Songyang Gao
19 papers · 2022–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🗺️ Taxonomy Completionist (48) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 👥 Mega-Team · Squad
👥
Mega-Team · Squad
⚡
Prolific Year · Productive
❓
The Questioner
💎
Century Club · Bronze
🌈
Renaissance Researcher
(5)
🗃️
Keyword Collector
(112)
Venues
Top co-authors
Research topics
Artificial Intelligence
(16)
Core AI
(15)
Machine Learning
(13)
Deep Learning
(9)
Natural Language Processing
(9)
Learning Types · Machine Learning
(9)
Learning Types · Deep Learning
(7)
Optimization & Theory
(6)
Application Areas
(5)
Resources & Methods
(5)
Reinforcement Learning
(4)
Methods
(4)
Applications
(3)
Interdisciplinary
(1)
Security & Privacy
(1)
Keywords
large language model
(10)
reinforcement learning
(3)
tool learning
(3)
reinforcement learning from human feedback
(2)
text classification
(2)
benchmark evaluation
(2)
policy optimization
(2)
reward model
(2)
distribution shift
(2)
agent system
(2)
ai safety
(2)
out-of-distribution generalization
(2)
language model alignment
(1)
adversarial training
(1)
preference optimization
(1)
text generation
(1)
model robustness
(1)
model evaluation
(1)
computational efficiency
(1)
prompt engineering
(1)
Papers
AgentGym: Evaluating and Training Large Language Model-based Agents across Diverse Environments
ACL 2025
Alleviating Shifted Distribution in Human Preference Alignment through Meta-Learning
AAAI 2025
Are Your LLMs Capable of Stable Reasoning?
ACL 2025
Capability Salience Vector: Fine-grained Alignment of Loss and Capabilities for Downstream Task Scaling Law
ACL 2025
CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward
EMNLP 2025
ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios
COLING 2025
Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data
EMNLP 2024
Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback
ICML 2024
LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
ACL 2024
Navigating the OverKill in Large Language Models
ACL 2024
RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning
EMNLP 2024
ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages
ACL 2024
DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization
ACL 2023
Farewell to Aimless Large-scale Pretraining: Influential Subset Selection for Language Model
ACL 2023
On the Universal Adversarial Perturbations for Efficient Data-free Adversarial Detection
ACL 2023
RealBehavior: A Framework for Faithfully Characterizing Foundation Models’ Human-like Behavior Mechanisms
EMNLP 2023
Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement
EMNLP 2023
Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective
COLING 2022
Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding
EMNLP 2022