SABlock: Semantic-Aware KV Cache Eviction with Adaptive Compression Block Size
arxiv.org·13h
📄Text Chunking
Flag this post
Leveraging Large Language Models to Identify Conversation Threads in Collaborative Learning
arxiv.org·13h
🔍Information Retrieval
Flag this post
Exploration through Generation: Applying GFlowNets to Structured Search
arxiv.org·13h
🕸️Graph Embeddings
Flag this post
Diagnosing Bottlenecks in Data Visualization Understanding by Vision-Language Models
arxiv.org·13h
🌀Differential Geometry
Flag this post
Tractable Shapley Values and Interactions via Tensor Networks
arxiv.org·13h
🕸️Tensor Networks
Flag this post
Adaptive Dual Prompting: Hierarchical Debiasing for Fairness-aware Graph Neural Networks
arxiv.org·13h
🎛️Feed Filtering
Flag this post
Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning
arxiv.org·13h
🔗Parser Combinators
Flag this post
FastJAM: a Fast Joint Alignment Model for Images
arxiv.org·13h
🌀Hyperbolic Geometry
Flag this post
GRAD: Real-Time Gated Recurrent Anomaly Detection in Autonomous Vehicle Sensors Using Reinforced EMA and Multi-Stage Sliding Window Techniques
arxiv.org·13h
🧠Machine Learning
Flag this post
Is Temporal Difference Learning the Gold Standard for Stitching in RL?
arxiv.org·13h
🧠Machine Learning
Flag this post
The Mirror Loop: Recursive Non-Convergence in Generative Reasoning Systems
arxiv.org·13h
🔗Parser Combinators
Flag this post
Framework for Machine Evaluation of Reasoning Completeness in Large Language Models For Classification Tasks
arxiv.org·13h
🧠Intelligence Compression
Flag this post
Part 1: Training a Neural Network to Detect Coffee First Crack from Audio - An Agentic Development Journey with Warp
🔍FLAC Forensics
Flag this post
Direct Debiased Machine Learning via Bregman Divergence Minimization
arxiv.org·13h
🧠Machine Learning
Flag this post
The Hallelujah Algorithm
🎨Graph Coloring
Flag this post
Block-Diagonal LoRA for Eliminating Communication Overhead in Tensor Parallel LoRA Serving
arxiv.org·13h
💻Local LLMs
Flag this post
Building a Monitoring System That Actually Works
towardsdatascience.com·23h
👁️Observatory Systems
Flag this post
Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
arxiv.org·13h
💻Local LLMs
Flag this post
The Principles of Diffusion Models
arxiv.org·13h
🧠Machine Learning
Flag this post
Loading...Loading more...