High Performance Space Debris Tracking in Complex Skylight Backgrounds with a Large-Scale Dataset
arXiv:2506.02614v2 Announce Type: replace-cross Abstract: With the rapid development of space exploration, space debris has attracted more attention due to…
Physics-Constrained Flow Matching: Sampling Generative Models with Hard Constraints
arXiv:2506.04171v1 Announce Type: cross Abstract: Deep generative models have recently been applied to physical systems governed by partial differential equations…
Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity
arXiv:2506.03337v1 Announce Type: cross Abstract: Federated Learning enables collaborative fine-tuning of Large Language Models (LLMs) across decentralized Non-Independent and Identically…
G4Seg: Generation for Inexact Segmentation Refinement with Diffusion Models
arXiv:2506.01539v1 Announce Type: cross Abstract: This paper considers the problem of utilizing a large-scale text-to-image diffusion model to tackle the…
EvolveNav: Self-Improving Embodied Reasoning for LLM-Based Vision-Language Navigation
arXiv:2506.01551v1 Announce Type: cross Abstract: Building Vision-Language Navigation (VLN) agents which can navigate following natural language instructions is a long-standing…
DLP: Dynamic Layerwise Pruning in Large Language Models
arXiv:2505.23807v3 Announce Type: replace-cross Abstract: Pruning has recently been widely adopted to reduce the parameter scale and improve the inference…
LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation
arXiv:2506.01538v2 Announce Type: cross Abstract: Although Multi-Agent Reinforcement Learning (MARL) is effective for complex multi-robot tasks, it suffers from low…
Bias as a Virtue: Rethinking Generalization under Distribution Shifts
arXiv:2506.00407v1 Announce Type: cross Abstract: Machine learning models often degrade when deployed on data distributions different from their training data.…
BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models
arXiv:2505.24649v1 Announce Type: cross Abstract: Large vision-language models have become widely adopted to advance in various domains. However, developing a…
Multiple LLM Agents Debate for Equitable Cultural Alignment
arXiv:2505.24671v1 Announce Type: cross Abstract: Large Language Models (LLMs) need to adapt their predictions to diverse cultural contexts to benefit…