Search: “model-releases”

RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wild

arXiv:2606.23344v1 Announce Type: new Abstract: Accurate document layout analysis remains a critical bottleneck for document parsing systems, due to the intricate coupling among heterogeneous document

rumors of new models being delayed

DGX agent

rumors of new models being delayed 🚨 SCOOP(s): - GPT-5.6 has been delayed and will no longer release this week. New target is ~mid-July. - DeepMind are not satisfied with the current state of 3.5 Pro

model-releasesgary-marcus--x

23 Jun 2026

SamatNext v0.2-B: An Exploratory Study of RMS-Normalized Hybrid Decoders for Curriculum Retention in Small Code Models

arXiv:2606.22248v1 Announce Type: new Abstract: Standard autoregressive Transformer decoders can often exhibit substantial forgetting under sequential fine-tuning on shifting curriculum distributions.

SATURN: Symbolic Spatial Reasoning for Multi-Perspective Grounding

arXiv:2606.22694v1 Announce Type: new Abstract: Vision-Language Models (VLMs) remain unreliable when spatial reasoning requires composing relations whose meanings depend on frames of reference. Existi

Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers

arXiv:2606.23607v1 Announce Type: new Abstract: Linear mode connectivity (LMC) provides a promising foundation for understanding and merging independently trained neural networks, but existing methods

ScanBot: A Benchmark for Precision Robotic Surface Scanning with Industrial Laser Profilers

model-releasesarxiv-cs-ro

arXiv:2505.17295v2 Announce Type: replace Abstract: We introduce ScanBot, a benchmark for instruction-conditioned, high-precision surface scanning with robot-mounted industrial laser profilers. Unlike

Scene-agnostic ALS boresight self-calibration

arXiv:2606.23101v1 Announce Type: new Abstract: ALS boresight calibration has relied for two decades on dedicated flight patterns over structured scenes containing planar surfaces of varied aspect and

SeFi-Image: A Text-to-Image Foundation Model with Semantic-First Diffusion

arXiv:2606.22568v1 Announce Type: new Abstract: Training image generation foundation models consumes substantial resources. Previous methods have attempted to leverage semantic guidance to accelerate

SegTME-UNI2: A Foundation Model-Based Framework for Generalisable Multiclass Cell Segmentation and LLM-Driven Tumour Microenvironment Characterisation in Histopathology

arXiv:2606.17702v2 Announce Type: replace Abstract: Characterising the tumour microenvironment (TME) from routine H&E-stained histology images requires simultaneous cell segmentation, feature extracti

Select-to-Act: Hierarchical Reinforcement Learning via Adaptive Language Guidance

arXiv:2606.22350v1 Announce Type: new Abstract: Reinforcement Learning (RL) has been widely applied to sequential decision-making, yet it often suffers from poor sample efficiency due to costly intera

Self-Evolution for Multi-Turn Tool-Calling Agents via Divergence-Point Preference Learning

arXiv:2606.23112v1 Announce Type: new Abstract: Multi-turn tool-using agents must coordinate long-horizon tool sequences while tracking dialogue state and policy constraints. Existing approaches often

Self-Improvement Can Self-Regress: The Rise-and-Collapse Failure Mode of LLM Self-Training

arXiv:2606.21090v1 Announce Type: cross Abstract: Self-improvement can self-regress. In REINFORCE post-training for code, a model can quickly improve on its optimized metric and then collapse within t

Sequential Minimal Optimization Algorithm for One-Class Support Vector Machines With Privileged Information

arXiv:2606.22210v1 Announce Type: new Abstract: One of the powerful techniques in data modeling is accounting for features that are available at the training stage, but are not available when the trai

Set-based v.s. Distribution-based Representations of Epistemic Uncertainty: A Comparative Study

arXiv:2602.22747v2 Announce Type: replace Abstract: Epistemic uncertainty in neural networks is commonly modeled using two second-order paradigms: distribution-based representations, which rely on pos

SFT Overtraining Predicts Rank Inversion via Entropy Collapse Under RLVR

arXiv:2606.18487v2 Announce Type: replace Abstract: The standard heuristic of selecting the SFT checkpoint with the highest pass@1 for GRPO can fail when SFT compresses the rollout distribution. For b

SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning

arXiv:2606.22873v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterprise applications. This broad deployment expands the

Skill Coverage: A Test Adequacy Metric for Agent Skills

arXiv:2606.20659v1 Announce Type: cross Abstract: Agent skills encode reusable procedural knowledge that guides large language model agents across tasks and execution contexts. Existing evaluations pr

Small LLMs: Pruning vs. Training from Scratch

arXiv:2606.14150v2 Announce Type: replace Abstract: Pruning promises a shortcut to strong small language models. In this work, we examine this promise by pruning Llama-3.1-8B at pruning ratios of 0.5-

Snyk launches Evo Agentic Development Security to police AI coding agents

model-releasessiliconangle

Cybersecurity company Snyk Ltd. today launched Evo Agentic Development Security, a new layer of its artificial intelligence security platform built to police the autonomous coding agents that increasi

SOHET: Sequence Of Heterogeneous Events Transformer with Self-Supervised Pre-Training

arXiv:2606.21356v1 Announce Type: new Abstract: Many machine learning applications rely on heterogeneous event streams to make predictions, either causally as events arrive or bidirectionally over com

SparseWorld: Enhancing End-to-End Autonomous Driving via World Models with Sparse Scene Representation

arXiv:2605.24354v2 Announce Type: replace Abstract: Recently, world models have made significant progress in enhancing end-to-end driving systems through both future situation forecasting and improved

Specialize Roles, Mix Deployments: Pushing the Cost-Accuracy Frontier of LLM Agent Teams

arXiv:2606.20629v1 Announce Type: cross Abstract: LLM agents are increasingly deployed as multi-role teams, where tasks are divided across specialized roles such as planner, executor, and verifier. In

Steer, Don't Solve: Training Small Critic Models for Large Code Agents

arXiv:2606.21811v1 Announce Type: cross Abstract: End-to-end code agent training is resource-intensive and plateaus on the strategy-level reasoning needed to resolve code issues, since jointly optimiz

Streaming Dense Voxel Representations for 3D Occupancy Prediction

arXiv:2503.22087v3 Announce Type: replace Abstract: In this paper, we explore dense voxel streaming for accurate and efficient 3D occupancy prediction. While dense voxel representations offer fine-gra

Strengthening LLMs for Tabular Prediction with Structural Priors

arXiv:2510.17385v5 Announce Type: replace Abstract: Tabular prediction has long been dominated by gradient-boosted decision trees and specialized deep tabular models, while large language models (LLMs

Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers

arXiv:2606.22383v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) has become a practical solution for adapting large pretrained vision transformers (ViTs) to downstream tasks whil

Sub-Billion, Super-Frontier: Small Language Models Rival Zero-Shot Frontier LLMs on General and Literary Relation Extraction

arXiv:2606.22606v1 Announce Type: cross Abstract: Large language models (LLMs) achieve strong relation extraction (RE), but their computational demands and reliance on proprietary APIs limit deploymen

Subject-Level Unknown-Identity Identification from Leap Motion Controller 2 Hand Landmarks

arXiv:2606.22986v1 Announce Type: new Abstract: This work studies subject recognition from Leap Motion Controller 2 (LMC2) hand landmark data under a subject-level unknown-identity identification prot

SVD-Surgeon: Optimal Singular-Value Surgery for Large Language Model Compression

arXiv:2606.23568v1 Announce Type: new Abstract: Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their deployment is constrained by substantial memory and

T-IMPACT: A Severity-Aware Benchmark for Contextual Image-Text Manipulation

arXiv:2606.22339v1 Announce Type: new Abstract: Recent advances in vision-language models and generative editing systems have made it increasingly easy to produce persuasive multimodal misinformation

Tag Claude in a channel, it spins up an instance with its own sandbox. It clones repos, writes code, tests, compiles all in that isolated en…

model-releasesboris-cherny--x

Tag Claude in a channel, it spins up an instance with its own sandbox. It clones repos, writes code, tests, compiles all in that isolated environment and the sandbox gets thrown away when it's done. O

TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wild

arXiv:2603.21478v2 Announce Type: replace-cross Abstract: Speech technologies have advanced rapidly and serve diverse populations worldwide. However, many languages remain underrepresented due to limi

Tapered Language Models

arXiv:2606.23670v1 Announce Type: new Abstract: Modern language models, including transformer, recurrent, and memory-based variants, share a common chassis: a stack of identical layers in which parame

Target-Aware Linear Regression Under Distribution Shift

arXiv:2606.22775v1 Announce Type: cross Abstract: Distribution shift between training and deployment is a pervasive challenge for modern AI systems. In many cases, the target marginals of covariates a

Task-Differentiated Atomic Skill Expansion and Routing for Continual Learning Across Highly Heterogeneous Tasks

arXiv:2606.21307v1 Announce Type: new Abstract: Continual learning (CL) is commonly studied under the assumption that sequential tasks are semantically related or structurally similar. However, in hig

Technical Report for the ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge: Pretraining-Diverse Ensemble of Foundation Vision Encoders for Robust Outdoor Scene Understanding

arXiv:2606.23113v1 Announce Type: new Abstract: This report presents our solution for the ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge, which requires parsing unstructured outdoor s

TeleStyle V2: Beyond Content-Preserving Style Transfer with Self-Distillation and Distribution-Matching-Distillation

arXiv:2606.20709v1 Announce Type: new Abstract: Given a content reference and a style reference, content-preserving style transfer requires the model to generate stylized outputs with content and styl

Temper-Then-Tilt: Principled Unlearning for Generative Models through Tempering and Classifier Guidance

arXiv:2602.10217v2 Announce Type: replace Abstract: We study machine unlearning in large generative models by framing the task as density ratio estimation to a target distribution rather than supervis

Temporal Causal Prior-Data Fitted Networks for Panel Data with Learned Reliability Signals

arXiv:2606.20889v1 Announce Type: new Abstract: Estimating causal effects in industrial time series requires handling temporal dynamics, time-varying treatments, and unobserved confounders. Existing c

Temporal Graph Pattern Machine

arXiv:2601.22454v3 Announce Type: replace Abstract: Temporal graph learning is pivotal for deciphering dynamic systems, where the core challenge lies in explicitly modeling the underlying evolving pat

Temporal-Spectral Alignment with Frequency Adaptation for Source-Free Time-Series Adaptation

arXiv:2606.23120v1 Announce Type: new Abstract: The goal of source-free domain adaptation (SFDA) for time-series data is to transfer knowledge from a pre-trained source model to an unlabeled target do

Temporally Aware Densification for Dynamic 3D Gaussian Splatting

arXiv:2606.23212v1 Announce Type: new Abstract: Despite modeling temporal motion, dynamic 3D Gaussian Splatting (3DGS) methods still inherit a static densification strategy that is ill-suited for dyna

Thalia: A Global, Multi-Modal Dataset for Volcanic Activity Monitoring

arXiv:2505.17782v4 Announce Type: replace Abstract: Monitoring volcanic activity is of paramount importance to safeguarding lives, infrastructure, and ecosystems. However, only a small fraction of kno

That's it. Point it at a channel, give it a task, and let it work. It's in beta on Slack today for Claude Enterprise and Team customers. Mor…

model-releasesboris-cherny--x

That's it. Point it at a channel, give it a task, and let it work. It's in beta on Slack today for Claude Enterprise and Team customers. More surfaces coming soon! Learn more: https://www.anthropic.co

The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs

arXiv:2606.22686v1 Announce Type: cross Abstract: Modern Large Language Models (LLMs) rely on extensive safety alignment, yet the mechanistic basis of refusal remains opaque. In this work, we investig

The MAMA-MIA Challenge: Advancing Generalizability and Fairness in Breast MRI Tumor Segmentation and Treatment Response Prediction

arXiv:2603.01250v3 Announce Type: replace Abstract: Breast cancer is the most frequently diagnosed malignancy among women worldwide and a leading cause of cancer-related mortality. Dynamic contrast-en

The Metanym Game: A Self-Contained, Self-Consistent LLM Peer-Community Benchmark for Structural Intelligence

arXiv:2606.21008v1 Announce Type: cross Abstract: The metanym game is a competitive word game for LLMs that measures structural intelligence against established cognitive-science constructs. No conten

The Power of Light: Improving Synthetic-to-Real Domain Adaptation through Physically-Based Indirect Illumination

arXiv:2606.22574v1 Announce Type: new Abstract: While synthetic data generation resolves the manual labeling bottleneck in computer vision, minimizing the syn-to-real domain gap requires optimizing re