Yanxiang Ma
5 papers · 2023–2026 · 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 ↓
๐
Conference Polyglot ยท Silver
๐บ๏ธ
Taxonomy Completionist
(11)
๐
Grand Slam
Venues
Top co-authors
Research topics
Keywords
adversarial robustness
(1)
information bottleneck
(1)
self-supervised learning
(1)
chain-of-thought reasoning
(1)
adversarial training
(1)
feature representation
(1)
mutual information
(1)
adversarial attack
(1)
robust accuracy
(1)
retrieval-augmented generation
(1)
masked autoencoder
(1)
analogical reasoning
(1)
legal reasoning
(1)
activation steering
(1)
gradient similarity
(1)
large language model
(1)
representation optimization
(1)
randomized defense
(1)
clean accuracy
(1)
random mask
(1)
Papers
Eliciting Chain-of-Thought in Base LLMs via Gradient-Based Representation Optimization
AAAI 2026
Mitigating Legal Hallucinations via Symbolic Constraints and Analogical Precedents
ACL 2026
Adversarial Robustness via Deformable Convolution with Stochasticity
ICML 2025
Learning Mask Invariant Mutual Information for Masked Image Modeling
ICLR 2025
Adversarial Robustness through Random Weight Sampling
NeurIPS 2023