Search: “models”

Locale-Conditioned Few-Shot Prompting Mitigates Demonstration Regurgitation in On-Device PII Substitution with Small Language Models

arXiv:2605.13538v1 Announce Type: cross Abstract: Personally Identifiable Information (PII) redaction usually replaces detected entities with placeholder tokens such as [PERSON], destroying the downst

local-aiarxiv-cs-ai

Research

Make-It-Poseable: Feed-forward Latent Posing Model for 3D Characters

DGX agent

arXiv:2512.16767v2 Announce Type: replace Abstract: Posing 3D characters is a fundamental task in computer graphics. However, existing paradigms, ranging from traditional auto-rigging to recent pose-c

researcharxiv-cs-cv

14 May 2026

Mix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings

arXiv:2605.13225v1 Announce Type: new Abstract: For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many tim

researcharxiv-cs-lg

Multimodal Hidden Markov Models for Persistent Emotional State Tracking

arXiv:2605.12838v1 Announce Type: new Abstract: Tracking an interpretable emotional arc of a conversation via the sentiment of individual utterances processed as a whole is central to both understandi

Repurposing Image Diffusion Models for Training-Free Music Style Transfer on Mel-spectrograms

arXiv:2411.15913v4 Announce Type: replace-cross Abstract: Music style transfer blends source structure with reference style to enable personalized music creation. However, existing zero-shot methods o

Scale-Gest: Scalable Model-Space Synthesis and Runtime Selection for On-Device Gesture Detection

arXiv:2605.12506v1 Announce Type: cross Abstract: Realizing on-device ML-based gesture detection under tight real-time performance, energy and memory constraints is challenging, especially when consid

local-aiarxiv-cs-ai

Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs

arXiv:2605.13737v1 Announce Type: new Abstract: When an omnimodal large language model accepts a question whose textual premise contradicts what it actually sees or hears, does the failure lie in perc

Table-R1: Region-based Reinforcement Learning for Table Understanding

arXiv:2505.12415v3 Announce Type: replace-cross Abstract: Tables present unique challenges for language models due to their structured row-column interactions, necessitating specialized approaches for

The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge

arXiv:2605.12908v1 Announce Type: cross Abstract: Weak-to-strong (W2S) generalization, in which a strong model is fine-tuned on outputs of a weaker, task-specialized model, has been proposed as an app

researcharxiv-cs-lg

Training LLMs with Reinforcement Learning for Intent-Aware Personalized Question Answering

arXiv:2605.12645v1 Announce Type: cross Abstract: Effective personalized question answering (PQA) in language models requires grounding responses in the user's underlying intent, where intent refers t

Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty

model-releasesarxiv-cs-cl

arXiv:2605.11436v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed on long-horizon tasks in partially observable environments, where they must act while inferring a

Beyond Prediction: Interval Neural Networks for Uncertainty-Aware System Identification

arXiv:2605.11460v1 Announce Type: new Abstract: System identification (SysID) is critical for modeling dynamical systems from experimental data, yet traditional approaches often fail to capture nonlin

BitLM: Unlocking Multi-Token Language Generation with Bitwise Continuous Diffusion

arXiv:2605.11577v1 Announce Type: new Abstract: Autoregressive language models generate text one token at a time, yet natural language is inherently structured in multi-token units, including phrases,

researcharxiv-cs-cl

Built a Chrome extension that talks directly with your local Ollama models

A Chrome extension that communicates directly with local Ollama instances without sending data to external servers , enabling users to submit messages through a popup interface with responses streamin

local-air-ollama

DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding

arXiv:2312.02549v2 Announce Type: replace-cross Abstract: Temporal Language Grounding seeks to localize video moments that semantically correspond to a natural language query. Recent advances employ t

local-aiarxiv-cs-cl

Efficient and Adaptive Human Activity Recognition via LLM Backbones

arXiv:2605.12019v1 Announce Type: new Abstract: Human Activity Recognition (HAR) is a core task in pervasive computing systems, where models must operate under strict computational constraints while r

EvoNav: Evolutionary Reward Function Design for Robot Navigation with Large Language Models

arXiv:2605.11859v1 Announce Type: new Abstract: Robot navigation is a crucial task with applications to social robots in dynamic human environments. While Reinforcement Learning (RL) has shown great p

safetyarxiv-cs-ro

FLARE: Adaptive Multi-Dimensional Reputation for Robust Client Reliability in Federated Learning

arXiv:2511.14715v3 Announce Type: replace Abstract: Federated learning (FL) enables collaborative model training while preserving data privacy. However, it remains vulnerable to malicious clients who

Investigating simple target-covariate relationships for Chronos-2 and TabPFN-TS

arXiv:2605.12200v1 Announce Type: new Abstract: Time Series Foundation Models (TSFMs) have recently achieved state-of-the-art performance, often outperforming supervised models in zero-shot settings.

Modeling Narrative Structure in Latin Epic Poetry with Automatically Generated Story Grammars

arXiv:2502.12276v2 Announce Type: replace Abstract: Computational methods for analyzing prose and poetry utilize word embeddings and other abstract representations that sometimes obscure context-rich

researcharxiv-cs-cl

Multimodal Abstractive Summarization of Instructional Videos with Vision-Language Models

arXiv:2605.11959v1 Announce Type: cross Abstract: Multimodal video summarization requires visual features that align semantically with language generation. Traditional approaches rely on CNN features

safetyarxiv-cs-cl

Quantifying the Reconstructability of Astrophysical Methods with Large Language Models and Information Theory: A Case Study in Spectral Reconstruction

arXiv:2605.11154v1 Announce Type: cross Abstract: Modern astrophysical studies rely heavily on complex data analysis pipelines; however, published descriptions often lack the detail required for compu

applicationsarxiv-cs-lg

See the past: Time-Reversed Scene Reconstruction from Thermal Traces Using Visual Language Models

arXiv:2510.05408v2 Announce Type: replace Abstract: Recovering the past from present observations is an intriguing challenge with potential applications in forensics and scene analysis. Thermal imagin

researcharxiv-cs-cv

Selection, Not Fusion: Radar-Modulated State Space Models for Radar-Camera Depth Estimation

arXiv:2605.11840v1 Announce Type: new Abstract: Radar-camera depth estimation must turn an ultra-sparse, all-weather, metric radar signal into a dense per-pixel depth map. Existing methods -- concaten

applicationsarxiv-cs-cv

Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model

arXiv:2605.12163v1 Announce Type: new Abstract: In language reasoning, longer chains of thought consistently yield better performance, which naturally suggests that visual latent reasoning may likewis

applicationsarxiv-cs-cv

Tutorials

Smoothness Errors in Dynamics Models and How to Avoid Them

arXiv:2602.05352v2 Announce Type: replace Abstract: Modern neural networks have shown promise for solving partial differential equations over surfaces, often by discretizing the surface as a mesh and

tutorialsarxiv-cs-lg

TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusion

arXiv:2602.22586v2 Announce Type: replace-cross Abstract: Synthetic tabular data generation has attracted growing attention due to its importance for data augmentation, foundation models, and privacy.

applicationsarxiv-cs-cl

Transferable Delay-Aware Reinforcement Learning via Implicit Causal Graph Modeling

arXiv:2605.12312v1 Announce Type: new Abstract: Random delays weaken the temporal correspondence between actions and subsequent state feedback, making it difficult for agents to identify the true prop

safetyarxiv-cs-lg

Vision2Code: A Multi-Domain Benchmark for Evaluating Image-to-Code Generation

model-releasesarxiv-cs-cv

arXiv:2605.11307v1 Announce Type: new Abstract: Image-to-code generation tests whether a vision-language model (VLM) can recover the structure of an image enough to express it as executable code. Exis

ZeroIDIR: Zero-Reference Illumination Degradation Image Restoration with Perturbed Consistency Diffusion Models

arXiv:2605.11435v1 Announce Type: new Abstract: In this paper, we propose a zero-reference diffusion-based framework, named ZeroIDIR, for illumination degradation image restoration, which decouples th

safetyarxiv-cs-cv

AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting

arXiv:2605.10239v1 Announce Type: new Abstract: This work explores a simple yet powerful lightweight adapter design for feed-forward 3D Gaussian Splatting (3DGS). Existing methods typically apply comp

researcharxiv-cs-cv

An Integrative Genome-Scale Metabolic Modeling and Machine Learning Framework for Predicting and Optimizing Single-Cell Protein Production in Saccharomyces cerevisiae

arXiv:2603.25561v2 Announce Type: replace Abstract: Saccharomyces cerevisiae is increasingly recognised as a key source for single-cell protein (SCP) production, a rising solution to global protein-su

applicationsarxiv-cs-lg

AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models

arXiv:2603.10126v2 Announce Type: replace-cross Abstract: We propose a standalone autoregressive (AR) Action Expert that generates actions as a continuous causal sequence while conditioning on refresh

Can LLMs Predict Polymer Physics Just by Reading Synthesis and Processing Prose?

arXiv:2605.08255v1 Announce Type: cross Abstract: Can large language models predict physical and mechanical polymer properties simply by reading unstructured scientific prose? Polymer performance is r

Decentralized Conformal Novelty Detection via Quantized Model Exchange

arXiv:2605.08263v1 Announce Type: cross Abstract: This work studies decentralized novelty detection with global false discovery rate (FDR) control across heterogeneous composite null distributions, wi

researcharxiv-cs-lg

Deep Dreams Are Made of This: Visualizing Monosemantic Features in Diffusion Models

arXiv:2605.08218v1 Announce Type: cross Abstract: This paper proposes latent visualization by optimization (LVO), a mechanistic interpretability technique that extends feature visualization by optimiz

researcharxiv-cs-cv

Detecting Multi-Agent Collusion Through Multi-Agent Interpretability

arXiv:2604.01151v2 Announce Type: replace Abstract: As LLM agents are increasingly deployed in multi-agent systems, they introduce risks of covert coordination that may evade standard forms of human o

Deterministic Differentiable Structured Pruning for Large Language Models

arXiv:2603.08065v2 Announce Type: replace-cross Abstract: Structured pruning reduces LLM inference cost by removing low-importance architectural components. This can be viewed as learning a multiplica

researcharxiv-cs-cl

DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding

model-releasesarxiv-cs-cl

arXiv:2605.08888v1 Announce Type: new Abstract: Evaluating whether Multimodal Large Language Models can produce trustworthy, verifiable reasoning over long, visually rich documents requires evaluation

Hardware

Efficient Dataset Distillation for Pre-Trained Self-Supervised Models via Statistical Flow Matching

arXiv:2602.05391v2 Announce Type: replace Abstract: Dataset distillation seeks to synthesize a highly compact dataset that achieves performance comparable to the original dataset on downstream tasks.

hardwarearxiv-cs-cv

Elite Polarization in European Parliamentary Speeches: a Novel Measurement Approach Using Large Language Models

arXiv:2507.06658v2 Announce Type: replace-cross Abstract: Theories of democratic stability, populism, and party-system crisis often point to a form of polarization that comparative research rarely mea

applicationsarxiv-cs-ai

ERIS: Enhancing Privacy and Scalability in Federated Learning via Federated Shard Aggregation

arXiv:2602.08617v2 Announce Type: replace Abstract: Scaling Federated Learning (FL) to billion-parameter models forces a challenging trade-off between privacy, scalability, and model utility. Existing

Evading Visual Aphasia: Contrastive Adaptive Semantic Token Pruning for Vision-Language Models

arXiv:2605.09429v1 Announce Type: cross Abstract: Are low-attention visual tokens truly redundant in vision-language reasoning? Existing pruning methods often assume so, ranking visual tokens by shall

EverydayMMQA: A Multilingual and Multimodal Framework for Culturally Grounded Spoken Visual QA

arXiv:2510.06371v2 Announce Type: replace-cross Abstract: Large-scale multimodal models achieve strong results on tasks like Visual Question Answering (VQA), but they are often limited when queries re

Exploring the AI Obedience: Why is Generating a Pure Color Image Harder than CyberPunk?

arXiv:2603.00166v2 Announce Type: replace-cross Abstract: Recent advances in generative AI have shown human-level performance in complex content creation. However, we identify a 'Paradox of Simplicity

Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling

model-releasesarxiv-cs-cl

arXiv:2512.02010v5 Announce Type: replace Abstract: As large language models have grown larger, interest has grown in low-precision numerical formats such as NVFP4 as a way to improve speed and reduce

From Passive Reuse to Active Reasoning: Grounding Large Language Models for Neuro-Symbolic Experience Replay

arXiv:2605.09419v1 Announce Type: new Abstract: While experience replay is essential for data efficiency in reinforcement learning (RL), standard methods treat the replay buffer as a passive memory sy

safetyarxiv-cs-ai

Functional Stable Model Semantics and Answer Set Programming Modulo Theories

arXiv:2605.09524v1 Announce Type: new Abstract: Recently there has been an increasing interest in incorporating ``intensional'' functions in answer set programming. Intensional functions are those who