Wenxiao Wang
38 papers · 2019–2026 · 11 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
🌍 Conference Polyglot (10) 🏃 Academic Marathon (6) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🐝 Cross-Pollinator (13)
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(13)
🤝
Dynamic Duo
(15)
👑
Triple Crown
🏆
Grand Slam
🧬
Topic Evolution
💎
Century Club
(37)
⚡
Prolific Year
(13)
🗃️
Keyword Collector
(138)
❓
The Questioner
🔥
Unstoppable
(7)
Conferences
ICLR (7)
NIPS (7)
CVPR (5)
AAAI (3)
ECCV (3)
ICCV (3)
ICML (3)
EMNLP (2)
IJCAI (2)
NAACL (2)
ACL (1)
Top co-authors
Research topics
Keywords
large language model
(6)
autonomous driving
(4)
prompt engineering
(3)
data poisoning
(3)
3d object detection
(3)
point cloud
(2)
volume rendering
(2)
finite aggregation
(2)
attention head
(2)
neural radiance field
(2)
pseudo label
(2)
certified robustness
(2)
deep neural network
(2)
model compression
(2)
trajectory prediction
(2)
contrastive learning
(2)
adversarial robustness
(1)
3d reconstruction
(1)
robust optimization
(1)
neural network pruning
(1)
Papers
HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference
ACL 2026
Tool Preferences in Agentic LLMs are Unreliable
EMNLP 2025
STraj: Self-training for Bridging the Cross-Geography Gap in Trajectory Prediction
AAAI 2025
DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors
EMNLP 2025
Improving Complex Reasoning with Dynamic Prompt Corruption: A Soft Prompt Optimization Approach
ICLR 2025
Don't Take Things Out of Context: Attention Intervention for Enhancing Chain-of-Thought Reasoning in Large Language Models
ICLR 2025
FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models
ICLR 2025
From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks
NAACL 2025
Concise and Organized Perception Facilitates Reasoning in Large Language Models
NAACL 2025
Regulating Intermediate 3D Features for Vision-Centric Autonomous Driving
AAAI 2024
Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection
CVPR 2024
DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness
ICLR 2024
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
ICLR 2024
Few-shot Hybrid Domain Adaptation of Image Generator
ICLR 2024
Instance-adaptive Zero-shot Chain-of-Thought Prompting
NIPS 2024
G2LTraj: A Global-to-Local Generation Approach for Trajectory Prediction
IJCAI 2024
EMVP: Embracing Visual Foundation Model for Visual Place Recognition with Centroid-Free Probing
NIPS 2024
Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts
ECCV 2024
From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning
ICML 2024
Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control
NIPS 2024
Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
NIPS 2024
Learning Occupancy for Monocular 3D Object Detection
CVPR 2024
CLIP Is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation
CVPR 2023
Temporal Robustness against Data poisoning
NIPS 2023
PVT-SSD: Single-Stage 3D Object Detector With Point-Voxel Transformer
CVPR 2023
Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases
NIPS 2023
Towards In-Distribution Compatible Out-of-Distribution Detection
AAAI 2023
MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection
ICCV 2023
One-shot Implicit Animatable Avatars with Model-based Priors
ICCV 2023
CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention
ICLR 2022
Masked Autoencoders for Point Cloud Self-Supervised Learning
ECCV 2022
Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph
ECCV 2022
Lethal Dose Conjecture on Data Poisoning
NIPS 2022
Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation
ICML 2022
Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework
ICML 2021
On Feature Decorrelation in Self-Supervised Learning
ICCV 2021
The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks
CVPR 2020
COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning
IJCAI 2019