Furong Huang
~Furong_Huang1
41
论文总数
20.5
年均投稿
平均评分
接收情况24/41
会议分布
ICLR
31
NeurIPS
8
COLM
2
发表论文 (41 篇)
202514 篇
5
LIAR: Leveraging Inverse Alignment to Jailbreak LLMs in Seconds
ICLR 2025Rejected
4
AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment
ICLR 2025Rejected
4
Towards Realistic Mechanisms That Incentivize Federated Participation and Contribution
ICLR 2025Rejected
4
GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-Time Alignment
ICLR 2025Poster
4
Auction-Based Regulation for Artificial Intelligence
ICLR 2025Rejected
6
LSH Tells You What To Discard: An Adaptive Locality-Sensitive Strategy for KV Cache Compression
ICLR 2025withdrawn
4
Does Thinking More Always Help? Mirage of Test-Time Scaling in Reasoning Models
NeurIPS 2025Poster
4
EnsemW2S: Can an Ensemble of LLMs be Leveraged to Obtain a Stronger LLM?
ICLR 2025Rejected
4
TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies
ICLR 2025Poster
5
Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset
ICLR 2025Poster
4
Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
ICLR 2025Poster
4
SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement
NeurIPS 2025Spotlight
4
SAIL: Self-improving Efficient Online Alignment of Large Language Models
ICLR 2025Rejected
4
ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs
NeurIPS 2025Poster
202427 篇
4
SDM-RL: Steady-State Divergence Maximization for Robust Reinforcement Learning
ICLR 2024Rejected
3
Decodable and Sample Invariant Continuous Object Encoder
ICLR 2024Poster
4
Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds
ICLR 2024Poster
4
Robustness to Multi-Modal Environment Uncertainty in MARL using Curriculum Learning
ICLR 2024withdrawn
5
Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariance
NeurIPS 2024Poster
3
FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?
NeurIPS 2024Poster
7
Spectral Greedy Coresets for Graph Neural Networks
ICLR 2024Rejected
4
Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
ICLR 2024Poster
4
SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation
ICLR 2024Poster
4
RealFM: A Realistic Mechanism to Incentivize Data Contribution and Device Participation
ICLR 2024Rejected
5
Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion
NeurIPS 2024Poster
4
Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies
ICLR 2024Spotlight
4
PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts
ICLR 2024Poster
4
AutoDAN: Automatic and Interpretable Adversarial Attacks on Large Language Models
ICLR 2024Rejected
4
On the Possibilities of AI-Generated Text Detection: A Sample Complexity Analysis
ICLR 2024Rejected
4
Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models
COLM 2024Poster
4
Transfer Q-star : Principled Decoding for LLM Alignment
NeurIPS 2024Poster
3
COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL
ICLR 2024Poster
3
Equal Long-term Benefit Rate: Adapting Static Fairness Notions to Sequential Decision Making
ICLR 2024Rejected
4
PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback
ICLR 2024Poster
3
Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
ICLR 2024Poster
4
AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models
COLM 2024Poster
4
Comfetch: Federated Learning of Large Networks on Constrained Clients via Sketching
ICLR 2024withdrawn
4
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
NeurIPS 2024Poster
4
Calibrated Dataset Condensation for Faster Hyperparameter Search
ICLR 2024Rejected
3
$\texttt{PREMIER-TACO}$ is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
ICLR 2024Rejected
4
DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
ICLR 2024Spotlight