Xiangzheng Zhang
11 papers · 2025–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (3) π Renaissance Researcher (5) πΊοΈ Taxonomy Completionist (25)
π
Cross-Pollinator
(14)
β
Rising Star
(5)
β‘
Prolific Year
(5)
Conferences
ACL (5)
AAAI (3)
EMNLP (3)
Top co-authors
Keywords
large language model
(5)
supervised fine-tuning
(3)
chain-of-thought reasoning
(2)
safety alignment
(2)
jailbreak attack
(2)
mathematical reasoning
(2)
reinforcement learning
(2)
knowledge distillation
(1)
multi-modal learning
(1)
adversarial learning
(1)
code generation
(1)
visual reasoning
(1)
instruction following
(1)
document understanding
(1)
model robustness
(1)
language model
(1)
model training
(1)
diffusion model
(1)
vision language model
(1)
generalization ability
(1)
Papers
Thinking with Reasoning Skills: Fewer Tokens, More Accuracy
ACL 2026
Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following
AAAI 2026
Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training
AAAI 2026
DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs
ACL 2026
TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment
ACL 2026
When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation
ACL 2026
Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond
ACL 2025
Large Language Models Badly Generalize across Option Length, Problem Types, and Irrelevant Noun Replacements
EMNLP 2025
Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision
EMNLP 2025
Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models
EMNLP 2025
Expand VSR Benchmark for VLLM to Expertize in Spatial Rules
AAAI 2025