0

Yang Xiao

Papers
18

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
18papers

Authored papers

18

A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook

arXiv 2026

2026

LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces

arXiv 2026

2026

AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts

arXiv 2026

2026

daVinci-Dev: Agent-native Mid-training for Software Engineering

arXiv 2026

2026

daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently

arXiv 2026

2026

LIMO: Less is More for Reasoning

arXiv 2025

2025

SCALE: Selective Resource Allocation for Overcoming Performance Bottlenecks in Mathematical Test-time Scaling

arXiv 2025

2025

LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling

arXiv 2025

2025

LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation

arXiv 2025

2025

LIMI: Less is More for Agency

arXiv 2025

2025

Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States

arXiv 2025

2025

XLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack Detection

arXiv 2024

2024

WildDESED: An LLM-Powered Dataset for Wild Domestic Environment Sound Event Detection System

arXiv 2024

2024

Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning

arXiv 2024

2024

How Far Are LLMs from Believable AI? A Benchmark for Evaluating the Believability of Human Behavior Simulation

arXiv 2023

2023

Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions

CVPR 2022 1

2022

Partial FC: Training 10 Million Identities on a Single Machine

arXiv 2020

2020

P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds

p2b-point-to-box-network-for-3d-object-1

2020

Affiliations

No known affiliations.

Frequent co-authors

10

from 18 papers