Search: “models”

Structured Neural Marked Point Processes for Interpretable Event Interaction Modeling

model-releasesarxiv-cs-lg

arXiv:2605.17568v1 Announce Type: new Abstract: Multi-class event streams arise in numerous real-world applications, where uncovering structured, interpretable inter-event relationships, together with

Hardware

Systematic Optimization of Real-Time Diffusion Model Inference on Apple M3 Ultra

DGX agent

arXiv:2605.16259v1 Announce Type: cross Abstract: While real-time image generation using diffusion models has advanced rapidly on NVIDIA GPUs, systematic optimization research on non-CUDA platforms su

hardwarearxiv-cs-ai

19 May 2026

TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models

arXiv:2605.17577v1 Announce Type: new Abstract: Large-scale pre-trained Vision-Language models (VLMs), such as CLIP, exhibit strong zero-shot generalization, yet remain highly vulnerable to impercepti

The last six months in LLMs in five minutes

model-releasessimon-willison

I put together these annotated slides from my five minute lightning talk at PyCon US 2026, using the latest iteration of my annotated presentation tool. # I presented this lightning talk at PyCon US 2

Unleashing the Potential of Diffusion Models for End-to-End Autonomous Driving

arXiv:2602.22801v2 Announce Type: replace-cross Abstract: Diffusion models have become a popular choice for decision-making tasks in robotics, and more recently, are also being considered for solving

safetyarxiv-cs-ai

Unlocking the Potential of Diffusion Language Models through Template Infilling

arXiv:2510.13870v3 Announce Type: replace-cross Abstract: Diffusion Language Models (DLMs) have emerged as a promising alternative to Autoregressive Language Models, yet their inference strategies rem

researcharxiv-cs-ai

Local Ai

Use your LM Studio models to code locally in @zeddotdev 🚀

Use your LM Studio models to code locally in @zeddotdev 🚀 Local model usage grew 3x in Zed's agent in the last 10 weeks. Cameron Mcloughlin on why he prefers local: 'I worry about over-reliance on pro

local-ailm-studio--x

We were able to sit down with the @GoogleDeepmind team behind the new Gemini Omni Flash model to hear all of their behind-the-scenes stories…

model-releasesgoogle-ai--x

We were able to sit down with the @GoogleDeepmind team behind the new Gemini Omni Flash model to hear all of their behind-the-scenes stories, memorable moments, and many, many (occasionally embarrassi

WOW-Seg: A Word-free Open World Segmentation Model

arXiv:2605.16903v1 Announce Type: new Abstract: Open world image segmentation aims to achieve precise segmentation and semantic understanding of targets within images by addressing the infinitely open

Beyond the Query: 5 Scenarios Laying the Foundation for the Agentic Era

model-releasesgoogle-cloud-ai

Accessing enterprise data is shifting from static reports to dynamic use by autonomous systems. To keep up, organizations must route fragmented data from SaaS, IoT, and legacy sources into secure, sca

Deterministic Event-Graph Substrates as World Models for Counterfactual Reasoning

arXiv:2605.15967v1 Announce Type: new Abstract: We study event-graph substrates: a class of world models that represent agent state as an append-only log of typed RDF triples and answer counterfactual

Tutorials

DiscussLLM: Teaching Large Language Models When to Speak

arXiv:2508.18167v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and generating human-like text, yet they largely operate as

tutorialsarxiv-cs-cl

Dynamic Chunking for Diffusion Language Models

model-releasesarxiv-cs-cl

arXiv:2605.15676v1 Announce Type: new Abstract: Block discrete diffusion language models factorize a sequence autoregressively over fixed-size positional blocks, decoupling within-block parallel denoi

Dynamics-Level Watermarking of Flow Matching Models with Random Codes

arXiv:2605.16239v1 Announce Type: new Abstract: We introduce a dynamics-level approach to watermarking generative models. Rather than embedding signals into model weights or outputs, we embed the wate

researcharxiv-cs-lg

Enabling Adversarial Robustness in AI Models through Kubeflow MLOps

arXiv:2605.15249v1 Announce Type: cross Abstract: AI models are increasingly deployed in cloud-native environments to support scalable and automated services. However, while platforms such as Kubernet

researcharxiv-cs-lg

Large Language Models as Optimization Controllers: Adaptive Continuation for SIMP Topology Optimization

arXiv:2603.25099v2 Announce Type: replace-cross Abstract: We present a framework in which a large language model (LLM) acts as an online adaptive controller for SIMP topology optimization, replacing c

llama.cpp with MTP support makes local models fast enough to use as daily drivers 🚀 Qwen3.6-27B dense generation (on A10G): From 25 tok/s →…

model-releasesclem-delangue--x

llama.cpp with MTP support makes local models fast enough to use as daily drivers 🚀 Qwen3.6-27B dense generation (on A10G): From 25 tok/s → 45 tok/s (+78%). Two flags on llama-server: --spec-type draf

Measuring Maximum Activations in Open Large Language Models

model-releasesarxiv-cs-cl

arXiv:2605.15572v1 Announce Type: new Abstract: The dynamic range of activations is a first-order constraint for low-bit quantization, activation scaling, and stable LLM inference. Prior work characte

Local Ai

MIND: Decoupling Model-Induced Label Noise via Latent Manifold Disentanglement

arXiv:2605.16081v1 Announce Type: cross Abstract: The paradigm of learning from automatic annotations driven by pre-trained experts and Foundation Models dominates data-hungry applications. However, i

local-aiarxiv-cs-cv

Offline Reinforcement Learning with Universal Horizon Models

arXiv:2605.15603v1 Announce Type: cross Abstract: Model-based reinforcement learning (RL) offers a compelling approach to offline RL by enabling value learning on imagined on-policy trajectories. Howe

safetyarxiv-cs-ai

One thing to watch for with Claude & GPT is that the models expose too much irrelevant history in their outputs. Slides are given footers sa…

model-releasesethan-mollick--x

One thing to watch for with Claude & GPT is that the models expose too much irrelevant history in their outputs. Slides are given footers saying things like 'Better, more targeted version' if you aske

Overfitting has a limitation: a model-independent generalization gap bound based on Renyi entropy

arXiv:2506.00182v3 Announce Type: replace-cross Abstract: Will further scaling up of machine learning models continue to bring success? A significant challenge in answering this question lies in under

researcharxiv-cs-lg

RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning

model-releasesarxiv-cs-cl

arXiv:2512.04457v2 Announce Type: replace Abstract: Removing specific data influence from large language models (LLMs) remains challenging, as retraining is costly and existing approximate unlearning

ReactiveGWM: Steering NPC in Reactive Game World Models

arXiv:2605.15256v1 Announce Type: new Abstract: Current game world models simulate environments from a subjective, player-centric perspective. However, by treating the Non-Player Character (NPC) merel

Reasoning Models Don't Just Think Longer, They Move Differently

arXiv:2605.15454v1 Announce Type: new Abstract: Reasoning-trained language models often spend more tokens on harder problems, but longer chains of thought do not show whether a model is merely computi

researcharxiv-cs-cl

Local Ai

Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers

arXiv:2505.12601v2 Announce Type: replace Abstract: As large language models (LLMs) grow in scale and specialization, routing--selecting the best model for a given input--has become essential for effi

local-aiarxiv-cs-lg

Reversing the Flow: Generation-to-Understanding Synergy in Large Multimodal Models

arXiv:2605.15792v1 Announce Type: new Abstract: The long-standing goal of multimodal AI is to build unified models in which visual understanding and visual generation mutually enhance one another. Des

Syntax Without Semantics: Teaching Large Language Models to Code in an Unseen Language

arXiv:2605.15607v1 Announce Type: new Abstract: Large language models (LLMs) achieve high pass rates on code generation benchmarks, yet whether they can transfer this ability to languages absent from

researcharxiv-cs-cl

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression

model-releasesarxiv-cs-lg

arXiv:2602.08324v3 Announce Type: replace Abstract: Chain-of-Thought (CoT) reasoning successfully enhances the reasoning capabilities of Large Language Models (LLMs), yet it incurs substantial computa

We causally trained a lot of SOTA search models internally, shall we make some small release from time to time 🤣🤣

model-releasesclem-delangue--x

We causally trained a lot of SOTA search models internally, shall we make some small release from time to time 🤣🤣 @bo_wangbo stealth releasing probably the strongest open multilingual ColBERT (and it'

'We give you model choice, without infrastructure chaos' — @MichaelDell, live from #DellTechWorld 🎤 Kimi K2.6, DeepSeek V4 Pro, GLM 5.1, Mi…

model-releasesclem-delangue--x

'We give you model choice, without infrastructure chaos' — @MichaelDell, live from #DellTechWorld 🎤 Kimi K2.6, DeepSeek V4 Pro, GLM 5.1, MiniMax M2.7 & DeepSeek V4 Flash are now one click away on Dell

Industry

yeah that's pretty good xAI might be able to cook with Cursor data + 10T model

yeah that's pretty good xAI might be able to cook with Cursor data + 10T model Introducing Composer 2.5, our most powerful model yet. It's more intelligent, better at sustained work on long-running ta

industryelon-musk--x

Action-Inspired Generative Models

arXiv:2605.14631v1 Announce Type: cross Abstract: We introduce Action-Inspired Generative Models (AGMs), a dual-network generative framework motivated by the observation that existing bridge-matching

Critic-Driven Voronoi-Quantization for Distilling Deep RL Policies to Explainable Models

arXiv:2605.14897v1 Announce Type: cross Abstract: Despite many successful attempts at explaining Deep Reinforcement Learning policies using distillation, it remains difficult to balance the performanc

EponaV2: Driving World Model with Comprehensive Future Reasoning

arXiv:2605.14696v1 Announce Type: new Abstract: Data scaling plays a pivotal role in the pursuit of general intelligence. However, the prevailing perception-planning paradigm in autonomous driving rel

Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model

arXiv:2605.14950v1 Announce Type: new Abstract: Vision-Language-Action models have emerged as a promising paradigm for robotic manipulation by unifying perception, language grounding, and action gener

FedStain: Modeling Higher-Order Stain Statistics for Federated Domain Generalization in Computational Pathology

arXiv:2605.14590v1 Announce Type: new Abstract: Robust whole-slide image (WSI) analysis under strict data-governance remains challenging due to substantial cross-institutional stain heterogeneity. Dom

MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models

arXiv:2605.14906v1 Announce Type: new Abstract: Memory is essential for large vision-language models (LVLMs) to handle long, multimodal interactions, with two method directions providing this capabili

Octopus: History-Free Gradient Orthogonalization for Continual Learning in Multimodal Large Language Models

arXiv:2605.14938v1 Announce Type: cross Abstract: Continual learning in multimodal large language models (MLLMs) aims to sequentially acquire knowledge while mitigating catastrophic forgetting, yet ex

Quantitative Video World Model Evaluation for Geometric-Consistency

arXiv:2605.15185v1 Announce Type: cross Abstract: Generative video models are increasingly studied as implicit world models, yet evaluating whether they produce physically plausible 3D structure and m

safetyarxiv-cs-ai

RePack then Refine: Efficient Diffusion Transformer with Vision Foundation Model

arXiv:2512.12083v3 Announce Type: replace Abstract: Semantic-rich features from Vision Foundation Models (VFMs) have been leveraged to enhance Latent Diffusion Models (LDMs). However, raw VFM features

researcharxiv-cs-cv

Rethinking Output Alignment For 1-bit Post-Training Quantization of Large Language Models

arXiv:2512.21651v2 Announce Type: replace Abstract: Large Language Models (LLMs) deliver strong performance across a wide range of NLP tasks, but their massive sizes hinder deployment on resource-cons

safetyarxiv-cs-lg

Applications

Scalable Krylov Subspace Methods for Generalized Mixed-Effects Models with Crossed Random Effects

arXiv:2505.09552v3 Announce Type: replace-cross Abstract: Mixed-effects models are widely used to model data with hierarchical grouping structures and high-cardinality categorical predictor variables.

applicationsarxiv-cs-lg

SemaTune: Semantic-Aware Online OS Tuning with Large Language Models

arXiv:2605.15026v1 Announce Type: cross Abstract: Online OS tuning can improve long-running services, but existing controllers are poorly matched to live hosts. They treat scheduler, power, memory, an

Teaching Large Language Models When Not to Know: Learning Temporal Critique for Ex-Ante Reasoning

arXiv:2605.14636v1 Announce Type: new Abstract: Large language models (LLMs) often fail to reason under temporal cutoffs: when prompted to answer from the standpoint of an earlier time, they exploit k

researcharxiv-cs-ai

Uncertainty Quantification for Large Language Diffusion Models

arXiv:2605.14570v1 Announce Type: new Abstract: Large Language Diffusion Models (LLDMs) are emerging as an alternative to autoregressive models, offering faster inference through higher parallelism. S

researcharxiv-cs-cl

Weekends are for vibe coding. But are your vibes continuously improving? Fine-tune your own model → stop waiting on someone else's release c…

model-releasesfireworks-ai--x

Weekends are for vibe coding. But are your vibes continuously improving? Fine-tune your own model → stop waiting on someone else's release cycle. Today's training update: Gemma 4 Dense is now availabl

A Markov Categorical Framework for Language Modeling