) enables high-contrast visualization of lung structures and holds strong medical potential. However,

New ways to buy ChatGPT ads

OpenAI introduced new advertising purchasing options for ChatGPT, expanding how businesses can buy ad placements within the platform. These new methods likely provide advertisers with additional flexi

model-releasesopenai

Object-Level Explanations for Image Geolocation Models: a GeoGuessr use-case

arXiv:2605.00912v1 Announce Type: new Abstract: When humans play geolocation games such as GeoGuessr, they rely on concrete visual cues, such as road markings, vegetation, or architectural details, to

OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models

arXiv:2605.00877v1 Announce Type: cross Abstract: The vast and underexplored ocean plays a critical role in regulating global climate and supporting marine biodiversity, yet artificial intelligence ha

oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning

arXiv:2510.07731v3 Announce Type: replace-cross Abstract: Organic reaction mechanisms are the stepwise elementary reactions by which reactants form intermediates and products, and are fundamental to u

Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection

arXiv:2605.01638v1 Announce Type: new Abstract: Multimodal deepfakes are proliferating on social media and threaten authenticity, information integrity, and digital forensics. Existing benchmarks are

OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedback

arXiv:2511.00510v2 Announce Type: replace Abstract: To address panoramic distortion, large search space, and identity ambiguity under a 360{eg} FoV, OmniTrack++ adopts a feedback-driven framework that

On Stable Long-Form Generation: Benchmarking and Mitigating Length Volatility

arXiv:2605.01357v1 Announce Type: new Abstract: Large Language Models (LLMs) excel at long-context understanding but exhibit significant limitations in long-form generation. Existing studies primarily

On the Effectiveness of Integration Methods for Multimodal Dialogue Response Retrieval

arXiv:2506.11499v2 Announce Type: replace Abstract: Multimodal chatbots have become one of the major topics for dialogue systems in both research community and industry. Recently, researchers have she

On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization

arXiv:2605.02141v1 Announce Type: new Abstract: Kullback-Leibler (KL) regularization is widely used in offline decision-making and offers several benefits, motivating recent work on the sample complex

Open models should compete on cost and specialization, not frontier benchmarks @natolambert puts it well: the right benchmark is savings in …

model-releasesharrison-chase--x

Open models should compete on cost and specialization, not frontier benchmarks @natolambert puts it well: the right benchmark is savings in compute and time, especially for repetitive agent tasks deep

OpenAI claims ChatGPT’s new default model hallucinates way less

model-releasesthe-verge-ai

OpenAI's newest default model for ChatGPT might not make stuff up as much. Hallucinations have been an ongoing problem for AI models, but OpenAI says its new GPT-5.5 Instant model has 'significant imp

OpenAI GPT-5 System Card

arXiv:2601.03267v2 Announce Type: replace Abstract: This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers

OphMAE: Bridging Volumetric and Planar Imaging with a Foundation Model for Adaptive Ophthalmological Diagnosis

arXiv:2605.02714v1 Announce Type: new Abstract: The advent of foundation models has heralded a new era in medical artificial intelligence (AI), enabling the extraction of generalizable representations

OralMLLM-Bench: Evaluating Cognitive Capabilities of Multimodal Large Language Models in Dental Practice

arXiv:2605.01333v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have emerged as a promising paradigm for dental image analysis. However, their ability to capture the multi-lev

Orchestrating Spatial Semantics via a Zone-Graph Paradigm for Intricate Indoor Scene Generation

model-releasesarxiv-cs-ro

arXiv:2605.02537v1 Announce Type: new Abstract: Autonomous 3D indoor scene synthesis breaks down in non-convex rooms with tightly coupled spatial constraints. Data-driven generators lack topological p

Orthographic Constraint Satisfaction and Human Difficulty Alignment in Large Language Models

arXiv:2511.21086v2 Announce Type: replace Abstract: Large language models must satisfy hard orthographic constraints during controlled text generation, yet systematic cross-family evaluation remains l

PACE: Parameter Change for Unsupervised Environment Design

arXiv:2605.01358v1 Announce Type: new Abstract: Unsupervised Environment Design (UED) offers a promising paradigm for improving reinforcement learning generalization by adaptively shaping training env

Pair2Score: Pairwise-to-Absolute Transfer for LLM-Based Essay Scoring

arXiv:2605.02069v1 Announce Type: new Abstract: Many scoring applications require absolute predictions, while pairwise comparisons can provide a simpler learning objective. We present Pair2Score, a tw

Pandora's Regret: A Proper Scoring Rule for Evaluating Sequential Search

arXiv:2605.01936v1 Announce Type: new Abstract: In sequential search, alternatives are tested until the true class is found. Standard proper scoring rules like log loss are local, ignoring the ranking

Parameter Space Analysis through Guided Visual Interpolations

arXiv:2509.19202v2 Announce Type: replace-cross Abstract: We propose Parameter Space Analysis through Guided Visual Interpolations (ParamInter), a novel tool for high-dimensional input parameter space

PC-MNet: Dual-Level Congruity Modeling for Multimodal Sarcasm Detection via Polarity-Modulated Attention

arXiv:2605.02447v1 Announce Type: new Abstract: Multimodal sarcasm detection, which aims to precisely identify pragmatic incongruities between literal text and nonverbal cues, has gained substantial a

PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction

arXiv:2605.01945v1 Announce Type: new Abstract: Tandem mass spectrometry provides a high-throughput framework for identifying and quantifying proteins in complex biological samples. In computational p

Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates

arXiv:2605.02236v1 Announce Type: cross Abstract: Recursive language-model loops often settle into recognizable attractor-like patterns. The practical question is how much injected text is needed to m

PhaseNet++: Phase-Aware Frequency-Domain Anomaly Detection for Industrial Control Systems via Phase Coherence Graphs

arXiv:2605.00929v1 Announce Type: new Abstract: Multivariate time series anomaly detection in ICS has attracted growing attention due to the increasing threat of cyber-physical attacks on critical inf