Search: “models”

CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models

arXiv:2601.21798v2 Announce Type: replace Abstract: Large Language Models(LLMs) have revolutionized text generation and multimodal perception,but their capabilities in 3D content generation remain und

researcharxiv-cs-cv

EgoExo-WM: Unlocking Exo Video for Ego World Models

DGX agent

arXiv:2605.15477v1 Announce Type: new Abstract: Egocentric world models present a promising direction for enabling agents to predict and plan, but their performance is constrained by the limited avail

safetyarxiv-cs-cv

18 May 2026

Extrapolation Guarantees for Perturbation Modeling Under the Additive Latent Shift Assumption

arXiv:2504.18522v3 Announce Type: replace-cross Abstract: We consider the problem of modeling the effects of perturbations like gene knockouts on measurements such as single-cell RNA counts. Given dat

Few-Shot Large Language Models for Actionable Triage Categorization of Online Patient Inquiries

model-releasesarxiv-cs-cl

arXiv:2605.15680v1 Announce Type: new Abstract: Online patient inquiries are often informal, incomplete, and written before professional assessment, yet they must still be routed to an appropriate lev

Few-Step Diffusion Language Models via Trajectory Self-Distillation

arXiv:2602.12262v3 Announce Type: replace Abstract: Diffusion large language models (DLLMs) have emerged as powerful generative models with the promise of fast text generation through parallel decodin

researcharxiv-cs-cl

Large Language Models Could Be Rote Learners

arXiv:2504.08300v5 Announce Type: replace-cross Abstract: Benchmark-based evaluation, e.g., multiple-choice questions (MCQs) and open-ended questions (OEQs), is widely used for evaluating Large Langua

Metropolis-Scale Road Network Datasets for Fine-Grained Urban Traffic Modeling

arXiv:2510.02278v2 Announce Type: replace Abstract: Modeling traffic dynamics is a critical challenge for urban computing, with applications from real-time traffic management to infrastructure plannin

applicationsarxiv-cs-lg

PanoWorld: Geometry-Consistent Panoramic Video World Modeling

arXiv:2605.15391v1 Announce Type: cross Abstract: We present PanoWorld, a panoramic video world model that generates geometry-consistent 360egree video from a single image and a caption. Existing pano

Prompt Stability Scoring for Text Annotation with Large Language Models

arXiv:2407.02039v3 Announce Type: replace Abstract: Researchers are increasingly using language models (LMs) for text annotation. These approaches rely only on a prompt telling the model to return a g

researcharxiv-cs-cl

Retrieval-Augmented Large Language Models for Schema-Constrained Clinical Information Extraction

arXiv:2605.15467v1 Announce Type: cross Abstract: Conversational nurse-patient transcripts contain actionable observations, but converting these transcripts into structured representations at scale re

Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models

arXiv:2605.15961v1 Announce Type: new Abstract: Large-scale pre-trained vision-language models like CLIP demonstrate remarkable zero-shot performance across diverse tasks. However, fine-tuning these m

researcharxiv-cs-cv

Testing properties of trees in graphical models with covariance queries

arXiv:2605.15996v1 Announce Type: cross Abstract: We consider the problem of testing properties of graphs underlying high-dimensional graphical models. We adopt the model of covariance queries introdu

Industry

the team did an internal test of this model last week the whole company (bar a few exceptions) had all their cursor chats redirected to comp…

the team did an internal test of this model last week the whole company (bar a few exceptions) had all their cursor chats redirected to composer 2.5 for like 2 days. i didn't even notice, which I thin

industryelon-musk--x

💯. Way too much focus on language models.

💯. Way too much focus on language models. Fei-Fei Li warns that AI may be staring too hard at language models. The world is not just text on a screen. It is physical, visual, spatial, and always chang

safetygary-marcus--x

16 May 2026

AIM-DDI: A Model-Agnostic Multimodal Integration Module for Drug-Drug Interaction Prediction

arXiv:2605.14327v1 Announce Type: cross Abstract: Drug-drug interaction (DDI) prediction is a critical task in computational biomedicine, as adverse interactions between co-administered drugs can caus

Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models

arXiv:2601.03969v2 Announce Type: replace Abstract: Large reasoning models enhanced by reinforcement learning with verifiable rewards have achieved significant performance gains by extending their cha

BiSpikCLM: A Spiking Language Model integrating Softmax-Free Spiking Attention and Spike-Aware Alignment Distillation

arXiv:2605.13859v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs) offer promising energy-efficient alternatives to large language models (LLMs) due to their event-driven nature and ultr

BiTrajDiff: Bidirectional Trajectory Generation with Diffusion Models for Offline Reinforcement Learning

arXiv:2506.05762v5 Announce Type: replace Abstract: Recent advances in offline Reinforcement Learning (RL) have proven that effective policy learning can benefit from imposing conservative constraints

Local Ai

Breaking the Reasoning Horizon in Entity Alignment Foundation Models

arXiv:2601.21174v2 Announce Type: replace Abstract: Entity alignment (EA) is critical for knowledge graph (KG) fusion. Existing EA models lack transferability and are incapable of aligning unseen KGs

local-aiarxiv-cs-lg

Complacent, Not Sycophantic: Reframing Large Language Models and Designing AI Literacy for Complacent Machines

arXiv:2605.14544v1 Announce Type: new Abstract: Large language models are often described as sycophantic, in the sense that they appear to flatter users or mirror their beliefs. We argue that this lab

Enhanced and Efficient Reasoning in Large Learning Models

arXiv:2605.14036v1 Announce Type: new Abstract: In current Large Language Models we can trust the production of smoothly flowing prose on the basis of the principles of machine learning. However, ther

applicationsarxiv-cs-ai

Tools

free to start. fast on day zero. proud to power the default model for LangSmith Fleet. happy building.

free to start. fast on day zero. proud to power the default model for LangSmith Fleet. happy building. LangSmith Fleet now has a free model powered by @FireworksAI_HQ for Developer and Plus plans. It’

toolsfireworks-ai--x

GhostCite: A Large-Scale Analysis of Citation Validity in the Age of Large Language Models

arXiv:2602.06718v2 Announce Type: replace-cross Abstract: Citations provide the basis for trusting scientific claims; when they are invalid or fabricated, this trust collapses. With the advent of Larg

How Sensitive Are Radiomic AI Models to Acquisition Parameters?

arXiv:2605.14667v1 Announce Type: new Abstract: A main barrier for the deployment of AI radiomic systems in clinical routine is their drop in performance under heterogeneous multicentre acquisition pr

ImmuVis: Hyperconvolutional Foundation Model for Imaging Mass Cytometry

arXiv:2602.04585v2 Announce Type: replace Abstract: We present ImmuVis, a family of efficient foundation models for imaging mass cytometry (IMC), a high-throughput multiplex imaging technology that ha

applicationsarxiv-cs-cv

K-Models: a Flexible and Interpretable Method for Ordinal Clustering with Application to Antigen-Antibody Interaction Profiles

arXiv:2605.14828v1 Announce Type: cross Abstract: Existing clustering methods for functional data often prioritize partitioning accuracy over interpretability, making it challenging to extract meaning

Local Ai

KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning

arXiv:2605.14907v1 Announce Type: new Abstract: Knowledge graph (KG) foundation models aim to generalize across graphs with unseen entities and relations by learning transferable relational structure.

local-aiarxiv-cs-ai

M^2RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling

arXiv:2603.14360v2 Announce Type: replace-cross Abstract: Transformers are highly parallel but are limited to computations in the TC^0 complexity class, excluding tasks such as entity tracking and cod

Measuring and Mitigating Toxicity in Large Language Models: A Comprehensive Replication Study

arXiv:2605.14087v1 Announce Type: new Abstract: Large Language Models (LLMs), when trained on web-scale corpora, inherently absorb toxic patterns from their training data. This leads to ``toxic degene

safetyarxiv-cs-cl

Mitigating Mask Prior Drift and Positional Attention Collapse in Large Diffusion Vision-Language Models

arXiv:2605.14530v1 Announce Type: new Abstract: Large diffusion vision-language models (LDVLMs) have recently emerged as a promising alternative to autoregressive models, enabling parallel decoding fo

safetyarxiv-cs-cv

Pelican-Unified 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Action

arXiv:2605.15153v1 Announce Type: cross Abstract: We present Pelican-Unified 1.0, the first embodied foundation model trained according to the principle of unification. Pelican-Unified 1.0 uses a sing

Local Ai

Pixal3D: Generate high-fidelity 3D assets from a single image. (TencentARC, locally runnable model)

local-air-stablediffusion

Pixal3D is a locally runnable AI model developed by TencentARC that generates high-fidelity 3D assets from single 2D images. The tool leverages advanced techniques to convert 2D image inputs into deta

Polaris: A Godel Agent Framework for Small Language Models through Experience-Abstracted Policy Repair

arXiv:2603.23129v2 Announce Type: replace Abstract: Godel agent realize recursive self-improvement: an agent inspects its own policy and traces and then modifies that policy in a tested loop. We intro

RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO

arXiv:2605.15190v1 Announce Type: new Abstract: Causal autoregressive video diffusion models support real-time streaming generation by extrapolating future chunks from previously generated content. Di

safetyarxiv-cs-cv

Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity

arXiv:2605.14075v1 Announce Type: cross Abstract: Large language models (LLMs) have revolutionized natural language processing. Understanding their internal mechanisms is crucial for developing more i

researcharxiv-cs-cl

SurF: A Generative Model for Multivariate Irregular Time Series Forecasting

arXiv:2605.14069v1 Announce Type: new Abstract: Irregularly sampled multivariate event streams remain a stubbornly difficult modality for generative modeling: tokenization-based approaches break down

applicationsarxiv-cs-lg

TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability

arXiv:2605.14738v1 Announce Type: cross Abstract: Recent work has promoted task-aware layer pruning as a way to improve model performance on particular tasks, as shown by TALE. In this paper, we inves

Tutorials

To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model

arXiv:2605.14291v1 Announce Type: cross Abstract: The rapid advancement of Large Vision-Language Models (LVLMs) is increasingly accompanied by unauthorized scraping and training on multimodal web data

tutorialsarxiv-cs-ai

Tutorials

What Do EEG Foundation Models Capture from Human Brain Signals?

arXiv:2605.11410v2 Announce Type: replace Abstract: Clinical electroencephalogram (EEG) analysis rests on a hand-crafted feature catalog refined over decades, e.g., band power, connectivity, complexit

tutorialsarxiv-cs-ai

Differences in Text Generated by Diffusion and Autoregressive Language Models

arXiv:2605.12522v1 Announce Type: cross Abstract: Diffusion language models (DLMs) are promising alternatives to autoregressive language models (ARMs), yet the intrinsic differences in their generated

Early Semantic Grounding in Image Editing Models for Zero-Shot Referring Image Segmentation

arXiv:2605.13122v1 Announce Type: new Abstract: Instruction-based image editing (IIE) models have recently demonstrated strong capability in modifying specific image regions according to natural langu

researcharxiv-cs-cv

Exemplar-Free Continual Learning for State Space Models

arXiv:2505.18604v3 Announce Type: replace Abstract: State-Space Models (SSMs) excel at capturing long-range dependencies with structured recurrence, making them well-suited for sequence modeling. Howe

Generative Modeling from Black-box Corruptions via Self-Consistent Stochastic Interpolants

arXiv:2512.10857v2 Announce Type: replace-cross Abstract: Transport-based methods have emerged as a leading paradigm for building generative models from large, clean datasets. However, in many scienti

Generative Modeling of Approximately Periodic Time Series by a Posterior-Weighted Gaussian Process

arXiv:2605.13150v1 Announce Type: cross Abstract: Discrete automated processes in industrial and cyber-physical systems often exhibit a repetitive structure in which successive repetitions follow a co

Guide, Think, Act: Interactive Embodied Reasoning in Vision-Language-Action Models

model-releasesarxiv-cs-cv

arXiv:2605.13632v1 Announce Type: cross Abstract: In this paper, we propose GTA-VLA(Guide, Think, Act), an interactive Vision-Language-Action (VLA) framework that enables spatially steerable embodied

Inference-Time Machine Unlearning via Gated Activation Redirection

arXiv:2605.12765v1 Announce Type: new Abstract: Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety. Machine unlearning

interwhen: A Generalizable Framework for Steering Reasoning Models with Test-time Verification

arXiv:2602.11202v3 Announce Type: replace-cross Abstract: Reasoning models produce long traces of intermediate decisions and tool calls, making test-time verification important for ensuring correctnes

Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Models

arXiv:2605.12725v1 Announce Type: new Abstract: Recent video anomaly detection research has expanded rapidly with an emphasis on general models of normality intended to work across many different scen

safetyarxiv-cs-cv