About
Research & Development
FedCLF: Enhancing Federated Learning for Connected Vehicle Networks
TLDR: FedCLF is a novel Federated Learning (FL) system designed for heterogeneous Internet of Vehicles (IoV) networks. It introduces a 'calibrated loss' utility for...
Research & Development
PALADIN: Equipping Language Agents with Robust Tool-Failure Recovery
TLDR: The research paper introduces PALADIN, a framework that teaches language model agents to recover from real-world tool failures like timeouts and API errors....
Research & Development
LLM Agents Tackle Real-World Software Compilation Challenges with BUILD-BENCH
TLDR: The paper introduces BUILD-BENCH, a new, more realistic benchmark for evaluating LLM agents on compiling diverse real-world open-source software. It also proposes OSS-BUILD-AGENT,...
Research & Development
BEV-VLM: A Unified Approach to Autonomous Driving Trajectory Planning
TLDR: BEV-VLM is a new framework for autonomous driving trajectory planning that uses Vision-Language Models (VLMs) with unified Bird’s-Eye View (BEV) feature maps fused...
Research & Development
Enhancing Multimodal AI with Synergistic Information Extraction
TLDR: InfMasking is a new contrastive learning method that improves multimodal AI by effectively capturing 'synergistic information'—where different data types (like images and text)...
Research & Development
VoiceBridge: A Unified System for High-Fidelity Speech Restoration Across Diverse Distortions
TLDR: VoiceBridge is a new general speech restoration (GSR) system that uses latent bridge models to reconstruct high-fidelity, 48 kHz speech from various low-quality...