Search: “models”

Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs

model-releasesarxiv-cs-cv

arXiv:2605.04903v1 Announce Type: cross Abstract: Large language models (LLMs) show strong potential for neural architecture generation, yet existing approaches produce complete model implementations

Safety

FairEnc: A Fair Vision-Language Model with Fair Vision and Text Encoders for Glaucoma Detection

DGX agent

arXiv:2605.04882v1 Announce Type: new Abstract: Automated glaucoma detection is critical for preventing irreversible vision loss and reducing the burden on healthcare systems. However, ensuring fairne

safetyarxiv-cs-cv

7 May 2026

IDRBench: Understanding the Capability of Large Language Models on Interdisciplinary Research

arXiv:2507.15736v2 Announce Type: replace Abstract: Innovation is a key driving force of human civilization. As the body of knowledge has grown considerably, bridging knowledge across different discip

Low-Latency Quasi-Static Modeling of UAV Tether Aerodynamics

arXiv:2512.22588v3 Announce Type: replace Abstract: One of the main limitations of multirotor UAVs is their short flight time due to battery constraints. A practical solution for continuous operation

applicationsarxiv-cs-ro

OPENJ: A Conceptual Framework for Open-Source Digital Human Modeling and Ergonomic Assessment in a CAD Environment

arXiv:2605.04270v1 Announce Type: cross Abstract: Industrial workplace challenges range from musculoskeletal disorders -- a leading cause of occupational injury -- to suboptimal workstation layouts, i

researcharxiv-cs-ro

The Pinocchio Dimension: Phenomenality of Experience as the Primary Axis of LLM Psychometric Differences

arXiv:2605.05080v1 Announce Type: new Abstract: We administer 45 validated psychometric questionnaires to 50 large language models (LLMs) to identify the dimensions along which LLMs differ psychometri

AfriVox-v2: A Domain-Verticalized Benchmark for In-the-Wild African Speech Recognition

arXiv:2605.03590v1 Announce Type: new Abstract: Recent large language models (LLMs) show strong speech recognition and translation capabilities for high-resource languages. However, African languages

Agentic AI-Based Joint Computing and Networking via Mixture of Experts and Large Language Models

arXiv:2605.02911v1 Announce Type: new Abstract: Future sixth-generation (6G) mobile networks are envisioned to be equipped with a diverse set of powerful, yet highly specialized, optimization experts.

Can Blockchains Reliably Train Machine Learning Models?

arXiv:2307.07066v2 Announce Type: replace-cross Abstract: Large proof of work (PoW) networks allow anyone to earn rewards by running computation-intensive hash puzzles for profit, yet they typically c

CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing

arXiv:2605.02910v1 Announce Type: cross Abstract: Recent advances in large language models have led to strong performance on reasoning and environment-interaction tasks, yet their ability for creative

Driving Style Recognition Like an Expert Using Semantic Privileged Information from Large Language Models

arXiv:2508.13881v2 Announce Type: replace Abstract: Existing driving style recognition systems largely depend on low-level sensor-derived features for training, neglecting the rich semantic reasoning

applicationsarxiv-cs-ro

EQUITRIAGE: A Fairness Audit of Gender Bias in LLM-Based Emergency Department Triage

arXiv:2605.03998v1 Announce Type: new Abstract: Emergency department triage assigns patients an acuity score that determines treatment priority, and clinical evidence documents persistent gender dispa

InsTraj: Instructing Diffusion Models with Travel Intentions to Generate Real-world Trajectories

arXiv:2604.04106v2 Announce Type: replace Abstract: The generation of realistic and controllable GPS trajectories is a fundamental task for applications in urban planning, mobility simulation, and pri

applicationsarxiv-cs-ai

Metadata, Wavelet, and Time Aware Diffusion Models for Satellite Image Super Resolution

arXiv:2506.23566v2 Announce Type: replace Abstract: The acquisition of high-resolution satellite imagery is often constrained by the spatial and temporal limitations of satellite sensors, as well as t

researcharxiv-cs-cv

Poly-EPO: Training Exploratory Reasoning Models

arXiv:2604.17654v3 Announce Type: replace Abstract: Exploration is a cornerstone of learning from experience: it enables agents to find solutions to complex problems, generalize to novel ones, and sca

safetyarxiv-cs-ai

Pretrained Model Representations as Acquisition Signals for Active Learning of MLIPs

arXiv:2605.03964v1 Announce Type: new Abstract: Training machine learning interatomic potentials (MLIPs) for reactive chemistry is often bottlenecked by the high cost of quantum chemical labels and th

Agents

Quantifying the human visual exposome with vision language models

arXiv:2605.03863v1 Announce Type: cross Abstract: The visual environment is a fundamental yet unquantified determinant of mental health. While the concept of the environmental exposome is well establi

agentsarxiv-cs-cv

The Counterexample Game: Iterated Conceptual Analysis and Repair in Language Models

arXiv:2605.03936v1 Announce Type: new Abstract: Conceptual analysis -- proposing definitions and refining them through counterexamples -- is central to philosophical methodology. We study whether lang

Adversarial Update-Based Federated Unlearning for Poisoned Model Recovery

arXiv:2605.02110v1 Announce Type: new Abstract: Federated learning (FL) is vulnerable to poisoning attacks, where malicious clients upload manipulated updates to degrade the performance of the global

Beyond Perplexity: Character Distribution Signatures and the MDTA Benchmark for AI Text Detection

arXiv:2605.01647v1 Announce Type: new Abstract: Training-free AI text detection methods primarily rely on model log-probabilities, achieving strong performance through approaches like Binoculars and D

Binary Rewards and Reinforcement Learning: Fundamental Challenges

arXiv:2605.02375v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a standard approach for improving reasoning in language models, yet models trained with

Combining Trained Models in Reinforcement Learning

arXiv:2605.02159v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) has delivered strong results in domains such as Atari and Go, but it still suffers from high sample cost and weak tran

Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech Detection

arXiv:2509.00673v2 Announce Type: replace Abstract: We investigate the efficacy of Large Language Models (LLMs) in detecting implicit and explicit hate speech, examining how models with minimal safety

safetyarxiv-cs-cl

Distributional Causal Mediation via Conditional Generative Modeling

arXiv:2605.01765v1 Announce Type: cross Abstract: Mediation analysis has traditionally focused on outcome-level summary contrasts, such as mean effects, which may obscure substantial distributional ch

applicationsarxiv-cs-lg

FedPLT: Scalable, Resource-Efficient, and Heterogeneity-Aware Federated Learning via Partial Layer Training

model-releasesarxiv-cs-lg

arXiv:2605.02337v1 Announce Type: cross Abstract: Federated Learning (FL) has gained significant attention in distributed machine learning by enabling collaborative model training across decentralized

Fine-Tuning Pre-Trained Code Models for AI-Generated Code Detection

arXiv:2605.01596v1 Announce Type: new Abstract: This paper describes the system submitted by team extbf{Archaeology} to SemEval-2026 Task~13 on AI-generated code detection. The shared task consists of

Local Ai

Heterogeneous Model Fusion for Privacy-Aware Multi-Camera Surveillance via Synthetic Domain Adaptation

arXiv:2605.02169v1 Announce Type: new Abstract: We propose HeroCrystal, a novel privacy-preserving framework for multi-camera domain-adaptive object detection, addressing challenges such as data priva

local-aiarxiv-cs-cv

Interpretable experiential learning based on state history and global feedback

model-releasesarxiv-cs-lg

arXiv:2605.00940v1 Announce Type: new Abstract: A new interpretable experiential learning model based on state history and global feedback is presented. It is capable of learning a behavioral model re

Agents

Optimizing Trajectory-Trees in Belief Space: An Application from Model Predictive Control to Task and Motion Planning

arXiv:2605.01860v1 Announce Type: new Abstract: This paper explores the benefits of computing arborescent trajectories (trajectory-trees) instead of commonly used sequential trajectories for partially

agentsarxiv-cs-ro

Single Image Defogging Using a Fourth-Order Telegraph PDE Guided by Physical Haze Modeling

arXiv:2605.00878v1 Announce Type: new Abstract: In real-world scenarios, image defogging is an inverse problem due to unknown scene depth, atmospheric scattering, and the common absence of ground trut

applicationsarxiv-cs-cv

SpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma Selection

arXiv:2605.02888v1 Announce Type: cross Abstract: Speculative decoding accelerates large language model (LLM) inference by using a small draft model to propose candidate tokens that a larger target mo

The 2026 ACII Dyadic Conversations (DaiKon) Workshop & Challenge

arXiv:2605.02672v1 Announce Type: cross Abstract: The 2026 ACII Dyadic Conversations (ACII-DaiKon) Workshop & Challenge introduces a benchmark for modeling interpersonal affect and social dynamics in

Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL

model-releasesarxiv-cs-lg

arXiv:2504.15077v5 Announce Type: replace Abstract: Large Language Models (LLMs) can translate natural language into SQL, but small models struggle with multi-table and complex queries in Zero-Shot Le

TIJERE: A Novel Threat Intelligence Joint Extraction Model Based on Analyst Expert Knowledge

arXiv:2605.02041v1 Announce Type: new Abstract: The extraction of entities and relationships from threat intelligence reports into structured formats, such as cybersecurity knowledge graphs, is essent

applicationsarxiv-cs-lg

When Attention Collapses: Residual Evidence Modeling for Compositional Inference

arXiv:2605.02323v1 Announce Type: new Abstract: Compositional inference - the decomposition of observations into an unknown number of latent components - is central to perception and scientific data a

Adaptive Dual-Teacher Distillation with Subnetwork Rectification for Bridging Semantic Gaps in Black-Box Domain Adaptation

model-releasesarxiv-cs-cv

arXiv:2603.22908v3 Announce Type: replace Abstract: Assuming that neither source data nor source model parameters are accessible, black-box domain adaptation (BBDA) represents a highly practical yet c

Adaptive Equilibrium: Dynamic Weighting Framework for Generalized Interruption of DeepFake Models

arXiv:2605.00443v1 Announce Type: cross Abstract: The advancement of generalized deepfake disruption is constrained by the interruption imbalance, a fundamental bottleneck inherent to the generation o

safetyarxiv-cs-cv

Tutorials

Advancing Edge Classification through High-Dimensional Causal Modeling of Node-Edge Interplay

arXiv:2605.00374v1 Announce Type: new Abstract: Edge classification, a crucial task for graph applications, remains relatively under-explored compared to link prediction. Current methods often overloo

tutorialsarxiv-cs-lg

How Language Models Process Out-of-Distribution Inputs: A Two-Pathway Framework

arXiv:2605.00269v1 Announce Type: new Abstract: Recent white-box OOD detection methods for LLMs -- including CED, RAUQ, and WildGuard confidence scores -- appear effective, but we show they are struct

safetyarxiv-cs-cl

Knowing When to Defer: Selective Prediction for Responsible Knowledge Tracing

arXiv:2509.21514v3 Announce Type: replace-cross Abstract: Research on Knowledge Tracing (KT) models traditionally focuses on improving predictive accuracy. However, responsible real-world deployment r

Learning from Supervision with Semantic and Episodic Memory: A Reflective Approach to Agent Adaptation

arXiv:2510.19897v2 Announce Type: replace Abstract: We investigate how agents built on pretrained large language models (LLMs) can learn target classification functions from labeled examples without p

Leveraging Vision-Language Models as Weak Annotators in Active Learning

arXiv:2605.00480v1 Announce Type: new Abstract: Active learning aims to reduce annotation cost by selectively querying informative samples for supervision under a limited labeling budget. In this work

researcharxiv-cs-cv

Score-based Greedy Search for Structure Identification of Partially Observed Linear Causal Models

arXiv:2510.04378v2 Announce Type: replace Abstract: Identifying the structure of a partially observed causal system is essential to various scientific fields. Recent advances have focused on constrain

Industry

We fine-tuned Alec Radford’s 1930 vintage LLM to solve SWE-bench issues. After just ‼️250‼️ training examples, the model solves its first is…

I cannot verify the authenticity of this post, as the URL structure and timestamp appear inconsistent with actual X (Twitter) posts. The claim about fine-tuning a '1930 vintage LLM' is anachronistic,

industryemad-mostaque--x

2 May 2026

Binary Spiking Neural Networks as Causal Models

arXiv:2604.27007v1 Announce Type: new Abstract: We provide a causal analysis of Binary Spiking Neural Networks (BSNNs) to explain their behavior. We formally define a BSNN and represent its spiking ac

researcharxiv-cs-ai

BrainDINO: A Brain MRI Foundation Model for Generalizable Clinical Representation Learning

arXiv:2604.27277v1 Announce Type: cross Abstract: Brain MRI underpins a wide range of neuroscientific and clinical applications, yet most learning-based methods remain task-specific and require substa

researcharxiv-cs-ai

Local Ai

Can Tabular Foundation Models Guide Exploration in Robot Policy Learning?

arXiv:2604.27667v1 Announce Type: cross Abstract: Policy optimization in high-dimensional continuous control for robotics remains a challenging problem. Predominant methods are inherently local and of

local-aiarxiv-cs-lg

CodeBrain: Bridging Decoupled Tokenizer and Multi-Scale Architecture for EEG Foundation Model

arXiv:2506.09110v3 Announce Type: replace Abstract: Electroencephalography (EEG) provides real-time insights into brain activity and supports diverse applications in neuroscience. While EEG foundation