Search: “models”

Anthropic says red team tests of Fable 5 found no universal jailbreaks, and it will keep first- and third-party user traffic on Mythos-class models for 30 days (Derek B. Johnson/CyberScoop)

Derek B. Johnson / CyberScoop: Anthropic says red team tests of Fable 5 found no universal jailbreaks, and it will keep first- and third-party user traffic on Mythos-class models for 30 days — Claude

model-releasestechmeme

ATM: Action-Consistency Transfer Matrix for Diagnosing and Improving Latent World Models

arXiv:2606.09028v1 Announce Type: cross Abstract: Latent world models are increasingly used for control and goal-conditioned planning, yet assessing whether their learned representations are useful fo

Benchmarking Vision-Language-Action Models on SO-101: Failure and Recovery Analysis

arXiv:2606.08881v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated strong generalization in robotic manipulation, yet existing evaluations are primarily conducted

Breaking the Tokenizer Barrier: On-Policy Distillation across Model Families

arXiv:2606.09456v1 Announce Type: new Abstract: On-Policy Distillation (OPD) has become a core technique in the post-training of Large Language Models (LLMs) for transferring knowledge from domain exp

safetyarxiv-cs-lg

Bridging Traditional Explainability Methods and Multimodal Multilingual Models: An XAI-Based Analysis

arXiv:2606.07533v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) effectively integrate text and audio to interpret context in complex interactive dialogues. However, the inte

Coarse-to-Fine Hierarchical Alignment for UAV-based Human Detection using Diffusion Models

model-releasesarxiv-cs-cv

arXiv:2512.13869v3 Announce Type: replace Abstract: Training object detectors demands extensive, task-specific annotations, yet this requirement becomes impractical in UAV-based human detection due to

Decoding Pedestrian Crossing Intention from Egocentric Vision via Vision Language Models

arXiv:2606.09142v1 Announce Type: cross Abstract: Egocentric vision offers a first-person view of human perception and decision making, yet its potential for traffic-safety prediction remains underexp

Diverse Thinking Schemata Elicit Better Reasoning in Large Language Models

arXiv:2606.08974v1 Announce Type: new Abstract: Large reasoning models (LRMs) have attracted increasing attention for their ability to solve complex mathematical problems by generating extended reason

Do Video Foundation Models Understand Intuitive Physics? A Layerwise Probing Analysis

arXiv:2606.09646v1 Announce Type: cross Abstract: We study whether pretrained video foundation models encode intuitive-physics information in their frozen representations, and how this information var

DynaCF: Mitigating Shortcut Learning in Reward Models via Dynamic Counterfactual Sensitivity

arXiv:2606.09043v1 Announce Type: new Abstract: Reward models trained from pairwise preferences often exploit superficial shortcut cues rather than learning true response quality. We propose DynaCF, a

researcharxiv-cs-lg

Echo-Memory: A Controlled Study of Memory in Action World Models

arXiv:2606.09803v1 Announce Type: new Abstract: We present extbf{Echo-Memory}, a controlled study of memory mechanisms in action-conditioned world models. These models generate multi-segment videos fr

researcharxiv-cs-cv

Tutorials

Emergence of Context Characteristics Sensitivity in Large Language Models

arXiv:2606.09525v1 Announce Type: cross Abstract: During instruction fine-tuning (IFT), large language models (LLMs) learn to follow instructions by using the provided context to answer a query. While

tutorialsarxiv-cs-ai

Enhancing Spatial Reasoning in Large Language Models for Metal-Organic Frameworks Structure Prediction

model-releasesarxiv-cs-lg

arXiv:2601.09285v2 Announce Type: replace Abstract: Metal-organic frameworks (MOFs) are porous crystalline materials with broad applications such as carbon capture and drug delivery, yet accurately pr

Fable is a step-change in models, and I hope it changes how you work with Claude. More to come in a series of posts on how it’s reshaped our…

Fable is a step-change in models, and I hope it changes how you work with Claude. More to come in a series of posts on how it’s reshaped our work, but the TLDR: it’s time to be more ambitious. Claude

model-releasesthariq--x

Local Ai

Frame Adjustments Demo: Most people think AI filmmaking means finding the one perfect model. It doesn't. @heydoughogan breaks down why the b…

Frame Adjustments Demo: Most people think AI filmmaking means finding the one perfect model. It doesn't. @heydoughogan breaks down why the best workflows are mix-and-match. Different models for differ

local-aicomfyui--x

HACK++: Towards More Effective Head-Aware Key-Value Compression for Efficient Visual Autoregressive Modeling

arXiv:2606.08302v1 Announce Type: new Abstract: Visual Autoregressive (VAR) models adopt a next-scale prediction paradigm, offering high-quality generation with substantially fewer decoding steps. How

researcharxiv-cs-cv

Industry

HF has been an amazing partner since day one, so this was easy. As we’ve grown from a post-training shop into a full model lab, @huggingface…

HF has been an amazing partner since day one, so this was easy. As we’ve grown from a post-training shop into a full model lab, @huggingface is the obvious partner to scale the infra open models deman

industryclem-delangue--x

How Much Dense Attention is Necessary? Oracle-Guided Sparse Prefill for Full/GQA Layers in Hybrid Long-Context Models

arXiv:2606.07703v1 Announce Type: cross Abstract: Long-context prefill remains expensive because full/GQA layers still score the historical sequence, even in hybrid models with local, sparse, linear,

How Well Do Latent World Models Understand Partially Observable Safety Constraints?

arXiv:2510.06492v2 Announce Type: replace Abstract: Latent world models are a promising approach for learning state representations and dynamics directly from high-dimensional observations, enabling r

safetyarxiv-cs-ro

IDEQ -- Improving Diffusion Models for the Traveling Salesman Problem (TSP) by Leveraging the Structure of the Solution Space

arXiv:2412.13858v2 Announce Type: replace Abstract: We investigate diffusion models to solve the Traveling Salesman Problem. Building on the recent DIFUSCO and T2TCO approaches, we propose IDEQ. IDEQ

IMUG-Bench: Benchmarking Unified Multimodal Models on Interleaved Understanding and Generation

arXiv:2606.09169v1 Announce Type: new Abstract: In recent years, unified multimodal models (UMMs) have emerged to support both understanding and generation within a single framework. Mastering dynamic

Agents

Introducing Cohere's first open-source coding model: North Mini Code Small & efficient, designed for agentic performance and built for commu…

Cohere released North Mini Code, an open-source coding model designed to be small and efficient while optimizing for agentic performance and community use. The model represents Cohere's initial offeri

agentsclem-delangue--x

Knowledge-Inclusive Adaptive Physics-Informed Neural Network for Microbial Interaction Modelling

arXiv:2606.07686v1 Announce Type: cross Abstract: Physics-Informed Neural Network (PINN) is a way of including knowledge in the form of equations in Machine Learning methods. Beyond equations, knowled

LargeMonitor: Monitoring Online Task-Free Continual Learning via Large Pretrained Models

arXiv:2606.09430v1 Announce Type: cross Abstract: Online task-free continual learning (TFCL) requires intelligent agents to sequentially accumulate knowledge from an unbounded, non-stationary data str

Late-Layer Fusion is Enough: Dual-Path Vision Token Routing for Multimodal Large Language Models under Visual Saturation

arXiv:2606.09131v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) commonly inherit the deep, symmetric Transformer backbone designed for unimodal text modeling, and apply the sa

Model-Based Learning of Whittle indices

model-releasesarxiv-cs-lg

arXiv:2511.20397v2 Announce Type: replace Abstract: We present BLINQ, a new model-based algorithm that learns the Whittle indices of an indexable, communicating and unichain Markov Decision Process (M

Pretrained, Frozen, Still Leaking: Auditing Cross-Encoder Attribute Transfer in EEG Foundation Models

arXiv:2606.09189v1 Announce Type: cross Abstract: EEG foundation-model releases are usually audited one endpoint at a time: raw-reconstruction, membership inference, identity linkage, or DP-SGD on the

Prisma-World: Camera-Controllable Multi-Agent Video World Model

arXiv:2606.09507v1 Announce Type: new Abstract: Video world models have made rapid progress in generating controllable visual experiences, but most of them still simulate the world from a single obser

safetyarxiv-cs-cv

PROBE-Web: An Interactive System for Probing Evaluation Landscapes of Knowledge Graph Completion Models

arXiv:2606.08926v1 Announce Type: new Abstract: Knowledge graph completion (KGC) models are commonly evaluated using rank-based metrics such as MRR and Hits@K, despite different users often requiring

safetyarxiv-cs-lg

ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models

model-releasesarxiv-cs-ro

arXiv:2606.09740v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models demonstrate strong perfor-1 mance on language-conditioned robotic manipulation within their training dis-2 tribution

Setting a custom price for a model in AgentsView

model-releasessimon-willison

TIL: Setting a custom price for a model in AgentsView I've been really enjoying AgentsView by Wes McKinney as a tool for exploring my token usage across different coding agents running on my laptop. C

SlideCheck: Guiding Self-Supervised Pretraining of Pathology Foundation Models via Dataset Distributions

arXiv:2606.07590v1 Announce Type: cross Abstract: Pathology foundation models are pretrained on large streams of WSI-derived patches, while supervision during data construction is often slide-level, s

Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models

arXiv:2606.08451v1 Announce Type: cross Abstract: Safety-aligned large language models often exhibit sycophancy, which is the tendency to affirm users' opinions regardless of factual accuracy. Althoug

Targeting World Models to Compromise Robot Learning Pipelines

arXiv:2606.09499v1 Announce Type: cross Abstract: World models have recently seen a rapid growth in both their popularity and capability as more data efficient tools for generating robot training data

The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust

arXiv:2606.07822v1 Announce Type: cross Abstract: As language models improve and become increasingly deployed to solve a variety of tasks, trustworthiness becomes essential. Calibration is a good prox

Transition-Based Digital Twin Modelling for Alzheimer's Disease under Sparse Longitudinal Data

arXiv:2606.09671v1 Announce Type: cross Abstract: Alzheimer's disease (AD) progression is highly heterogeneous and is typically observed through sparse and irregular longitudinal data, posing challeng

Video Understanding by Design: How Datasets Shape Video Models

arXiv:2509.09151v2 Announce Type: replace-cross Abstract: Research in video understanding has advanced rapidly, driven by increasingly diverse datasets and more powerful model architectures. While exi

AdaJudge: Adaptive Multi-Perspective Judging for Reward Modeling

arXiv:2601.08097v2 Announce Type: replace Abstract: Reward modeling is essential for aligning large language models with human preferences, yet predominant architectures rely on a static pooling strat

safetyarxiv-cs-cl

Agentic World Modeling for 6G: Near-Real-Time Generative State-Space Reasoning

arXiv:2511.02748v2 Announce Type: replace-cross Abstract: We argue that sixth-generation (6G) intelligence is not fluent token prediction but the capacity to imagine and choose -- to simulate future s

safetyarxiv-cs-lg

Benchmarking Language Modeling for Lossless Compression of Full-Fidelity Audio

arXiv:2603.08683v2 Announce Type: replace-cross Abstract: Autoregressive 'language' models (LMs) trained on raw waveforms can be repurposed for lossless audio compression, but prior work is limited to

CountsDiff: A Diffusion Model on the Natural Numbers for Generation and Imputation of Count-Based Data

arXiv:2604.03779v2 Announce Type: replace-cross Abstract: Diffusion models have excelled at generative tasks for both continuous and token-based domains, but their application to discrete ordinal data

Agents

I really do think we'll see a lot of value accrue in AI startups building 'model routing as a service' Not just OpenRouter - this includes a…

I really do think we'll see a lot of value accrue in AI startups building 'model routing as a service' Not just OpenRouter - this includes a much broader set of verticalized agents and infrastructure.

agentsjerry-liu--x

Inheritance Between Feedforward and Convolutional Networks via Model Projection

model-releasesarxiv-cs-lg

arXiv:2602.06245v2 Announce Type: replace-cross Abstract: Neural-network techniques are often transferred across architecture families by analogy, but such transfer is valid only when the assumptions

Interesting model here 35b a3b trained for agentic use It gets 60.7 on Terminal Bench2 qwen 3.6 27b gets 59.3 Essentially the same Going to …

model-releasesclem-delangue--x

Interesting model here 35b a3b trained for agentic use It gets 60.7 on Terminal Bench2 qwen 3.6 27b gets 59.3 Essentially the same Going to have to try it out https://huggingface.co/nex-agi/Nex-N2-min

LARA: Latent Action Representation Alignment for Vision-Language-Action Models

arXiv:2606.07100v1 Announce Type: new Abstract: Visual-language action (VLA) models enable robots to predict actions directly from observations and language instructions, but their performance depends

safetyarxiv-cs-cv

Latent-space Attacks for Refusal Evasion in Language Models

arXiv:2605.21706v2 Announce Type: replace Abstract: Safety-aligned language models are trained to refuse harmful requests, yet refusal behavior can be suppressed by steering their internal representat

Industry

Model routing is growing a lot these days

Model routing is growing a lot these days Good take My guess is - demand for intelligence is near infinite - but 80% of workloads will be running on 99% cheaper models within 12-18 months - 20% of wor

industryclem-delangue--x

Seeing a number of benchmarks showing Opus is the best model for long-running work. Five tips for running Opus autonomously for hours/days: …

model-releasesboris-cherny--x

Seeing a number of benchmarks showing Opus is the best model for long-running work. Five tips for running Opus autonomously for hours/days: 1. Use auto mode for permissions, so Claude doesn’t ask for