All Articles
16523 articles total
CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation
CompilerKV introduces risk-adaptive KV compression that compiles retention policies offline, significantly reducing memory overhead for long-context LLMs.
Fly0: Persistent Metric Anchoring for Zero-Shot Aerial Vision-Language Navigation
Fly0 decouples semantic reasoning from geometric planning to enable zero-shot aerial vision-language navigation for drones in unstructured environments.
When Visual Evidence is Ambiguous: Pareidolia as a Diagnostic Probe for Vision Models
A study using face pareidolia as a diagnostic probe reveals that Vision-Language Models often over-interpret ambiguous patterns as human faces compared to specialized detectors.
Give Them an Inch and They Will Take a Mile:Understanding and Measuring Caller Identity Confusion in MCP-Based AI Systems
A security analysis of the Model Context Protocol (MCP) reveals significant vulnerabilities regarding caller identity confusion and lack of fine-grained authorization.
TransDex: Pre-training Visuo-Tactile Policy with Point Cloud Reconstruction for Dexterous Manipulation of Transparent Objects
TransDex is a visuo-tactile fusion policy that uses point cloud reconstruction pre-training to enable dexterous manipulation of transparent objects by robots.
PlotTwist: A Creative Plot Generation Framework with Small Language Models
PlotTwist is a framework that enables Small Language Models (under 3B parameters) to generate high-quality creative plots through structured preference-based alignment.
What Rose Petals Teach Us about Induction
A discussion on the conceptual relationship between rose petals and the principle of induction.
Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures
Introduces the Hyperdimensional Probe, a hybrid supervised probe that combines symbolic representations with neural probing to better decode LLM internal representations.
Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression
Presents a framework for dynamic expert clustering and structured compression in MoE LLMs, reducing parameters by 80% while maintaining quality.
Kontinuous Kontext: Continuous Strength Control for Instruction-based Image Editing
Introduces Kontinuous Kontext, a model for instruction-based image editing that allows continuous control over the strength of edits.
Beyond-Diagonal RIS Under Non-Idealities: Learning-Based Architecture Discovery and Optimization
Proposes a learning-based two-tier architecture discovery framework (LTTADF) to optimize beyond-diagonal reconfigurable intelligent surfaces for wireless networks.
QuArch: A Benchmark for Evaluating LLM Reasoning in Computer Architecture
Introduces QuArch, a new benchmark for evaluating the reasoning capabilities of LLMs in the field of computer architecture.
Active Electrosensing and Communication in MARL-trained Weakly Electric Fish Collectives
Explores the emergence of collective behavior in weakly electric fish using a computational framework trained via multi-agent reinforcement learning.
ImplicitRDP: An End-to-End Visual-Force Diffusion Policy with Structural Slow-Fast Learning
Presents ImplicitRDP, an end-to-end visual-force diffusion policy for contact-rich manipulation using Structural Slow-Fast Learning.
Memo2496: Expert-Annotated Dataset and Dual-view Adaptive Framework for Music Emotion Recognition
Presents the Memo2496 dataset and the DAMER framework for improving music emotion recognition through dual-view adaptive learning.
PRISP: Privacy-Safe Few-Shot Personalization via Lightweight Adaptation
Introduces PRISP, a privacy-safe few-shot personalization framework for LLMs using a Text-to-LoRA hypernetwork.
Why I'm building a note taking app without AI
A developer discusses their decision to build a note-taking application without integrating AI features, focusing on traditional utility.
All 253 Patterns from Christopher Alexander's a Pattern Language Summarized
A summary of all 253 patterns from Christopher Alexander's 'A Pattern Language', providing an architectural and urban planning reference.
Lego’s Donkey Kong arcade machine lets Mario jump endless barrels — Miyamoto is reportedly happy
Lego has released a Donkey Kong arcade machine set that includes a basic functional game mechanism.
GSPRec: On Improving Item Representations in Graph Signal Processing for Collaborative Filtering
GSPRec is a graph spectral collaborative filtering framework that improves item representations by incorporating user interaction ordering.