Hanlin Zhang
15 papers · 2020–2025 · 8 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 ↓+5 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (31) π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint
π₯
Mega-Team Β· Legion
β‘
Prolific Year Β· Productive
β
The Questioner
(2)
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(70)
Top co-authors
Research topics
Machine Learning
(13)
Artificial Intelligence
(8)
Natural Language Processing
(8)
Core AI
(8)
Optimization & Theory
(7)
Application Areas
(6)
Resources & Methods
(5)
Deep Learning
(2)
Core Methods
(2)
Generation
(2)
Learning Types
(2)
Knowledge & Reasoning
(1)
Reinforcement Learning
(1)
Applications
(1)
Bayesian & Probabilistic
(1)
Keywords
language model
(5)
in-context learning
(2)
retrieval-augmented generation
(2)
position bia
(2)
neural network optimization
(2)
symbolic reasoning
(2)
domain generalization
(2)
data filtering
(2)
domain adaptation
(2)
logical reasoning
(1)
natural language understanding
(1)
instruction following
(1)
bidirectional attention
(1)
variational inference
(1)
explanation generation
(1)
distribution shift
(1)
language modeling
(1)
reinforcement learning from human feedback
(1)
knowledge base
(1)
constrained optimization
(1)
Papers
Eliminating Position Bias of Language Models: A Mechanistic Approach
ICLR 2025
Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems
ICLR 2025
How Does Critical Batch Size Scale in Pre-training?
ICLR 2025
Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models
ICLR 2025
A Study on the Calibration of In-context Learning
NAACL 2024
CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training
NeurIPS 2024
DataComp-LM: In search of the next generation of training sets for language models
NeurIPS 2024
Evaluating Step-by-Step Reasoning through Symbolic Verification
NAACL 2024
Optimizing Language Models with Fair and Stable Reward Composition in Reinforcement Learning
EMNLP 2024
Watermarks in the Sand: Impossibility of Strong Watermarking for Language Models
ICML 2024
Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the Machiavelli Benchmark
ICML 2023
Improved Logical Reasoning of Language Models via Differentiable Symbolic Programming
ACL 2023
Toward learning human-aligned cross-domain robust models by countering misaligned features
UAI 2022
Towards Principled Disentanglement for Domain Generalization
CVPR 2022
Towards Interpretable Natural Language Understanding with Explanations as Latent Variables
NeurIPS 2020