model releases

Learning Motion Feasibility from Point Clouds in Cluttered Environments

arXiv:2606.26700v1 Announce Type: cross Abstract: Motion feasibility prediction plays a central role in robotics, particularly in task and motion planning and manipulation. A major bottleneck for this

Model Releases

Learning to Recover Task Experts from a Multi-Task Merged Model

DGX agent

arXiv:2606.26902v1 Announce Type: new Abstract: Multi-task model merging aims to consolidate several task-specific experts into a unified model, yet static merging consistently suffers from parameter

model-releasesarxiv-cs-ai

26 Jun 2026

Learning to Select Maximum Clique Algorithms: From Traditional Machine Learning to a Dual-Channel Hybrid Neural Architecture

arXiv:2508.08005v4 Announce Type: replace-cross Abstract: The Maximum Clique Problem (MCP) is an NP-hard problem with wide-ranging applications in fields such as bioinformatics, network science, and s

Letter: the US lifts its block on Mythos 5, allowing Anthropic to release it to more than 100 US institutions; sources: talks about Fable 5 are ongoing (Semafor)

Semafor: Letter: the US lifts its block on Mythos 5, allowing Anthropic to release it to more than 100 US institutions; sources: talks about Fable 5 are ongoing — THE SCOOP — The US government Friday

Life After Benchmark Saturation: A Case Study of CORE-Bench

arXiv:2606.26158v1 Announce Type: new Abstract: When a benchmark's accuracy saturates, it is often retired and replaced with a more challenging version. We show that this approach privileges accuracy

Limited Reference, Reliable Generation: A Two-Component Framework for Tabular Data Generation in Low-Data Regimes

arXiv:2509.09960v2 Announce Type: replace-cross Abstract: Synthetic tabular data generation is increasingly essential in machine learning, supporting downstream applications when real-world, high-qual

LiMoDE: Rethinking Lifelong Robot Manipulation from a Mixture-of-Dynamic-Experts Perspective

arXiv:2606.26183v1 Announce Type: cross Abstract: Building a generalist robot that can leverage prior knowledge for continuous task adaptation remains a significant challenge. Previous works alleviate

Liquid Fusion of Heterogeneous Representations Towards General Salient Object Detection

arXiv:2606.26849v1 Announce Type: new Abstract: General Salient Object Detection (SOD) aims to identify and segment visually interesting objects from uni-modality or multi-modality scenes, recently ad

LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing

arXiv:2606.26740v1 Announce Type: new Abstract: Streaming video editing has made rapid progress, yet practical deployment is still limited by two core issues: maintaining stable backgrounds and non-ed

LMs as Task-Specific Knowledge Bases: An Interpretability Analysis

model-releasesarxiv-cs-cl

arXiv:2606.27237v1 Announce Type: new Abstract: Language models (LMs) capture large amounts of factual knowledge applicable to a wide range of tasks, motivating the view of their parameters as a knowl

Look-Before-Move: Narrative-Grounded World Visual Attention in Dynamic 3D Story Worlds

arXiv:2606.26964v1 Announce Type: new Abstract: As embodied AI and world models increasingly operate in dynamic 3D environments, visual perception must move beyond passively interpreting given observa

Low Resource Multimodal Translation of Nepali Spoken Words into Emotion-Conditioned Sign Language Avatars

arXiv:2606.26107v1 Announce Type: cross Abstract: Sign language communication systems, that integrate emotional expression remain underexplored, particularly for low-resource languages. This pilot stu

Mask to Concept: Auto-Promptable SAM3 via Efficient Test-Time Concept Embedding Search for Few-Shot Annotation

arXiv:2606.26711v1 Announce Type: new Abstract: Transforming foundation segmentation models from human-prompted tools into auto-promptable annotators is critical for scalable medical data annotation.

Mean-Field PhiBE: Continuous-Time Mean-Field Reinforcement Learning from Discrete-Time Data

arXiv:2606.26498v1 Announce Type: cross Abstract: This paper addresses model-free continuous-time mean-field control in a setting where the population dynamics evolve continuously according to an unkn

Memory Depth, Not Memory Access: Selective Parametric Consolidation for Long-Running Language Agents

arXiv:2606.26806v1 Announce Type: new Abstract: Long-running language agents need more than memory access. Retrieval systems can fetch past facts at query time, but they do not decide which experience

MetaboNet-Bench: A Multi-modal Benchmark for Glucose Forecasting in Type 1 Diabetes

arXiv:2606.18640v2 Announce Type: replace Abstract: Glucose forecasting algorithms are an important aspect of glycemic control management in type 1 diabetes. So far, the research community has develop

MKG-RAG-Bench: Benchmarking Retrieval in Multimodal Knowledge Graph-Augmented Generation

arXiv:2606.26458v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) over knowledge graphs has emerged as a promising approach for grounding large language models, yet existing benchma

MLFFM-SegDiff: A Multi-Level Feature Fusion Diffusion Model for Skin Lesion Segmentation

arXiv:2606.26712v1 Announce Type: cross Abstract: Skin lesion segmentation is a key task in computer-aided dermatological diagnosis, where accuracy directly impacts downstream analysis and disease cla

> mythos is so good at cyber it can't be released also > mythos can't detect 20k fraudulent chinese accounts attacking it

model-releasesclem-delangue--x

This post discusses apparent contradictions in claims about Mythos' cybersecurity capabilities, suggesting tension between assertions that it excels at cyber defense versus reports that it failed to d

NavIsaacLab: Generating Realistic Crowd via Parallel Robot Learning for Benchmarking Human-aware Navigation

model-releasesarxiv-cs-ro

arXiv:2606.26265v1 Announce Type: new Abstract: Robot autonomous navigation that accounts for surrounding human activities is crucial for ensuring both safety and natural human-robot interaction in re

NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research

arXiv:2606.26671v1 Announce Type: new Abstract: Post-training alignment determines the reasoning and human preference following capabilities of large language models, yet most existing works withhold

Necessary but Not Sufficient: Temperature Control and Reproducibility in LLM-as-Judge Safety Evaluations

arXiv:2606.26185v1 Announce Type: new Abstract: LLM-as-judge ('grader') components are now standard in evaluation harnesses, including safety evaluations where a pass/fail verdict may gate downstream

Nemotron-TwoTower: Diffusion Language Modeling with Pretrained Autoregressive Context

model-releasesarxiv-cs-cl

arXiv:2606.26493v1 Announce Type: new Abstract: Diffusion language models offer a promising alternative to autoregressive models due to their potential for parallel and iterative generation. However,

New paper on giving LLM agents experience that improves the weights and stays readable at the same time. Agent-experience methods split into…

New paper on giving LLM agents experience that improves the weights and stays readable at the same time. Agent-experience methods split into two camps. Externalized natural-language rules stay interpr

model-releasesdair-ai--x

NuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language Models

arXiv:2606.27047v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong performance across a wide range of tasks, but ensuring their reliability in highly technical dom

OI-Bench: An Option Injection Benchmark for Evaluating LLM Susceptibility to Directive Interference

model-releasesarxiv-cs-cl

arXiv:2601.13300v2 Announce Type: replace Abstract: Benchmarking large language models (LLMs) is critical for understanding their capabilities, limitations, and robustness. In addition to interface ar

OpenAI hopes to make GPT-5.6 generally available in the coming weeks and says 'this kind of government access process' should not become the long-term default (Amrith Ramkumar/Wall Street Journal)

Amrith Ramkumar / Wall Street Journal: OpenAI hopes to make GPT-5.6 generally available in the coming weeks and says “this kind of government access process” should not become the long-term default —

OpenAI introduces GPT-5.6 to challenge Claude Mythos 5

model-releasessiliconangle

OpenAI Group PBC today introduced GPT-5.6, a new series of large language models that it says can outperform Claude Mythos 5 across certain coding tasks. The most advanced algorithm in the lineup is k

OpenAI releases three versions of GPT-5.6, called Sol, Terra, and Luna, as a limited preview to ~20 companies, with participants disclosed to the US government (Axios)

Axios: OpenAI releases three versions of GPT-5.6, called Sol, Terra, and Luna, as a limited preview to ~20 companies, with participants disclosed to the US government — OpenAI is rolling out GPT-5.6 F

OpenAI says GPT-5.6 Sol and Terra were capable of identifying vulnerabilities but were unable to execute autonomous, end-to-end attacks against hardened targets (OpenAI)

OpenAI: OpenAI says GPT-5.6 Sol and Terra were capable of identifying vulnerabilities but were unable to execute autonomous, end-to-end attacks against hardened targets — GPT-5.6 is a new family of th

OpenAI unveils GPT-5.6 amid US AI regulatory drama

model-releasesthe-verge-ai

Less than 24 hours after news broke that OpenAI would stagger its next model release at the request of the Trump administration, that model, GPT-5.6, is here. On Friday, the company unveiled the limit

OpenFinGym: A Verifiable Multi-Task Gym Environment for Evaluating Quant Agents

arXiv:2606.26350v1 Announce Type: new Abstract: Although large language model agents are increasingly applied to quantitative-finance workflows, their evaluation remains fragmented across isolated tas

OpenRCA 2.0: From Outcome Labels to Causal Process Supervision

arXiv:2606.27154v1 Announce Type: new Abstract: Root cause analysis (RCA) poses a holistic test of LLM agentic capabilities, such as long-context understanding, multi-step reasoning, and tool use. How

Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis

arXiv:2406.10090v3 Announce Type: replace Abstract: Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization. However, having

Parametric Generalized Adaptive Moment Features (PG-AMF) for Bearing Fault Diagnosis and Machine Health Monitoring

arXiv:2606.26317v1 Announce Type: cross Abstract: Accurate fault diagnosis of rolling element bearings in rotating machinery is considered essential for ensuring industrial safety and enabling predict

Parametric Open Source Games

arXiv:2606.27068v1 Announce Type: cross Abstract: Open-source game theory studies agents whose behavior may depend on one another's decision procedures, but most existing models use discrete or symbol

Patent Representation Learning via Self-supervision

arXiv:2511.10657v2 Announce Type: replace-cross Abstract: We study self-supervised patent representation learning with contrastive objectives. A standard baseline constructs positives by encoding the

Perception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image Detection

arXiv:2606.26552v1 Announce Type: cross Abstract: The rapid advancement of generative models presents a significant challenge to existing deepfake detection methods, particularly given the widespread

PersistentKV: Page-Aware Decode Scheduling for Long-Context LLM Serving on Commodity GPUs

arXiv:2606.26666v1 Announce Type: new Abstract: Autoregressive large language model (LLM) serving is increasingly limited by key-value (KV) cache movement rather than dense matrix multiplication. Mode

PhyEditBench: A Real-World Multi-Stage Benchmark for Physics-Aware Image Editing

arXiv:2606.26551v1 Announce Type: new Abstract: While instruction-based image editing, enabled by multi-modal generative models, has advanced significantly, existing benchmarks lack a comprehensive ev

PortraitGen: Exemplar-Driven GRPO with Dual-Reward Guidance for Photorealistic Portrait Generation

arXiv:2606.26930v1 Announce Type: new Abstract: Reinforcement Learning like Group Relative Policy Optimization (GRPO) has significantly advanced text-to-image post-training. However, current methods o

Post-Training Recipe, More Than Model Family, Shapes Multi-Agent LLM Conversational Behavior

arXiv:2606.20632v2 Announce Type: replace-cross Abstract: Multi-LLM systems use multiple language models to deliberate, judge each other's outputs, or coordinate as agents. Their value depends on the

ProvenAI: Provenance-Native Traces of Evidence in Generated Answers

arXiv:2606.26449v1 Announce Type: cross Abstract: Retrieval-augmented systems routinely present citations alongside generated answers, yet a citation does not confirm that the corresponding source mea

Quoting OpenAI

model-releasessimon-willison

We're beginning a limited preview of the GPT‑5.6 series: Sol, our flagship model; Terra, a balanced model for everyday work; and Luna, a fast and affordable model. Terra has competitive performance to

Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation

arXiv:2606.26907v1 Announce Type: new Abstract: While text-to-image (T2I) models have achieved remarkable progress, they struggle with real-world requests that are often underspecified, implicit, or d

R2D-RL: A RoboCup 2D Soccer Environment for Multi-Agent Reinforcement Learning

arXiv:2606.18786v2 Announce Type: replace Abstract: Robot soccer is a challenging testbed for multi-agent reinforcement learning because it combines partial observability, cooperative and adversarial

Real-Time Safety Evaluation of Human Arm Operations Using a Wrist-Mounted IMU with PSM System

model-releasesarxiv-cs-ro

arXiv:2502.09241v2 Announce Type: replace Abstract: This paper presents a novel approach to real-time safety monitoring in human-robot collaborative manufacturing environments through a wrist-mounted

ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP

arXiv:2606.26794v1 Announce Type: cross Abstract: CLIP and its variants are widely adopted visual backbones in multimodal systems, but their pretraining remains dominated by descriptive image-text ali