AI News — Latest Developments & Breakthroughs

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Explainable embeddings with Distance Explainer

arXiv:2505.15516v2 Announce Type: replace-cross Abstract: While eXplainable AI (XAI) has advanced significantly, few methods address interpretability in embedde

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised Reasoning

arXiv:2505.16950v4 Announce Type: replace-cross Abstract: Transformer LLMs have been shown to exhibit strong reasoning ability that scales with inference-time c

ArXiv cs.AI 👁️ Computer Vision 📄 Paper ⚡ AI Lesson 6d ago

RestoreVAR: Visual Autoregressive Generation for All-in-One Image Restoration

arXiv:2505.18047v3 Announce Type: replace-cross Abstract: The use of latent diffusion models (LDMs) such as Stable Diffusion has significantly improved the perc

ArXiv cs.AI 👁️ Computer Vision 📄 Paper ⚡ AI Lesson 6d ago

Wideband RF Radiance Field Modeling Using Frequency-embedded 3D Gaussian Splatting

arXiv:2505.20714v3 Announce Type: replace-cross Abstract: Indoor environments typically contain diverse RF signals distributed across multiple frequency bands,

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Reward Is Enough: LLMs Are In-Context Reinforcement Learners

arXiv:2506.06303v5 Announce Type: replace-cross Abstract: Reinforcement learning (RL) is a framework for solving sequential decision-making problems. In this wo

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Enhancing Jailbreak Attacks on LLMs via Persona Prompts

arXiv:2507.22171v3 Announce Type: replace-cross Abstract: Jailbreak attacks aim to exploit large language models (LLMs) by inducing them to generate harmful con

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communication

arXiv:2508.11733v3 Announce Type: replace-cross Abstract: LLM-based multi-agent systems exhibit strong collaborative capabilities but often suffer from redundan

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 6d ago

Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting

arXiv:2509.14181v4 Announce Type: replace-cross Abstract: Although contrastive and other representation-learning methods have long been explored in vision and N

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

PromptLoop: Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment

arXiv:2510.00430v2 Announce Type: replace-cross Abstract: Despite recent progress, reinforcement learning (RL)-based fine-tuning of diffusion models often strug

ArXiv cs.AI 📄 Paper ⚡ AI Lesson 6d ago

Fiaingen: A financial time series generative method matching real-world data quality

arXiv:2510.01169v2 Announce Type: replace-cross Abstract: Data is vital in enabling machine learning models to advance research and practical applications in fi

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

From Imperative to Declarative: Towards LLM-friendly OS Interfaces for Boosted Computer-Use Agents

arXiv:2510.04607v2 Announce Type: replace-cross Abstract: Computer-use agents (CUAs) powered by large language models (LLMs) have emerged as a promising approac

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

You only need 4 extra tokens: Synergistic Test-time Adaptation for LLMs

arXiv:2510.10223v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed in specialized domains such as finance, medicin

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

From Prompts to Packets: A View from the Network on ChatGPT, Copilot, and Gemini

arXiv:2510.11269v2 Announce Type: replace-cross Abstract: GenAI chatbots are now pervasive in digital ecosystems, fundamentally reshaping user interactions over

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries

arXiv:2510.14751v2 Announce Type: replace-cross Abstract: Next-token prediction (NTP) has driven the success of large language models (LLMs), but it struggles w

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

OffSim: Offline Simulator for Model-based Offline Inverse Reinforcement Learning

arXiv:2510.15495v2 Announce Type: replace-cross Abstract: Reinforcement learning algorithms typically utilize an interactive simulator (i.e., environment) with

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Is Multilingual LLM Watermarking Truly Multilingual? Scaling Robustness to 100+ Languages via Back-Translation

arXiv:2510.18019v2 Announce Type: replace-cross Abstract: Multilingual watermarking aims to make large language model (LLM) outputs traceable across languages,

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

QUARK: Quantization-Enabled Circuit Sharing for Transformer Acceleration by Exploiting Common Patterns in Nonlinear Operations

arXiv:2511.06767v2 Announce Type: replace-cross Abstract: Transformer-based models have revolutionized computer vision (CV) and natural language processing (NLP

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Uncertainty Makes It Stable: Curiosity-Driven Quantized Mixture-of-Experts

arXiv:2511.11743v3 Announce Type: replace-cross Abstract: Deploying deep neural networks on resource-constrained devices faces two critical challenges: maintain

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Reward Engineering for Spatial Epidemic Simulations: A Reinforcement Learning Platform for Individual Behavioral Learning

arXiv:2511.18000v2 Announce Type: replace-cross Abstract: We present ContagionRL, a Gymnasium-compatible reinforcement learning platform specifically designed f

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation

arXiv:2511.18281v3 Announce Type: replace-cross Abstract: Diffusion models (DMs) produce high-quality images, yet their sampling remains costly when adapted to

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

E0: Enhancing Generalization and Fine-Grained Control in VLA Models via Tweedie Discrete Diffusion

arXiv:2511.21542v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models offer a unified framework for robotic manipulation by integrating

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Goal-Oriented Multi-Agent Semantic Networking: Unifying Intents, Semantics, and Intelligence

arXiv:2512.01035v2 Announce Type: replace-cross Abstract: 6G services are evolving toward goal-oriented and AI-native communication, which are expected to deliv

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

From Panel to Pixel: Zoom-In Vision-Language Pretraining from Biomedical Scientific Literature

arXiv:2512.02566v2 Announce Type: replace-cross Abstract: There is a growing interest in developing strong biomedical vision-language models. A popular approach

ArXiv cs.AI 🧠 Large Language Models 📄 Paper ⚡ AI Lesson 6d ago

Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding

arXiv:2512.04000v2 Announce Type: replace-cross Abstract: The application of Large Multimodal Models (LMMs) to long-form video understanding is constrained by l

⚡ AI-Lesson Articles