Search: “models”

D-CLING: Prior-Preserving Depth-Conditioned Fine-Tuning for Navigation Foundation Models

arXiv:2605.19690v1 Announce Type: new Abstract: Navigation Foundation Models (NFMs) trained on large cross-embodied datasets have demonstrated powerful generalizability in various scenarios. Adopting

safetyarxiv-cs-ro

Model Releases

Federated Learning for ICD Classification with Lightweight Models and Pretrained Embeddings

DGX agent

arXiv:2507.03122v2 Announce Type: replace-cross Abstract: This study investigates the feasibility and performance of federated learning (FL) for multi-label ICD code classification using clinical note

model-releasesarxiv-cs-cl

20 May 2026

Agents

High-quality generation of dynamic game content via small language models: A proof of concept

arXiv:2601.23206v2 Announce Type: replace Abstract: Large language models (LLMs) offer promise for dynamic game content generation, but they face critical barriers, including narrative incoherence and

agentsarxiv-cs-ai

iGSP:Implicit Gradient Subspace Projection for Efficient Continual Learning of Vision-Language Models

model-releasesarxiv-cs-cv

arXiv:2605.19301v1 Announce Type: new Abstract: Vision-Language Models require efficient adaptation to continually emerging downstream tasks. While Parameter-Efficient Fine-Tuning mitigates catastroph

Neural Operators for Design-Space Surrogate Modeling of Tendon-Actuated Continuum Robots

arXiv:2605.19104v1 Announce Type: cross Abstract: Continuum robots enable dexterous manipulation in constrained environments, but require accurate and efficient models for real-time manipulation and c

researcharxiv-cs-ai

Probabilistic Tiny Recursive Model

arXiv:2605.19943v1 Announce Type: new Abstract: Tiny Recursive Models (TRM) solve complex reasoning tasks with a fraction of the parameters of modern large language models (LLMs) by iteratively refini

researcharxiv-cs-ai

Recursive Entropic Risk Optimization in Discounted MDPs: Sample Complexity Bounds with a Generative Model

arXiv:2506.00286v3 Announce Type: replace-cross Abstract: We study risk-sensitive reinforcement learning in finite discounted MDPs with recursive entropic risk measures (ERM), where the risk parameter

Local Ai

Rethinking Visual Attribution for Chest X-ray Reasoning in Large Vision Language Models

arXiv:2605.20158v1 Announce Type: cross Abstract: Large Vision Language Models (LVLMs) show promise in medical applications, but their inability to faithfully ground responses in visual evidence raise

local-aiarxiv-cs-ai

ScheduleFree+: Scaling Learning-Rate-Free & Schedule-Free Learning to Large Language Models

arXiv:2605.19095v1 Announce Type: cross Abstract: Schedule-Free Learning has shown promise as a practical anytime training method for machine learning, showing success across dozens of standard benchm

Shaping the Prior: How Synthetic Task Distributions Determine Tabular Foundation Model Quality

arXiv:2605.18971v1 Announce Type: cross Abstract: What determines the quality of a tabular foundation model? Unlike language or vision, tabular foundation models acquire their inductive biases almost

researcharxiv-cs-ai

SLoW: Select Low-frequency Words! Automatic Dictionary Selection for Translation on Large Language Models

model-releasesarxiv-cs-cl

arXiv:2507.18902v2 Announce Type: replace Abstract: There are more than 7,000 languages around the world, and current Large Language Models (LLMs) only support hundreds of languages. Dictionary-based

TADA! Tuning Audio Diffusion Models through Activation Steering

model-releasesarxiv-cs-lg

arXiv:2602.11910v2 Announce Type: replace-cross Abstract: Audio diffusion models can synthesize high-fidelity music from text, yet achieving fine-grained control over specific musical attributes remai

The proof came from a general-purpose reasoning model, not a system built specifically to solve math problems or this problem in particular,…

The proof came from a general-purpose reasoning model, not a system built specifically to solve math problems or this problem in particular, and represents an important milestone for the math and AI c

model-releasesopenai--x

Industry

Today, we’re sharing that a general-purpose internal @openai model achieved a breakthrough on one of the best-known combinatorial geometry p…

Today, we’re sharing that a general-purpose internal @openai model achieved a breakthrough on one of the best-known combinatorial geometry problems. Less than 1 year ago frontier AI models were at IMO

industrysam-altman--x

Tutorials

Tweedie's Formulae and Diffusion Generative Models Beyond Gaussian

arXiv:2605.19391v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in generating samples from unknown data distributions. Most popular stochastic differential equation

tutorialsarxiv-cs-lg

wait… did Cohere just release Command A+ models under Apache 2.0 for the first time ever?! 🙊 welcome to Europe! 🤗

model-releasesclem-delangue--x

wait… did Cohere just release Command A+ models under Apache 2.0 for the first time ever?! 🙊 welcome to Europe! 🤗 Introducing: Cohere Command A+ We’ve created our most powerful LLM yet, optimized it t

ARROW: Augmented Replay for RObust World models

arXiv:2603.11395v2 Announce Type: replace-cross Abstract: Continual reinforcement learning challenges agents to acquire new skills while retaining previously learned ones with the goal of improving pe

Contrastive Conceptor Activation Steering (COAST): Unlocking Vision-Language-Action Models through Hidden States

arXiv:2605.17144v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models leverage powerful perceptual priors from web-scale Vision-Language Model (VLM) pre-training, yet they remain surpr

CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and Benchmark

arXiv:2605.18621v1 Announce Type: cross Abstract: Spatial intelligence requires multimodal large language models (MLLMs) to move beyond single-view perception and reason consistently about objects, vi

Data-Driven Dynamic Modeling of a Tendon-Actuated Continuum Robot

arXiv:2605.18720v1 Announce Type: new Abstract: Developing dynamic models for tendon-driven continuum robots is challenging due to their nonlinear, high-dimensional, and friction-dominated dynamics. T

researcharxiv-cs-ro

Tutorials

deepagents v0.6 is about performance the first level at which we can control that is the model layer: how can you squeeze perf out of a mode…

tutorialsharrison-chase--x

deepagents v0.6 is about performance the first level at which we can control that is the model layer: how can you squeeze perf out of a model? tweaking prompts, tool names, and tool descriptions in ac

Diffusion Models, Denoiser Architecture and Creativity

arXiv:2605.16415v1 Announce Type: new Abstract: The creativity of diffusion models refers to their ability to generate highly realistic images that are different from their training data. Creativity i

safetyarxiv-cs-cv

Applications

DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics

arXiv:2603.09668v2 Announce Type: replace Abstract: Modeling wind-driven object dynamics from video observations is highly challenging due to the invisibility and spatio-temporal variability of wind,

applicationsarxiv-cs-cv

Dual-Space Knowledge Distillation with Key-Query Matching for Large Language Models with Vocabulary Mismatch

arXiv:2603.22056v2 Announce Type: replace Abstract: Large language models (LLMs) achieve state-of-the-art (SOTA) performance across language tasks, but are costly to deploy due to their size and resou

safetyarxiv-cs-cl

Dynamic Elliptical Graph Factor Models via Riemannian Optimization with Geodesic Temporal Regularization

model-releasesarxiv-cs-lg

arXiv:2605.18316v1 Announce Type: new Abstract: Inferring time-varying graph structures from high-dimensional nodal observations is a fundamental problem arising in neuroscience, finance, climatology,

ECG-WM: A Physiology-Informed ECG World Model for Clinical Intervention Simulation

arXiv:2605.17580v1 Announce Type: new Abstract: Electrocardiogram (ECG)-based models have achieved strong performance in diagnostic tasks, yet they remain limited in modeling how cardiac dynamics evol

Embodied Task Planning via Graph-Informed Action Generation with Large Language Models

model-releasesarxiv-cs-cl

arXiv:2601.21841v3 Announce Type: replace Abstract: While Large Language Models (LLMs) have demonstrated strong zero-shot reasoning capabilities, their deployment as embodied agents still faces fundam

Ensembling Tabular Foundation Models - A Diversity Ceiling And A Calibration Trap

arXiv:2605.18696v1 Announce Type: cross Abstract: Tabular foundation models (TFMs) now match or beat tuned gradient-boosted trees on a growing fraction of tabular tasks, but no single TFM wins on ever

Everything Google Cloud customers need to know coming out of Google I/O

model-releasesgoogle-cloud-ai

At Google Cloud Next ‘26, we unveiled the blueprint for the Agentic Enterprise, sharing our eighth-generation TPUs, Gemini Enterprise Agent Platform, a fully reimagined Agentic Data Cloud, Workspace I

FLAG: Foundation model representation with Latent diffusion Alignment via Graph for spatial gene expression prediction

arXiv:2605.18055v1 Announce Type: cross Abstract: Predicting spatial gene expression from routine H&E enables large-scale molecular profiling, yet current models treat this as isolated pointwise tasks

Fourier Compressor: Frequency-Domain Visual Token Compression for Vision-Language Models

arXiv:2508.06038v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) incur substantial computational overhead and inference latency due to the large number of vision tokens introduc

Local Ai

FrequencyBooster: Full-Frequency Modeling for High-Fidelity Pixel Diffusion

arXiv:2605.17759v1 Announce Type: new Abstract: To circumvent the inherent fidelity bottlenecks and optimization misalignment of VAE-based latent diffusion, pixel-space diffusion models have emerged a

local-aiarxiv-cs-cv

From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models

model-releasesarxiv-cs-cv

arXiv:2508.01608v2 Announce Type: replace Abstract: Image geolocalization, the task of identifying the geographic location depicted in an image, is important for applications in crisis response, digit

From Static Risk to Dynamic Trajectories: Toward World-Model-Inspired Clinical Prediction

arXiv:2605.16927v1 Announce Type: new Abstract: Clinical decision-making is a feedback system where risk estimates influence treatment, which in turn changes disease trajectories, and both shape clini

Geometry-Aware Attention Guidance for Diffusion Models via Modern Hopfield Dynamics

arXiv:2603.02531v2 Announce Type: replace-cross Abstract: Classifier-Free Guidance (CFG) improves sample quality in diffusion models, but its dual-pass inference and reliance on null-condition trainin

Google adds a conversational search feature to YouTube and rolls out the new Gemini Omni model in YouTube Shorts Remix and the Create app (Sanuj Bhatia/Android Central)

Sanuj Bhatia / Android Central: Google adds a conversational search feature to YouTube and rolls out the new Gemini Omni model in YouTube Shorts Remix and the Create app — Seriously, who is asking for

model-releasestechmeme

Local Ai

How Many Visual Tokens Do Multimodal Language Models Need? Scaling Visual Token Pruning with F^3A

arXiv:2605.16359v1 Announce Type: cross Abstract: Vision-language models improve perception by feeding increasingly long visual token sequences into language backbones, but the resulting inference cos

local-aiarxiv-cs-ai

Lance: Unified Multimodal Modeling by Multi-Task Synergy

arXiv:2605.18678v1 Announce Type: cross Abstract: We present Lance, a lightweight native unified model supporting multimodal understanding, generation, and editing for both images and videos. Rather t

Large Language Models and Impossible Language Acquisition: 'False Promise' or an Overturn of our Current Perspective towards AI

arXiv:2602.08437v5 Announce Type: replace Abstract: In Chomsky's provocative critique 'The False Promise of CHATGPT,' Large Language Models (LLMs) are characterized as mere pattern predictors that do

researcharxiv-cs-cl

Agents

Learning from Self-Debate: Preparing Reasoning Models for Multi-Agent Debate

arXiv:2601.22297v2 Announce Type: replace Abstract: The reasoning abilities of large language models (LLMs) have been substantially improved by reinforcement learning with verifiable rewards (RLVR). A

agentsarxiv-cs-cl

Multimodal Cultural Heritage Knowledge Graph Extension with Language and Vision Models

arXiv:2605.17669v1 Announce Type: new Abstract: The preservation and interpretation of cultural heritage increasingly rely on digital technologies, among which Knowledge Graphs (KGs) stand out for the

One Model, Two Roles: Emergent Specialization in a Shared Recurrent Transformer

arXiv:2605.17811v1 Announce Type: cross Abstract: Can a shared-weight recurrent Transformer develop distinct internal roles without being partitioned into separate modules? We study this in Asymmetric

Prune, Update and Trim: Robust Structured Pruning for Large Language Models

arXiv:2605.18331v1 Announce Type: new Abstract: Large Language Models (LLMs) have experienced significant growth and development in recent years. However, performing inference on LLMs remains costly,

researcharxiv-cs-lg

Query-Aware Learnable Graph Pooling Tokens as Prompt for Large Language Models

model-releasesarxiv-cs-cl

arXiv:2501.17549v2 Announce Type: replace Abstract: Graph-structured data plays a vital role in numerous domains, such as social networks, citation networks, commonsense reasoning graphs and knowledge

Applications

Reducing Hallucination in Vision-Language Models via Stage-wise Preference Optimization under Distribution Shift

arXiv:2605.16411v1 Announce Type: cross Abstract: Hallucination remains a fundamental challenge in vision-language models (VLMs), where autoregressive generation may produce linguistically plausible y

applicationsarxiv-cs-ai

Retrieval and competition: how a protein foundation model starts a protein

arXiv:2605.16331v1 Announce Type: cross Abstract: Protein language models are increasingly used to guide experimental and clinical decisions, yet it is often unclear whether a confident prediction ref

StableVLA: Towards Robust Vision-Language-Action Models without Extra Data

model-releasesarxiv-cs-cv

arXiv:2605.18287v1 Announce Type: new Abstract: It is infeasible to encompass all possible disturbances within the training dataset. This raises a critical question regarding the robustness of Vision-

Structured Labeling Enables Faster Vision-Language Models for End-to-End Autonomous Driving

arXiv:2506.05442v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) offer a promising approach to end-to-end autonomous driving due to their human-like reasoning capabilities. Howe