Search: “models”

HERO: Hierarchical Extrapolation and Refresh for Efficient World Models

arXiv:2508.17588v2 Announce Type: replace Abstract: Generation-driven world models create immersive virtual environments but suffer slow inference due to the iterative nature of diffusion models. Whil

researcharxiv-cs-cv

Local Ai

Model page: https://ollama.com/library/glm-5.1

DGX agent

GLM-5.1 is a language model available through Ollama's model library, accessible via the Ollama platform for local deployment and use. The model can be pulled and run locally using Ollama's tools, mak

local-aiollama--x

15 May 2026

Proxy Compression for Language Modeling

arXiv:2602.04289v2 Announce Type: replace Abstract: Modern language models are trained almost exclusively on token sequences produced by a fixed tokenizer, an external lossless compressor often over U

safetyarxiv-cs-cl

REALM: Retrospective Encoder Alignment for LFP Modeling

arXiv:2605.14867v1 Announce Type: cross Abstract: Spike activity has been the dominant neural signal for behavior decoding due to its high spatial and temporal resolution. However, as brain-computer i

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

arXiv:2605.15178v1 Announce Type: new Abstract: We introduce SANA-WM, an efficient 2.6B-parameter open-source world model natively trained for one-minute generation, synthesizing high-fidelity, 720p,

Some models to try with Codex: kimi-k2.6:cloud (with vision support) glm-5.1:cloud If you don't yet have a paid subscription with Ollama's c…

Some models to try with Codex: kimi-k2.6:cloud (with vision support) glm-5.1:cloud If you don't yet have a paid subscription with Ollama's cloud, choose a model that supports reliable tool calling: ne

model-releasesollama--x

Hardware

Synthetic Sociality: How Generative Models Privatize the Social Fabric

arXiv:2605.14090v1 Announce Type: cross Abstract: We put forth a critical theoretical framework for analyzing generative models both descriptively and normatively. Our thesis is that generative models

hardwarearxiv-cs-lg

Unsupervised learning of acquisition variability in structural connectomes via hybrid latent space modeling

arXiv:2605.13933v1 Announce Type: cross Abstract: Acquisition differences across sites, scanners, and protocols in dMRI introduce variability that complicates structural connectome analysis. This moti

Benchmarking Attribute Discrimination in Infant-Scale Vision-Language Models

arXiv:2512.18951v3 Announce Type: replace Abstract: Infants learn not only object categories but also fine-grained visual attributes such as color, size, and texture from limited experience. Prior inf

Characterizing Universal Object Representations Across Vision Models

arXiv:2605.13675v1 Announce Type: new Abstract: Deep neural networks trained with different architectures, objectives, and datasets have been reported to converge on similar visual representations. Ho

safetyarxiv-cs-cv

DAWM: Diffusion Action World Models for Offline Reinforcement Learning via Action-Inferred Transitions

arXiv:2509.19538v2 Announce Type: replace-cross Abstract: Diffusion-based world models have demonstrated strong capabilities in synthesizing realistic long-horizon trajectories for offline reinforceme

Domain Adaptation of Large Language Models for Polymer-Composite Additive Manufacturing Using Retrieval-Augmented Generation and Fine-Tuning

arXiv:2605.12516v1 Announce Type: cross Abstract: General-purpose large language models (LLMs) often struggle to generate reliable responses in specialized engineering domains due to limited domain gr

Entropy Aware Reward Guidance for Diffusion Language Model Alignment

arXiv:2602.05000v2 Announce Type: replace-cross Abstract: Reward guidance, also known as posterior sampling, is a popular method for test-time adaptation and post-training in continuous diffusion mode

TiCo: Time-Controllable Spoken Dialogue Model

arXiv:2603.22267v2 Announce Type: replace-cross Abstract: We introduce TiCo, a time-controllable spoken dialogue model (SDM) that follows time-constrained instructions (e.g., 'Please generate a respon

UNIV: Unified Foundation Model for Infrared and Visible Modalities

arXiv:2509.15642v3 Announce Type: replace Abstract: Joint RGB-infrared perception is essential for achieving robustness under diverse weather and illumination conditions. Although foundation models ex

Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics

arXiv:2605.12178v1 Announce Type: cross Abstract: World models enable agents to anticipate the effects of their actions by internalizing environment dynamics. In enterprise systems, however, these dyn

EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming Languages

arXiv:2603.09678v2 Announce Type: replace-cross Abstract: Large language models achieve near-ceiling performance on code generation benchmarks, yet most of the programming languages used by popular be

HEBATRON: A Hebrew-Specialized Open-Weight Mixture-of-Experts Language Model

arXiv:2605.11255v1 Announce Type: new Abstract: We present Hebatron, a Hebrew-specialized open-weight large language model built on the NVIDIA Nemotron-3 sparse Mixture-of-Experts architecture. Traini

HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer

arXiv:2605.11061v1 Announce Type: new Abstract: The evolution of visual generative models has long been constrained by fragmented architectures relying on disjoint text encoders and external VAEs. In

LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?

arXiv:2605.11301v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have heterogeneous strengths across OCR, chart understanding, spatial reasoning, visual question answering, c

safetyarxiv-cs-cl

Applications

Mechanistic Interpretability of ASR models using Sparse Autoencoders

arXiv:2605.12225v1 Announce Type: new Abstract: Understanding the internal machinations of deep Transformer-based NLP models is more crucial than ever as these models see widespread use in various dom

applicationsarxiv-cs-cl

MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models

arXiv:2501.02955v2 Announce Type: replace Abstract: In recent years, vision language models (VLMs) have made significant advancements in video understanding. However, a crucial capability - fine-grain

Agents

Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs

arXiv:2605.12460v1 Announce Type: cross Abstract: The continued improvements in language model capability have unlocked their widespread use as drivers of autonomous agents, for example in coding or c

agentsarxiv-cs-cl

Pretraining Strategies and Scaling for ECG Foundation Models: A Systematic Study

arXiv:2605.12241v1 Announce Type: cross Abstract: Specialized foundation models are beginning to emerge in various medical subdomains, but pretraining methodologies and parametric scaling with the siz

researcharxiv-cs-lg

Probabilistic Calibration Is a Trainable Capability in Language Models

arXiv:2605.11845v1 Announce Type: new Abstract: Language models are increasingly used in settings where outputs must satisfy user-specified randomness constraints, yet their generation probabilities a

StoicLLM: Preference Optimization for Philosophical Alignment in Small Language Models

arXiv:2605.11483v1 Announce Type: new Abstract: While large language models excel at factual adaptation, their ability to internalize nuanced philosophical frameworks under severe data constraints rem

World Action Models: The Next Frontier in Embodied AI

arXiv:2605.12090v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have achieved strong semantic generalization for embodied policy learning, yet they learn reactive observation-to-

safetyarxiv-cs-cl

A Geometric Perspective on Next-Token Prediction in Large Language Models: Three Emerging Phases

arXiv:2605.09011v1 Announce Type: cross Abstract: We investigate the geometry of predictive information across the layers of large language models (LLMs). We repurpose representation lenses-learned af

CLEF: EEG Foundation Model for Learning Clinical Semantics

arXiv:2605.10817v1 Announce Type: new Abstract: Clinical EEG interpretation requires reasoning over full EEG sessions and integrating signal patterns with clinical context. Existing EEG foundation mod

Continuity Laws for Sequential Models

arXiv:2605.08539v1 Announce Type: cross Abstract: Inductive biases influence the behavior and performance of sequential models. In this work, we study an underexplored inductive bias in sequential mod

safetyarxiv-cs-ai

DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification

arXiv:2605.09269v1 Announce Type: new Abstract: Aligning Multimodal Large Language Models (MLLMs) requires reliable reward models, yet existing single-step evaluators can suffer from lazy judging, exp

researcharxiv-cs-cl

Tutorials

Efficient Estimation of Kernel Surrogate Models for Task Attribution

arXiv:2602.03783v2 Announce Type: replace-cross Abstract: Modern AI agents such as large language models are trained on diverse tasks -- translation, code generation, mathematical reasoning, and text

tutorialsarxiv-cs-ai

Evaluating Pragmatic Reasoning in Large Language Models: Evidence from Scalar Diversity

arXiv:2605.09042v1 Announce Type: new Abstract: Evaluating pragmatic reasoning in large language models (LLMs) remains challenging because model behavior can vary depending on evaluation methods. Prev

researcharxiv-cs-cl

FormalRewardBench: A Benchmark for Formal Theorem Proving Reward Models

arXiv:2605.10141v1 Announce Type: new Abstract: Recent neural theorem provers use reinforcement learning with verifiable rewards (RLVR), where proof assistants provide binary correctness signals. Whil

H-POPE: Hierarchical Polling-based Probing Evaluation of Hallucinations in Large Vision-Language Models

arXiv:2411.04077v2 Announce Type: replace Abstract: By leveraging both texts and images, large vision language models (LVLMs) have shown significant progress in various multi-modal tasks. Nevertheless

LaWM: Least Action World Models for Long-Horizon Physical Consistency from Visual Observations

arXiv:2605.08279v1 Announce Type: cross Abstract: Learning predictive world models from visual observations is a core problem in embodied AI, with applications to model-based reinforcement learning an

safetyarxiv-cs-ai

Modeling Atomic Conformational Ensembles of Proteins via Test-Time Supervision of Boltz-2 on Cryo-EM Density Maps

arXiv:2605.09832v1 Announce Type: new Abstract: Knowledge of a protein's atomic conformational ensemble is critical to determining its function, yet state-of-the-art ensemble prediction models are lim

researcharxiv-cs-lg

PhyGround: Benchmarking Physical Reasoning in Generative World Models

arXiv:2605.10806v1 Announce Type: cross Abstract: Generative world models are increasingly used for video generation, where learned simulators are expected to capture the physical rules that govern re

Position: AI Security Policy Should Target Systems, Not Models

arXiv:2605.09504v1 Announce Type: cross Abstract: We present swarm-attack, an open-source adversarial testing framework in which multiple lightweight LLM agents coordinate through shared memory, paral

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models

arXiv:2605.09630v1 Announce Type: new Abstract: Tokenizer-free language models eliminate the tokenizer step of the language modeling pipeline by operating directly on bytes; patch-based variants furth

researcharxiv-cs-cl

SMIXAE: Towards Unsupervised Manifold Discovery in Language Models

arXiv:2605.09224v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) have been used widely to decompose and interpret neural network activations, especially those of transformer language models.

SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?

arXiv:2602.03916v3 Announce Type: replace-cross Abstract: Spatial reasoning is a fundamental aspect of human cognition, yet it remains a major challenge for contemporary vision-language models (VLMs).

TabPFN-3 just released: a pre-trained tabular foundation model for up to 1M rows [R][N]

model-releasesr-machinelearning

TabPFN-3 is a pre-trained tabular foundation model that supports datasets up to 1,000,000 rows × 200 features , representing a significant scaling improvement for the TabPFN family. The model delivers

TIDES: Implicit Time-Awareness in Selective State Space Models

arXiv:2605.09742v1 Announce Type: cross Abstract: Selective state space models (SSMs), such as Mamba, achieve strong per-token expressivity by making the time discretization step Tilde{Delta} a learne

Towards Generative Predictive Display for Vision-Based Teleoperation: A Zero-Shot Benchmark of Off-the-Shelf Video Models

arXiv:2605.09670v1 Announce Type: cross Abstract: Teleoperation systems are fundamentally limited by communication latency, which degrades situational awareness and control performance. Predictive dis

Transformation-Augmented GRPO for Enhancing Exploration in Reasoning of Large Language Models

arXiv:2601.22478v3 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO) has become the dominant method for reinforcement learning with verifiable rewards in large language models

VC-Soup: Value-Consistency Guided Multi-Value Alignment for Large Language Models

arXiv:2603.18113v2 Announce Type: replace-cross Abstract: As large language models (LLMs) increasingly shape content generation, interaction, and decision-making across the Web, aligning them with hum

VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models

model-releasesarxiv-cs-ro

arXiv:2605.10485v1 Announce Type: new Abstract: Precise spatial reasoning is fundamental to robotic manipulation, yet the visual backbones of current vision-language-action (VLA) models are predominan