arXiv:2608.21995v1 Announce Type: cross Abstract: We propose Variance Driven Exploration (VarDE), a principled approach for pure exploration in highly…
Category: AI
Bulbul: A Dataset for Dialectal Arabic Speech Recognition
arXiv:2608.21950v1 Announce Type: cross Abstract: Arabic automatic speech recognition (ASR) faces unique challenges due to diglossia, extensive regional…
EDGE: Experience-Distillation for Guided Exploration in Agentic Reinforcement Learning
arXiv:2608.21946v1 Announce Type: cross Abstract: Reinforcement learning with outcome-based objectives such as GRPO enables LLM-based agents to solve…
Bi-EZP: LLM-Guided Bilevel Program Evolution for Ensemble Zero-Cost Proxy Discovery
arXiv:2608.21927v1 Announce Type: cross Abstract: Zero-cost proxies enable neural architecture search (NAS) to rank candidate networks from statistics…
Google Research Introduces ME-POIs: A Mobility-Informed Framework that Adds “How a Place Is Used” to Text-Based POI Embeddings
framework that folds aggregate human movement into text-based place embeddings. Language models describe what a place is; they miss how it is used.…
NoTB: Oracle-Free Triage of LLM-Generated RTL via Cross-Model Formal Consensus
arXiv:2608.21962v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to generate register-transfer-level (RTL) designs…
How to Leverage Local Small Language Models for Your Projects
A practical guide to running compact, privacy-preserving language models on your own hardware for faster, cheaper, and more controllable AI-powered…
Breaking the Assumptions: Auditing Input-Side Jailbreak Defenses Against Semantic Attacks
arXiv:2608.21895v1 Announce Type: cross Abstract: Locally deployed Large Language Models (LLMs) via inference engines such as Ollama run without the…
GuardPaint:SpeculativeSafetyDecodingforText-to-ImageGeneration
arXiv:2608.21869v1 Announce Type: cross Abstract: Text-to-image (T2I) diffusion models offer powerful visual generation, but their controllability creates…
HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning
arXiv:2608.21863v1 Announce Type: cross Abstract: Tool-Integrated Reasoning (TIR) is a fundamental capability for LLM agents to solve complex tasks by…