Cs-Ai
Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfinding
Agentic Uncertainty Reveals Agentic Overconfidence
Bridging 6G IoT and AI: LLM-Based Efficient Approach for Physical Layer's Optimization Tasks
TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
Generating Data-Driven Reasoning Rubrics for Domain-Adaptive Reward Modeling
SuReNav: Superpixel Graph-based Constraint Relaxation for Navigation in Over-constrained Environments
Towards Understanding What State Space Models Learn About Code
POP: Online Structural Pruning Enables Efficient Inference of Large Foundation Models
Gold Exploration using Representations from a Multispectral Autoencoder
RARe: Retrieval Augmented Retrieval with In-Context Examples
Simmering: Sufficient is better than optimal for training neural networks
Toward Reasoning on the Boundary: A Mixup-based Approach for Graph Anomaly Detection
Prism: Spectral Parameter Sharing for Multi-Agent Reinforcement Learning
TrailBlazer: History-Guided Reinforcement Learning for Black-Box LLM Jailbreaking
A methodology for analyzing financial needs hierarchy from social discussions using LLM
Emergent Low-Rank Training Dynamics in MLPs with Smooth Activations
RuleSmith: Multi-Agent LLMs for Automated Game Balancing
Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning
HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction
AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents
Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention
