Yixuan Wang
34 papers · 2021–2026 · 13 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Cross-Pollinator (13) π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (13) π Academic Marathon (5)
π
Academic Marathon
(5)
π
Conference Polyglot
(13)
π§
Keyword Pioneer
π
Grand Slam
π₯
Unstoppable
(5)
β‘
Prolific Year
(13)
π
Century Club
(31)
β
The Questioner
ποΈ
Keyword Collector
(124)
Conferences
ACL (5)
CORL (4)
RSS (4)
AAAI (3)
EMNLP (3)
ICLR (3)
ICML (3)
NIPS (3)
COLING (2)
AACL (1)
ICCV (1)
IJCNLP (1)
L4DC (1)
Top co-authors
Keywords
graph neural network
(3)
large language model
(3)
dynamics model
(2)
key-value cache
(2)
syntactic structure
(2)
language generation
(2)
evaluation metric
(2)
generative model
(2)
speculative decoding
(2)
barrier function
(2)
inference acceleration
(2)
morphosyntactic typology
(2)
attention mechanism
(2)
cache eviction
(2)
grammatical error correction
(2)
safe reinforcement learning
(2)
domain adaptation
(2)
data augmentation
(1)
variational inference
(1)
logical reasoning
(1)
Papers
CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis
AAAI 2026
AlphaContext: An Evolutionary Tree-based Psychometric Context Generator for Creativity Assessment
ACL 2026
Judge Q: Trainable Queries for Optimized Information Retention in KV Cache Eviction
AAAI 2026
DeepNote: Note-Centric Deep Retrieval-Augmented Generation
EMNLP 2025
Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling
ACL 2025
Logical forms complement probability in understanding language model (and human) performance
ACL 2025
Tag-Evol: Achieving Efficient Instruction Evolving via Tag Injection
ACL 2025
Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query
EMNLP 2025
Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems
ICLR 2025
KAN: KolmogorovβArnold Networks
ICLR 2025
On the expressiveness and spectral bias of KANs
ICLR 2025
Directly Forecasting Belief for Reinforcement Learning with Delays
ICML 2025
CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity
RSS 2025
DemoGen: Synthetic Demonstration Generation for Data-Efficient Visuomotor Policy Learning
RSS 2025
LM-Combiner: A Contextual Rewriting Model for Chinese Grammatical Error Correction
COLING 2024
Make Some Noise: Unlocking Language Model Parallel Inference Capability through Noisy Training
EMNLP 2024
Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays
ICML 2024
D$^3$Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Rearrangement
CORL 2024
3D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensing
CORL 2024
GenDP: 3D Semantic Fields for Category-Level Generalizable Diffusion Policy
CORL 2024
REGLO: Provable Neural Network Repair for Global Robustness Properties
AAAI 2024
Improving Grammatical Error Correction via Contextual Data Augmentation
ACL 2024
State-wise safe reinforcement learning with pixel observations
L4DC 2024
HORSE: Hierarchical Representation for Large-Scale Neural Subset Selection
NIPS 2024
RoboPack: Learning Tactile-Informed Dynamics Models for Dense Packing
RSS 2024
Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation
NIPS 2024
Variational Delayed Policy Optimization
NIPS 2024
Delving into Evaluation Metrics for Generation: A Thorough Assessment of How Metrics Generalize to Rephrasing Across Languages
AACL 2023
Delving into Evaluation Metrics for Generation: A Thorough Assessment of How Metrics Generalize to Rephrasing Across Languages
IJCNLP 2023
Predicting Object Interactions with Behavior Primitives: An Application in Stowing Tasks
CORL 2023
Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments
ICML 2023
Dynamic-Resolution Model Learning for Object Pile Manipulation
RSS 2023
Adaptive Unsupervised Self-training for Disfluency Detection
COLING 2022
Weak Adaptation Learning: Addressing Cross-Domain Data Insufficiency With Weak Annotator
ICCV 2021