Search: “models”

Interfaze: The Future of AI is built on Task-Specific Small Models

arXiv:2602.04101v2 Announce Type: replace Abstract: We present Interfaze, a native hybrid model that fuses task-specific deep neural networks (CNNs and DNNs) directly into a transformer decoder throug

LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models

DGX agent

arXiv:2606.04485v1 Announce Type: new Abstract: Tabular foundation models (TFMs) increasingly rival tree ensembles, but their performance is often compute-inefficient: with standard affine scalar toke

model-releasesarxiv-cs-lg

4 Jun 2026

LoopMoE: Unifying Iterative Computation with Mixture-of-Experts for Language Modeling

arXiv:2606.04438v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) and looped architectures scale models along two orthogonal axes, namely parameter capacity and effective depth. However, main

QuBLAST: A Framework for Quantizing Large Language Models with Block-Level Compression Approach and Activation Scaling Strategy

arXiv:2606.04620v1 Announce Type: cross Abstract: LLMs have become the state-of-the-art algorithms for solving NLP tasks. However, they typically come at huge computational and memory costs, thus maki

SPLIT-PINN: Separable Probability Learning Technique via Physics-Informed Neural Networks for High-Dimensional Probabilistic Modeling

arXiv:2606.04000v1 Announce Type: cross Abstract: We present a probabilistic modeling framework for incorporating small-scale spatial heterogeneity into macroscopic descriptions of material behavior f

Applications

Towards Evaluating the Robustness of Visual State Space Models

arXiv:2406.09407v3 Announce Type: replace Abstract: Vision State Space Models (VSSMs), a novel architecture that combines the strengths of recurrent neural networks and latent variable models, have de

applicationsarxiv-cs-cv

transitions like this are why we think it's helpful to have a provider-agnostic harness we used to talk more about swapping models when the …

model-releasesharrison-chase--x

transitions like this are why we think it's helpful to have a provider-agnostic harness we used to talk more about swapping models when the latest and greatest came out -- but the latest and greatest

UniCAD: A Unified Benchmark and Universal Model for Multi-Modal Multi-Task CAD

arXiv:2606.05058v1 Announce Type: cross Abstract: Computer-Aided Design (CAD) underpins modern engineering and manufacturing by enabling the creation of precise, editable 3D models. However, CAD resea

VGGSounder: Audio-Visual Evaluations for Foundation Models

arXiv:2508.08237v4 Announce Type: replace-cross Abstract: The emergence of audio-visual foundation models underscores the importance of reliably assessing their multi-modal understanding. The VGGSound

Tutorials

A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners

arXiv:2606.03685v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) improves end-to-end classical planning in large language models (LLMs), but do these models also learn to represent and r

tutorialsarxiv-cs-ai

Tools

[AINews] Microsoft Build: MAI-Thinking-1 and MAI Family models

Microsoft announced the MAI-Thinking-1 and MAI family of models at their Build conference, representing new advances in their AI model lineup. These models likely focus on improved reasoning capabilit

toolslatent-space

Another banger open-source release. Miso One is an 8B text-to-speech model with real emotional range, so voiceovers carry warmth, hesitation…

Another banger open-source release. Miso One is an 8B text-to-speech model with real emotional range, so voiceovers carry warmth, hesitation, and excitement instead of sounding flat. It's purpose-buil

model-releasesdair-ai--x

Automated Report-Derived Oncology VQA Benchmark for Evaluating Vision-Language Models on 3D Medical Imaging

arXiv:2606.02809v1 Announce Type: new Abstract: Evaluating vision-language models (VLMs) on medical images requires benchmarks that are clinically grounded, scalable, and controlled for evaluation con

BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces

arXiv:2606.02798v1 Announce Type: new Abstract: Many decision-support settings require systems that adapt to individual users, but evaluation data for this problem remain limited. Existing benchmarks

Consistent Yet Wrong: Evidence Insensitivity in Spatial Vision-Language Models

arXiv:2606.02742v1 Announce Type: new Abstract: Spatial reasoning is fundamental to robotics, autonomy, and embodied AI, yet modern vision-language models (VLMs) remain unreliable on metric distance q

Google introduces Gemma 4 12B, a unified, encoder-free open multimodal model that can run locally on devices with 16GB of VRAM or unified memory (Carl Franzen/VentureBeat)

Carl Franzen / VentureBeat: Google introduces Gemma 4 12B, a unified, encoder-free open multimodal model that can run locally on devices with 16GB of VRAM or unified memory — While many AI open source

model-releasestechmeme

ReaLM: Residual Quantization Bridging Knowledge Graph Embeddings and Large Language Models

arXiv:2510.09711v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have recently emerged as a powerful paradigm for Knowledge Graph Completion (KGC), offering strong reasoning and

Reasoning Structure of Large Language Models

arXiv:2606.03883v1 Announce Type: new Abstract: Large reasoning models (LRMs) are often evaluated using metrics such as final-answer accuracy or token count. However, identical scores on these metrics

RogueMerge: Robust and Unified Attacks against LLM Model Merging

arXiv:2606.03344v1 Announce Type: cross Abstract: Model merging composes specialized capabilities into a single LLM by aggregating task vectors sourced from unverified public platforms, exposing a cri

SVHalluc: Benchmarking Speech-Vision Hallucination in Audio-Visual Large Language Models

arXiv:2606.02642v1 Announce Type: cross Abstract: Despite the success of audio-visual large-language models (LLMs), they can produce plausible but ungrounded outputs, termed hallucination. Existing be

Synthetic Hallucinations, Real Gains: Hard Negatives from Frontier Models for FIM Hallucination Mitigation

arXiv:2606.03130v1 Announce Type: new Abstract: Small open-source code models that power IDE autocomplete still emit hallucinated Fill-in-the-Middle (FIM) completions: syntactically natural calls to m

VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models

arXiv:2512.22539v2 Announce Type: replace-cross Abstract: While Vision-Language-Action models (VLAs) are rapidly advancing towards generalist robot policies, it remains difficult to quantitatively und

Safety

When Models Refuse: Political Steerability and Feature Richness as Measures of Ideological Depth

arXiv:2508.21448v3 Announce Type: replace Abstract: Large language models (LLMs) sometimes refuse to follow benign instructions, such as declining to argue a political position or adopt a stated perso

safetyarxiv-cs-cl

Assessment of Generative Named Entity Recognition in the Era of Large Language Models

arXiv:2601.17898v2 Announce Type: replace Abstract: Named entity recognition (NER) is evolving from a sequence labeling task into a generative paradigm with the rise of large language models (LLMs). W

Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization

arXiv:2606.02300v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains, yet personalizing their outputs to individual users remai

Business Utility of Large Language Models as Exploratory Data Analysis Agents

arXiv:2606.00051v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in analytical workflows, but their suitability as exploratory data analysis (EDA) agents in busines

Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation

arXiv:2606.01048v1 Announce Type: new Abstract: We propose Decoupled Residual Denoising Diffusion models (DRDD) for unified and data-efficient image-to-image (I2I) translation. While diffusion models

researcharxiv-cs-cv

DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?

arXiv:2505.16915v3 Announce Type: replace-cross Abstract: While recent Text-to-Image (T2I) models show impressive capabilities in synthesizing images from brief descriptions, they struggle with the lo

Domain-Shift-Aware Conformal Prediction for Large Language Models

arXiv:2510.05566v2 Announce Type: replace-cross Abstract: Large language models have achieved impressive performance across diverse tasks. However, their tendency to produce overconfident and factuall

Dynamic Proxy-Mixing: Transferring Replay Controllers from Small to Large Models for Continual Instruction Tuning

arXiv:2606.00400v1 Announce Type: new Abstract: Continual instruction tuning updates a language model through a sequence of new domains, yet each update can progressively erode previously learned capa

Emergent Transfer of a Physics Foundation Model from Simulation to Laboratory Turbulence

arXiv:2606.01470v1 Announce Type: cross Abstract: Whether physics foundation models can be usefully deployed on laboratory experiments remains an open question for scientific machine learning (ML). We

From Moments to Models: Graphon-Mixture Learning for Mixup and Contrastive Learning

arXiv:2510.03690v4 Announce Type: replace Abstract: Real-world graph datasets often arise from mixtures of populations, where graphs are generated by multiple distinct underlying distributions. In thi

GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning

arXiv:2601.22651v2 Announce Type: replace-cross Abstract: Training-data attribution for vision generative models aims to identify which training data influenced a given output. While most methods scor

Learning Action-Conditional and Object-Centric Gaussian Splatting World Models for Rigid Objects

arXiv:2606.01950v1 Announce Type: cross Abstract: World models enable intelligent agents to predict the consequences of their actions on the environment. In this paper, we propose Multi Rigid Object G

researcharxiv-cs-cv

Machine Learning Surrogate Modeling for Homogenization of Hyperelastic Materials with Boolean Microstructures

arXiv:2606.00938v1 Announce Type: cross Abstract: Data-driven surrogate models are an alternative to numerical homogenization of heterogeneous materials. In this contribution, a supervised learning ap

Margin Adaptive DPO: Leveraging Reward Model for Granular Control in Preference Optimization

arXiv:2510.05342v2 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) has emerged as a simple and effective method for aligning large language models. However, its reliance on

Local Ai

MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models

arXiv:2606.01060v1 Announce Type: cross Abstract: Preference alignment has substantially improved the observable behavior of large language models, yet it remains unclear what alignment changes intern

local-aiarxiv-cs-ai

PaperVoyager : Building Interactive Web with Visual Language Models

arXiv:2603.22999v3 Announce Type: replace Abstract: Recent advances in visual language models have enabled autonomous agents for complex reasoning, tool use, and document understanding. However, exist

Pramana: Fine-Tuning Large Language Models for Epistemic Reasoning through Navya-Nyaya

arXiv:2604.04937v1 Announce Type: cross Abstract: Large language models produce fluent text but struggle with systematic reasoning, often hallucinating confident but unfounded claims. When Apple resea

ProbeScale: Probing Analysis to Optimize Neural Scaling Laws for Efficient Small Language Model Inference

arXiv:2606.01806v1 Announce Type: cross Abstract: Small Language Models (SLMs) offer a balance between capability and computational feasibility. Neural scaling laws inform their optimal training, sugg

Local Ai

RA-LWLM: Retrieval-Augmented In-Context Localization with Wireless Foundation Models

arXiv:2606.01899v1 Announce Type: cross Abstract: Wireless localization is a fundamental capability of sixth-generation (6G) networks. Conventional model-based methods require accurate modeling of the

local-aiarxiv-cs-ai

Revise, Don't Freeze: Sampler-Matched Training for Self-Correcting Masked Diffusion Language Models

arXiv:2606.01026v1 Announce Type: new Abstract: Masked diffusion language models (MDLMs) re-predict every position at each denoising step, but standard samplers commit tokens once revealed, leaving th

RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models

model-releasesarxiv-cs-ro

arXiv:2606.02277v1 Announce Type: new Abstract: Vision-language-action (VLA) models are built on the premise that semantic understanding from pretrained language or vision-language backbones should gu

Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders

arXiv:2606.00746v1 Announce Type: new Abstract: Vision foundation models are bottlenecked by the quadratic cost of self-attention, which limits usable resolution and increases the cost of large-scale

Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning

arXiv:2603.11653v2 Announce Type: replace Abstract: Continual Reinforcement Learning (CRL) for Vision-Language-Action (VLA) models is a promising direction toward self-improving embodied agents that c

SimSD: Simple Speculative Decoding in Diffusion Language Models

arXiv:2606.02544v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs, offering faster inference throug

Tiny Recursive Models for Solving the J2-Perturbed Lambert Problem

arXiv:2606.00895v1 Announce Type: cross Abstract: This paper presents a fast, recursive neural solver for the J2-perturbed Lambert problem based on Tiny Recursive Models (TRM), termed the TRM-Perturbe

Towards 3D-Aware Video Diffusion Models: Render-Free Human Motion Control with Mesh Tokenization

arXiv:2606.02000v1 Announce Type: cross Abstract: Diffusion models have shown remarkable success in video generation. However, whether such models are truly aware of the 3D structure underlying visual