KiloClaw - Managed 🦀 
Mini toolsPapers
Filter by company
-
Slim attention: cut your context memory in half without loss – K-cache is all you need for MHA
-
MACRO: Advancing Multi-Reference Image Generation with Structured Long-Context Data
-
Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs
-
Think 360°: Evaluating the Width-centric Reasoning Capability of MLLMs Beyond Depth
-
WiFi2Cap: Semantic Action Captioning from Wi-Fi CSI via Limb-Level Semantic Alignment
-
Coordinate Encoding on Linear Grids for Physics-Informed Neural Networks
-
TimeWeaver: Age-Consistent Reference-Based Face Restoration with Identity Preservation
-
Synthetic or Authentic? Building Mental Patient Simulators from Longitudinal Evidence
-
How Far Can VLMs Go for Visual Bug Detection? Studying 19,738 Keyframes from 41 Hours of Gameplay Videos
-
Detecting Non-Membership in LLM Training Data via Rank Correlations
-
Who Spoke What When? Evaluating Spoken Language Models for Conversational ASR with Semantic and Overlap-Aware Metrics
-
PopResume: Causal Fairness Evaluation of LLM/VLM Resume Screeners with Population-Representative Dataset
-
Labeled Compression Schemes for Concept Classes of Finite Functions
-
Double Coupling Architecture and Training Method for Optimization Problems of Differential Algebraic Equations with Parameters
-
Spiking Personalized Federated Learning for Brain-Computer Interface-Enabled Immersive Communication
-
Behavioral Heterogeneity as Quantum-Inspired Representation
-
How Utilitarian Are OpenAI's Models Really? Replicating and Reinterpreting Pfeffer, Krügel, and Uhl (2025)
-
SOUPLE: Enhancing Audio-Visual Localization and Segmentation with Learnable Prompt Contexts
-
Explanation Generation for Contradiction Reconciliation with LLMs
-
Multitask-Informed Prior for In-Context Learning on Tabular Data: Application to Steel Property Prediction
-
Algorithmic warm starts for Hamiltonian Monte Carlo
-
Beyond Binary Correctness: Scaling Evaluation of Long-Horizon Agents on Subjective Enterprise Tasks
-
REALITrees: Rashomon Ensemble Active Learning for Interpretable Trees
-
CLiGNet: Clinical Label-Interaction Graph Network for Medical Specialty Classification from Clinical Transcriptions
-
PRISM: A Dual View of LLM Reasoning through Semantic Flow and Latent Computation
-
KALAVAI: Predicting When Independent Specialist Fusion Works -- A Quantitative Model for Post-Hoc Cooperative LLM Training
-
MVPBench: A Multi-Video Perception Evaluation Benchmark for Multi-Modal Video Understanding
-
Multimodal Industrial Anomaly Detection via Geometric Prior
-
Reconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learning
-
Can LLM Agents Generate Real-World Evidence? Evaluating Observational Studies in Medical Databases
-
From Pixels to Semantics: A Multi-Stage AI Framework for Structural Damage Detection in Satellite Imagery
-
Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models
-
Caterpillar of Thoughts: The Optimal Test-Time Algorithm for Large Language Models
-
ABSTRAL: Automatic Design of Multi-Agent Systems Through Iterative Refinement and Topology Optimization
-
Reliable Classroom AI via Neuro-Symbolic Multimodal Reasoning
-
Transformers Trained via Gradient Descent Can Provably Learn a Class of Teacher Models
-
MultiCam: On-the-fly Multi-Camera Pose Estimation Using Spatiotemporal Overlaps of Known Objects
-
URA-Net: Uncertainty-Integrated Anomaly Perception and Restoration Attention Network for Unsupervised Anomaly Detection
-
UAV-DETR: DETR for Anti-Drone Target Detection
-
L-UNet: An LSTM Network for Remote Sensing Image Change Detection
-
PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgical Smoke Removal
-
CoMaTrack: Competitive Multi-Agent Game-Theoretic Tracking with Vision-Language-Action Models
-
Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought
-
UniQueR: Unified Query-based Feedforward 3D Reconstruction
-
Gau-Occ: Geometry-Completed Gaussians for Multi-Modal 3D Occupancy Prediction
-
Avoiding Over-smoothing in Social Media Rumor Detection with Pre-trained Propagation Tree Transformer
-
The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration
-
Agent-Sentry: Bounding LLM Agents via Execution Provenance
-
Chain-of-Authorization: Internalizing Authorization into Large Language Models via Reasoning Trajectories
-
Designing to Forget: Deep Semi-parametric Models for Unlearning
