📰 Reads

93,110 articles · Updated every 3 hours

arXiv:2509.18127v3 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) enable interpretability research by decomposing entangled model activations

ArXiv cs.AI 📄 Paper 3h ago

DyBBT: Dynamic Balance via Bandit-inspired Targeting for Dialog Policy with Cognitive Dual-Systems

arXiv:2509.19695v3 Announce Type: replace-cross Abstract: Task oriented dialog systems often rely on static exploration strategies that do not adapt to dynamic

ArXiv cs.AI 📄 Paper 3h ago

HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST

arXiv:2509.19742v4 Announce Type: replace-cross Abstract: Zero-shot Dialog State Tracking (zs-DST) is essential for enabling Task-Oriented Dialog Systems (TODs)

ArXiv cs.AI 📄 Paper 3h ago

SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From

arXiv:2509.26404v2 Announce Type: replace-cross Abstract: Fingerprinting Large Language Models (LLMs)is essential for provenance verification and model attribut

ArXiv cs.AI 📄 Paper 3h ago

Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-Level Physics Problem Solving

arXiv:2510.00919v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) with foundation models has achieved strong performance across div

ArXiv cs.AI 📄 Paper 3h ago

LLM as Attention-Informed NTM and Topic Modeling as long-input Generation: Interpretability and long-Context Capability

arXiv:2510.03174v2 Announce Type: replace-cross Abstract: Topic modeling aims to produce interpretable topic representations and topic--document correspondences

ArXiv cs.AI 📄 Paper 3h ago

Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain

arXiv:2510.05159v4 Announce Type: replace-cross Abstract: While finetuning AI agents on interaction data -- such as web browsing or tool use -- improves their c

ArXiv cs.AI 📄 Paper 3h ago

GTCN-G: A Residual Graph-Temporal Fusion Network for Imbalanced Intrusion Detection

arXiv:2510.07285v3 Announce Type: replace-cross Abstract: The escalating complexity of network threats and the inherent class imbalance in traffic data present

ArXiv cs.AI 📄 Paper 3h ago

Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following

arXiv:2510.14420v4 Announce Type: replace-cross Abstract: Language models often struggle to follow multi-constraint instructions that are crucial for real-world

ArXiv cs.AI 📄 Paper 3h ago

StableSketcher: Enhancing Diffusion Model for Pixel-based Sketch Generation via Visual Question Answering Feedback

arXiv:2510.20093v2 Announce Type: replace-cross Abstract: Although recent advancements in diffusion models have significantly enriched the quality of generated

ArXiv cs.AI 📄 Paper 3h ago

Why Did Apple Fall: Evaluating Curiosity in Large Language Models

arXiv:2510.20635v2 Announce Type: replace-cross Abstract: Curiosity serves as a pivotal conduit for human beings to discover and learn new knowledge. Recent adv

ArXiv cs.AI 📄 Paper 3h ago

FaCT: Faithful Concept Traces for Explaining Neural Network Decisions

arXiv:2510.25512v2 Announce Type: replace-cross Abstract: Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global con

ArXiv cs.AI 📄 Paper 3h ago

Generative Modeling Enables Molecular Structure Retrieval from Coulomb Explosion Imaging

arXiv:2511.00179v2 Announce Type: replace-cross Abstract: Capturing the structural changes that molecules undergo during chemical reactions in real space and ti

ArXiv cs.AI 📄 Paper 3h ago

Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compression

arXiv:2511.06424v2 Announce Type: replace-cross Abstract: While zero-shot diffusion-based compression methods have seen significant progress in recent years, th

ArXiv cs.AI 📄 Paper 3h ago

Reasoning about Intent for Ambiguous Requests

arXiv:2511.10453v3 Announce Type: replace-cross Abstract: Large language models often respond to ambiguous requests by implicitly committing to one interpretati

ArXiv cs.AI 📄 Paper 3h ago

GeoPl@ntNet: A Platform for Exploring Essential Biodiversity Variables

arXiv:2511.13790v2 Announce Type: replace-cross Abstract: This paper describes GeoPl@ntNet, an interactive web application designed to make Essential Biodiversi

ArXiv cs.AI 📄 Paper 3h ago

HiFiNet: Hierarchical Fault Identification in Wireless Sensor Networks via Edge-Based Classification and Graph Aggregation

arXiv:2511.17537v2 Announce Type: replace-cross Abstract: Wireless Sensor Networks (WSN) are the backbone of essential monitoring applications, but their deploy

ArXiv cs.AI 📄 Paper 3h ago

CropVLM: Learning to Zoom for Fine-Grained Vision-Language Perception

arXiv:2511.19820v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) often struggle with tasks that require fine-grained image understanding,

ArXiv cs.AI 📄 Paper 3h ago

Hybrid-AIRL: Enhancing Inverse Reinforcement Learning with Supervised Expert Guidance

arXiv:2511.21356v2 Announce Type: replace-cross Abstract: Adversarial Inverse Reinforcement Learning (AIRL) has shown promise in addressing the sparse reward pr

ArXiv cs.AI 📄 Paper 3h ago

BINDER: Instantly Adaptive Mobile Manipulation with Open-Vocabulary Commands

arXiv:2511.22364v2 Announce Type: replace-cross Abstract: Open-vocabulary mobile manipulation (OVMM) requires robots to follow language instructions, navigate,

ArXiv cs.AI 📄 Paper 3h ago

Red Teaming Large Reasoning Models

arXiv:2512.00412v4 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, of

ArXiv cs.AI 📄 Paper 3h ago

Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices

arXiv:2512.06443v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed on edge devices. To meet strict resource constr

ArXiv cs.AI 📄 Paper 3h ago

INFORM-CT: INtegrating LLMs and VLMs FOR Incidental Findings Management in Abdominal CT

arXiv:2512.14732v2 Announce Type: replace-cross Abstract: Incidental findings in CT scans, though often benign, can have significant clinical implications and s

ArXiv cs.AI 📄 Paper 3h ago

Revisiting the Reliability of Language Models in Instruction-Following

arXiv:2512.14754v2 Announce Type: replace-cross Abstract: Advanced LLMs have achieved near-ceiling instruction-following accuracy on benchmarks such as IFEval.