Search: “models”

PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization

arXiv:2605.03129v1 Announce Type: cross Abstract: Browsing-enabled LLM assistants can fetch webpages and answer contact-seeking queries, creating a practical channel for scraping contact-style persona

Model Releases

Retrieval and Multi-Hop Reasoning in 1M-Token Context Windows: Evaluating LLMs on Classical Chinese Text

DGX agent

arXiv:2605.02173v1 Announce Type: new Abstract: We evaluate the long-context retrieval and reasoning capabilities of five frontier large language models with advertised 1M-token context windows on a c

model-releasesarxiv-cs-ai

6 May 2026

small workflow note that adds up. /staged-pr is a skill (via slash command) i run when wrapping up a PR. it takes my staged code changes and…

small workflow note that adds up. /staged-pr is a skill (via slash command) i run when wrapping up a PR. it takes my staged code changes and drafts a concise PR title & description, based on my prefer

agentsharrison-chase--x

TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization

arXiv:2605.01418v1 Announce Type: new Abstract: Time-series generative models often lack control over temporal granularity, forcing users to accept whatever granularity the model produces. To enable t

researcharxiv-cs-ai

WMF-AM: Probing LLM Working Memory via Depth-Parameterized Cumulative State Tracking

arXiv:2603.27343v2 Announce Type: replace Abstract: Existing large language models (LLMs) evaluations use fixed-difficulty benchmarks that cannot adapt as models improve, and rarely isolate specific c

agentsarxiv-cs-ai

Accurate Legal Reasoning at Scale: Neuro-Symbolic Offloading and Structural Auditability for Robust Legal Adjudication

arXiv:2605.02472v1 Announce Type: new Abstract: Legal texts often contain computational legal clauses--provisions whose understanding requires complex logic. While frontier Large Reasoning Models (LRM

Activation Compression in LLMs: Theoretical Analysis and Efficient Algorithm

arXiv:2605.01255v1 Announce Type: new Abstract: Training large language models (LLMs) is highly memory-intensive, as training must store not only weights and optimizer states but also intermediate act

Adoption and Use of LLMs at an Academic Medical Center

model-releasesarxiv-cs-ai

arXiv:2602.00074v2 Announce Type: replace-cross Abstract: While large language models (LLMs) can support clinical documentation needs, standalone tools struggle with 'workflow friction' from manual da

Adversarial Flow Matching for Imperceptible Attacks on End-to-End Autonomous Driving

arXiv:2605.00880v1 Announce Type: new Abstract: Autonomous driving (AD) is evolving towards end-to-end (E2E) frameworks through two primary paradigms: monolithic models exemplified by Vision-Language-

agentsarxiv-cs-cv

ATR-Bench: A Federated Learning Benchmark for Adaptation, Trust, and Reasoning

arXiv:2505.16850v2 Announce Type: replace-cross Abstract: Federated Learning (FL) has emerged as a promising paradigm for collaborative model training while preserving data privacy across decentralize

Benchmarking Retrieval Strategies for Biomedical Retrieval-Augmented Generation: A Controlled Empirical Study

arXiv:2605.02520v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) offers a well-established path to grounding large language model (LLM) outputs in external knowledge, yet the quest

Breaking the Silence: A Dataset and Benchmark for Bangla Text-to-Gloss Translation

arXiv:2504.02293v3 Announce Type: replace Abstract: Gloss is a written approximation that bridges Sign Language (SL) and its corresponding spoken language. Despite a deaf and hard-of-hearing populatio

Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts

arXiv:2605.01882v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have shown considerable potential in chart understanding and reasoning tasks. However, they still struggle with

Constructing Interpretable Features from Compositional Neuron Groups

arXiv:2506.10920v2 Announce Type: replace Abstract: A central goal for mechanistic interpretability has been to identify the right units of analysis in large language models (LLMs) that causally expla

CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features

arXiv:2508.12535v3 Announce Type: replace Abstract: Sparse Autoencoders (SAEs) can extract interpretable features from large language models (LLMs) without supervision. However, their effectiveness in

CyclicJudge: Mitigating Judge Bias Efficiently in LLM-based Evaluation

arXiv:2603.01865v3 Announce Type: replace Abstract: LLM-as-judge evaluation has become standard practice for open-ended model assessment; however, judges exhibit systematic biases that cannot be avera

DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detection

arXiv:2511.13108v3 Announce Type: replace Abstract: The rapid progress of generative models such as GANs and diffusion models has led to the widespread proliferation of AI-generated images, raising co

researcharxiv-cs-cv

ESARBench: A Benchmark for Agentic UAV Embodied Search and Rescue

model-releasesarxiv-cs-ro

arXiv:2605.01371v1 Announce Type: new Abstract: The rapid advancement of Multimodal Large Language Models (MLLMs) has empowered Unmanned Aerial Vehicle (UAV) with exceptional capabilities in spatial r

Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks

arXiv:2605.01484v1 Announce Type: new Abstract: With the rapidly improving reasoning abilities of Large Language Models (LLMs), there is also a rising demand to use them in a wide variety of domains.

everyone would have a deeper appreciation for Agent Products that rock because of great Context/Harness Engineering if they… talked to: - LL…

everyone would have a deeper appreciation for Agent Products that rock because of great Context/Harness Engineering if they… talked to: - LLM Base models - Post-Trained models with no harness (no tool

agentsharrison-chase--x

Feedback-Normalized Developer Memory for Reinforcement-Learning Coding Agents: A Safety-Gated MCP Architecture

arXiv:2605.01567v1 Announce Type: cross Abstract: Large language model (LLM) coding agents increasingly operate over repositories, terminals, tests, and execution traces across long software-engineeri

Flexi-LoRA with Input-Adaptive Ranks: Efficient Finetuning for Speech and Reasoning Tasks

arXiv:2605.01959v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning methods like Low-Rank Adaptation (LoRA) have become essential for deploying large language models, yet their static pa

Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs

arXiv:2601.22709v3 Announce Type: replace Abstract: Vision-Language Models (VLMs) achieve strong multimodal performance but are costly to deploy, and post-training quantization often causes significan

GAZE: Grounded Agentic Zero-shot Evaluation with Viewer-Level Tools and Literature Retrieval on Rare Brain MRI

arXiv:2605.00876v1 Announce Type: cross Abstract: Vision-language models (VLMs) read an image and produce text in a single forward pass, whereas radiologists typically inspect an image several times a

HalluScan: A Systematic Benchmark for Detecting and Mitigating Hallucinations in Instruction-Following LLMs

arXiv:2605.02443v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, yet they remain susceptible to

// HeavySkill // One of the cleaner takes on agentic harness design I've read. They argue that what actually drives agent harness performanc…

// HeavySkill // One of the cleaner takes on agentic harness design I've read. They argue that what actually drives agent harness performance is not the orchestration code. It's a single inner skill:

model-releasesdair-ai--x

Local Ai

High-Fidelity Mobile Avatars with Pruned Local Blendshapes

arXiv:2605.01854v1 Announce Type: new Abstract: We propose a method to reconstruct high-fidelity human avatars from multi-view video that can run on mobile devices. Many works can model high-quality G

local-aiarxiv-cs-cv

InterPhys: Physics-aware Human Motion Synthesis in a Dynamic Scene

arXiv:2605.01036v1 Announce Type: new Abstract: This paper tackles the problem of physics-aware human motion synthesis in a dynamic scene. Unlike existing works which mainly tend to generate physicall

LiteVLA-H: Dual-Rate Vision-Language-Action Inference for Onboard Aerial Guidance and Semantic Perception

arXiv:2605.00884v1 Announce Type: new Abstract: Vision-language-action (VLA) models have shown strong semantic grounding and task generalization in manipulation, but aerial deployment remains difficul

Mean-Field Path-Integral Diffusion: From Samples to Interacting Agents

model-releasesarxiv-cs-ai

arXiv:2605.00007v1 Announce Type: cross Abstract: Independent sample generation is the prevailing paradigm in modern diffusion-based generative models of AI. We ask a different question: can samples c

Meta-learning Structure-Preserving Dynamics

arXiv:2508.11205v2 Announce Type: replace Abstract: Structure-preserving approaches to dynamics discovery have demonstrated great potential for modeling physical systems due to their use of strong ind

Mextsuperscript{4}Fuse: Lightweight State-Space MoE with a Cross-Scale Gating Bridge for Brain Tumor Segmentation

arXiv:2605.02444v1 Announce Type: new Abstract: Encoder-decoder imbalance and the reliance on large input volumes make many 3D brain tumor segmentation models both compute-heavy and brittle. We presen

oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning

arXiv:2510.07731v3 Announce Type: replace-cross Abstract: Organic reaction mechanisms are the stepwise elementary reactions by which reactants form intermediates and products, and are fundamental to u

Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates

arXiv:2605.02236v1 Announce Type: cross Abstract: Recursive language-model loops often settle into recognizable attractor-like patterns. The practical question is how much injected text is needed to m

phi-Table: A Statistical Explanation for Global SHAP

arXiv:2512.07578v3 Announce Type: replace-cross Abstract: Global SHAP explanations are typically presented as feature-importance rankings, which identify variables that matter to a black-box model but

researcharxiv-cs-lg

Quaternion Nonlinear Transform-Induced Nuclear Norm for Low-Rank Tensor Completion

arXiv:2605.01467v1 Announce Type: cross Abstract: Tensor completion has emerged as a powerful framework for recovering missing data in multidimensional signals by exploiting low-rank tensor structures

RamanBench: A Large-Scale Benchmark for Machine Learning on Raman Spectroscopy

arXiv:2605.02003v1 Announce Type: new Abstract: Machine Learning (ML) has transformed many scientific fields, yet key applications still lack standardized benchmarks. Raman spectroscopy, a widely used

Real-Time Text Transmission via LLM-Based Entropy Coding over Fixed-Rate Channels

arXiv:2605.01991v1 Announce Type: cross Abstract: Learning, prediction, and compression are intimately connected: a model that accurately predicts the next symbol in a sequence can be coupled with a s

Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation

arXiv:2605.02757v1 Announce Type: new Abstract: Vision-language-action (VLA) models typically rely on large-scale real-world videos, whereas simulated data, despite being inexpensive and highly parall

Segment-Aligned Policy Optimization for Multi-Modal Reasoning

arXiv:2605.01327v1 Announce Type: cross Abstract: Existing reinforcement learning approaches for Large Language Models typically perform policy optimization at the granularity of individual tokens or

SIAM: Head and Brain MRI Segmentation from Few High-Quality Templates via Synthetic Training

arXiv:2605.02737v1 Announce Type: new Abstract: Synthetic training has recently advanced brain MRI segmentation by enabling contrast-agnostic models trained entirely on generated data. However, most e

researcharxiv-cs-cv

Social Bias in LLM-Generated Code: Benchmark and Mitigation

model-releasesarxiv-cs-ai

arXiv:2605.00382v2 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed to generate code for human-centered applications where demographic fairness is critical. Howeve

Split-on-Share: Mixture of Sparse Experts for Task-Agnostic Continual Learning

arXiv:2601.17616v2 Announce Type: replace Abstract: Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to

Submodular Benchmark Selection

arXiv:2605.02209v1 Announce Type: cross Abstract: Evaluating large language models across many benchmarks is expensive, yet many benchmarks are highly correlated. We formalize the selection of a small

SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation

arXiv:2508.15658v5 Announce Type: replace Abstract: The rapid growth of academic literature makes the manual creation of scientific surveys increasingly infeasible. While large language models show pr

Tutorials

Time-series forecasting through the lens of dynamics

arXiv:2507.15774v2 Announce Type: replace Abstract: While deep learning is facing an homogenization across modalities led by Transformers, they are still challenged by shallow linear models in the tim

tutorialsarxiv-cs-lg

Safety

Toward a Scientific Discovery Engine for Weather and Climate Data: A Visual Analytics Workbench for Embedding-Based Exploration

arXiv:2605.00972v1 Announce Type: cross Abstract: Earth system science is producing increasingly large, high-dimensional datasets from physics based Earth system models to AI-based weather and climate

safetyarxiv-cs-cv

Unsupervised full-field Bayesian inference of orthotropic hyperelasticity from a single biaxial test: a myocardial case study

arXiv:2510.09498v3 Announce Type: replace-cross Abstract: Cardiac muscle tissue exhibits highly non-linear hyperelastic and orthotropic material behavior during passive deformation. Traditional consti