2025
Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback.
CoRR, June, 2025
GL-LowPopArt: A Nearly Instance-Wise Minimax-Optimal Estimator for Generalized Low-Rank Trace Regression.
CoRR, June, 2025
Near-Optimal Clustering in Mixture of Markov Chains.
CoRR, June, 2025
LLM Agents for Bargaining with Utility-based Feedback.
CoRR, May, 2025
Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness.
CoRR, May, 2025
Flex-Judge: Think Once, Judge Anywhere.
CoRR, May, 2025
AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners.
CoRR, May, 2025
Guiding Reasoning in Small Language Models with LLM Assistance.
CoRR, April, 2025
When Debate Fails: Bias Reinforcement in Large Language Models.
CoRR, March, 2025
MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation.
CoRR, March, 2025
Probability-Flow ODE in Infinite-Dimensional Function Spaces.
CoRR, March, 2025
DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs.
CoRR, March, 2025
Self-Training Elicits Concise Reasoning in Large Language Models.
CoRR, February, 2025
What is the Alignment Objective of GRPO?
CoRR, February, 2025
MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition.
CoRR, February, 2025
FedDr+: Stabilizing Dot-regression with Global Feature Distillation for Federated Learning.
Trans. Mach. Learn. Res., 2025
C²: Scalable Auto-Feedback for LLM-based Chart Generation.
Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025
Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
FlickerFusion: Intra-trajectory Domain Generalizing Multi-agent Reinforcement Learning.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
MA2E: Addressing Partial Observability in Multi-Agent Reinforcement Learning with Masked Auto-Encoder.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
2024
Optimal clustering from noisy binary feedback.
Mach. Learn., May, 2024
Non-backtracking Graph Neural Networks.
Trans. Mach. Learn. Res., 2024
FLR: Label-Mixture Regularization for Federated Learning with Noisy Labels.
Trans. Mach. Learn. Res., 2024
C<sup>2</sup>: Scalable Auto-Feedback for LLM-based Chart Generation.
CoRR, 2024
FlickerFusion: Intra-trajectory Domain Generalizing Multi-Agent RL.
CoRR, 2024
Diffusion-based Episodes Augmentation for Offline Multi-Agent Reinforcement Learning.
CoRR, 2024
VACoDe: Visual Augmented Contrastive Decoding.
CoRR, 2024
BAPO: Base-Anchored Preference Optimization for Personalized Alignment in Large Language Models.
CoRR, 2024
Why In-Context Learning Transformers are Tabular Data Classifiers.
CoRR, 2024
Towards Unbiased Evaluation of Detecting Unanswerable Questions in EHRSQL.
CoRR, 2024
Rotting Infinitely Many-armed Bandits beyond the Worst-case Rotting: An Adaptive Approach.
CoRR, 2024
Non-linear Fusion in Federated Learning: A Hypernetwork Approach to Federated Domain Generalization.
CoRR, 2024
Revisiting Early-Learning Regularization When Federated Learning Meets Noisy Labels.
CoRR, 2024
Learning Video Temporal Dynamics With Cross-Modal Attention For Robust Audio-Visual Speech Recognition.
Proceedings of the IEEE Spoken Language Technology Workshop, 2024
A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
An Adaptive Approach for Infinitely Many-armed Bandits under Generalized Rotting Constraints.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Preference Alignment with Flow Matching.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Conditional Synthesis of 3D Molecules with Time Correction Sampler.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Block Transformer: Global-to-Local Language Modeling for Fast Inference.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Carpe diem: On the Evaluation of World Knowledge in Lifelong Language Models.
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024
Fine-tuning Pre-trained Models for Robustness under Noisy Labels.
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024
DistiLLM: Towards Streamlined Distillation for Large Language Models.
Proceedings of the Forty-first International Conference on Machine Learning, 2024
Synergistic Integration of Coordinate Network and Tensorial Feature for Improving Neural Radiance Fields from Sparse Inputs.
Proceedings of the Forty-first International Conference on Machine Learning, 2024
Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions.
Proceedings of the Twelfth International Conference on Learning Representations, 2024
Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024
Towards Difficulty-Agnostic Efficient Transfer Learning for Vision-Language Models.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024
BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024
Stable Language Model Pre-training by Reducing Embedding Variability.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024
FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024
Leveraging Normalization Layer in Adapters with Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learning.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024
2023
Accelerated MM Algorithms for Inference of Ranking Scores from Comparison Data.
Oper. Res., July, 2023
Test Score Algorithms for Budgeted Stochastic Utility Maximization.
INFORMS J. Optim., January, 2023
Improving Adaptability and Generalizability of Efficient Transfer Learning for Vision-Language Models.
CoRR, 2023
FedFN: Feature Normalization for Alleviating Data Heterogeneity Problem in Federated Learning.
CoRR, 2023
Carpe Diem: On the Evaluation of World Knowledge in Lifelong Language Models.
CoRR, 2023
Fine-Tuning the Retrieval Mechanism for Tabular Deep Learning.
CoRR, 2023
Distort, Distract, Decode: Instruction-Tuned Model Can Refine its Response from Noisy Instructions.
CoRR, 2023
Cross-Modal Retrieval Meets Inference: Improving Zero-Shot Classification with Cross-Modal Retrieval.
CoRR, 2023
FedSoL: Bridging Global Alignment and Local Generality in Federated Learning.
CoRR, 2023
Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model.
CoRR, 2023
Enhancing Generalization and Plasticity for Sample Efficient Reinforcement Learning.
CoRR, 2023
Communication-Efficient Collaborative Heterogeneous Bandits in Networks.
CoRR, 2023
The StarCraft Multi-Agent Exploration Challenges: Learning Multi-Stage Tasks and Environmental Factors Without Precise Reward Functions.
IEEE Access, 2023
Meta-Learning Amidst Heterogeneity and Ambiguity.
IEEE Access, 2023
Flooding with Absorption: An Efficient Protocol for Heterogeneous Bandits over Complex Networks.
Proceedings of the 27th International Conference on Principles of Distributed Systems, 2023
Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Recycle-and-Distill: Universal Compression Strategy for Transformer-based Speech SSL Models with Attention Map Reusing and Masking Distillation.
Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023
Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification.
Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023
Mitigating Dataset Bias by Using Per-Sample Gradient.
Proceedings of the Eleventh International Conference on Learning Representations, 2023
CUDA: Curriculum of Data Augmentation for Long-tailed Recognition.
Proceedings of the Eleventh International Conference on Learning Representations, 2023
HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023
Bayesian Multi-Task Transfer Learning for Soft Prompt Tuning.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023
NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023
Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023
Revisiting Intermediate Layer Distillation for Compressing Language Models: An Overfitting Perspective.
Proceedings of the Findings of the Association for Computational Linguistics: EACL 2023, 2023
Coreset Sampling from Open-Set for Fine-Grained Self-Supervised Learning.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
Re-Thinking Federated Active Learning Based on Inter-Class Diversity.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
Toward Risk-based Optimistic Exploration for Cooperative Multi-Agent Reinforcement Learning.
Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems, 2023
Contextual Linear Bandits under Noisy Features: Towards Bayesian Oracles.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023
Nearly Optimal Latent State Decoding in Block MDPs.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023
Large Language Models Are Reasoning Teachers.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023
A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023
Self-Contrastive Learning: Single-Viewed Supervised Contrastive Framework Using Sub-network.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023
Denoising after Entropy-Based Debiasing a Robust Training Method for Dataset Bias with Noisy Labels.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023
2022
Region-Conditioned Orthogonal 3D U-Net for Weather4Cast Competition.
CoRR, 2022
The StarCraft Multi-Agent Challenges+ : Learning of Multi-Stage Tasks and Environmental Factors without Precise Reward Functions.
CoRR, 2022
Benchmark Dataset for Precipitation Forecasting by Post-Processing the Numerical Weather Prediction.
CoRR, 2022
Risk Perspective Exploration in Distributional Reinforcement Learning.
CoRR, 2022
Revisiting Architecture-aware Knowledge Distillation: Smaller Models and Faster Search.
CoRR, 2022
Demystifying the Base and Novel Performances for Few-shot Class-incremental Learning.
CoRR, 2022
ALASCA: Rethinking Label Smoothing for Deep Learning Under Label Noise.
CoRR, 2022
Supernet Training for Federated Image Classification under System Heterogeneity.
CoRR, 2022
Adversarial Bandits Robust to S-Switch Regret.
CoRR, 2022
Revisiting the Updates of a Pre-trained Model for Few-shot Learning.
CoRR, 2022
SuperNet in Neural Architecture Search: A Taxonomic Survey.
CoRR, 2022
Understanding Cross-Domain Few-Shot Learning: An Experimental Study.
CoRR, 2022
Mold into a Graph: Efficient Bayesian Optimization over Mixed-Spaces.
CoRR, 2022
Revisiting Orthogonality Regularization: A Study for Convolutional Neural Networks in Image Classification.
IEEE Access, 2022
Calibration of Few-Shot Classification Tasks: Mitigating Misconfidence From Distribution Mismatch.
IEEE Access, 2022
Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022
MEDIAR: Harmony of Data-Centric and Model-Centric for Multi-Modality Microscopy.
Proceedings of The Cell Segmentation Challenge in Multi-modality High-Resolution Microscopy Images, 2022
Preservation of the Global Knowledge by Not-True Distillation in Federated Learning.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022
Rotting Infinitely Many-Armed Bandits.
Proceedings of the International Conference on Machine Learning, 2022
Real-time and Explainable Detection of Epidemics with Global News Data.
Proceedings of the 1st Workshop on Healthcare AI and COVID-19, 2022
FedBABU: Toward Enhanced Representation for Federated Image Classification.
Proceedings of the Tenth International Conference on Learning Representations, 2022
Neural Processes with Stochastic Attention: Paying more attention to the context dataset.
Proceedings of the Tenth International Conference on Learning Representations, 2022
Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks.
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022
ReFine: Re-randomization before Fine-tuning for Cross-domain Few-shot Learning.
Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022
FedRN: Exploiting k-Reliable Neighbors Towards Robust Federated Learning.
Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022
2021
A Test Score-Based Approach to Stochastic Submodular Optimization.
Manag. Sci., 2021
Meta-learning Amidst Heterogeneity and Ambiguity.
CoRR, 2021
Self-Contrastive Learning.
CoRR, 2021
FedBABU: Towards Enhanced Representation for Federated Image Classification.
CoRR, 2021
Preservation of the Global Knowledge by Not-True Self Knowledge Distillation in Federated Learning.
CoRR, 2021
FINE Samples for Learning with Noisy Labels.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021
Weather4cast at NeurIPS 2022: Super-Resolution Rain Movie Prediction under Spatio-temporal Shifts.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the NeurIPS 2022 Competition Track, 2021
Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation.
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021
Improved Regret Bounds of Bilinear Bandits using Action Space Analysis.
Proceedings of the 38th International Conference on Machine Learning, 2021
BOIL: Towards Representation Change for Few-shot Learning.
Proceedings of the 9th International Conference on Learning Representations, 2021
2020
Reinforcement with Fading Memories.
Math. Oper. Res., 2020
Adaptive Local Bayesian Optimization Over Multiple Discrete Variables.
CoRR, 2020
Accurate and Fast Federated Learning via Combinatorial Multi-Armed Bandits.
CoRR, 2020
TornadoAggregate: Accurate and Scalable Federated Learning via the Ring-Based Architecture.
CoRR, 2020
MixCo: Mix-up Contrastive Learning for Visual Representation.
CoRR, 2020
Does MAML really want feature reuse only?
CoRR, 2020
Regret in Online Recommendation Systems.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020
SIPA: A Simple Framework for Efficient Networks.
Proceedings of the 20th International Conference on Data Mining Workshops, 2020
Precipitation Nowcasting Using Grid-based Data in South Korea Region.
Proceedings of the 20th International Conference on Data Mining Workshops, 2020
FEWER: Federated Weight Recovery.
Proceedings of the DistributedML@CoNEXT 2020: Proceedings of the 1st Workshop on Distributed Machine Learning, 2020
Accelerating Randomly Projected Gradient with Variance Reduction.
Proceedings of the 2020 IEEE International Conference on Big Data and Smart Computing, 2020
Convergence Rates of Gradient Descent and MM Algorithms for Bradley-Terry Models.
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020
2019
Non-Stationary Streaming PCA.
CoRR, 2019
Convergence Rates of Gradient Descent and MM Algorithms for Generalized Bradley-Terry Models.
CoRR, 2019
A pipelined hybrid recommender system for ranking the items on the display.
Proceedings of the Workshop on ACM Recommender Systems Challenge, 2019
Optimal Sampling and Clustering in the Stochastic Block Model.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019
Efficient Model for Image Classification With Regularization Tricks.
Proceedings of the NeurIPS 2019 Competition and Demonstration Track, 2019
Spectral Approximate Inference.
Proceedings of the 36th International Conference on Machine Learning, 2019
2018
Game Theoretic Perspective of Optimal CSMA.
IEEE Trans. Wirel. Commun., 2018
Spectrogram-channels u-net: a source separation model viewing each channel as the spectrogram of each source.
CoRR, 2018
Noisy Power Method with Grassmann Average.
Proceedings of the 2018 IEEE International Conference on Big Data and Smart Computing, 2018
2017
Clustering in Block Markov Chains.
CoRR, 2017
Contextual Multi-armed Bandits under Feature Uncertainty.
CoRR, 2017
On the Delay Scaling Laws of Cache Networks.
Proceedings of the 12th International Conference on Future Internet Technologies, 2017
Collaborative Clustering: Sample Complexity and Efficient Algorithms.
Proceedings of the International Conference on Algorithmic Learning Theory, 2017
2016
Distributed Medium Access Over Time-Varying Channels.
IEEE/ACM Trans. Netw., 2016
Delay Optimal CSMA With Linear Virtual Channels Under a General Topology.
IEEE/ACM Trans. Netw., 2016
Sketching with Test Scores and Submodular Maximization.
CoRR, 2016
Optimal Cluster Recovery in the Labeled Stochastic Block Model.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016
Distributed coordination maximization over networks: a stochastic approximation approach.
Proceedings of the 17th ACM International Symposium on Mobile Ad Hoc Networking and Computing, 2016
Parameter Estimation for Generalized Thurstone Choice Models.
Proceedings of the 33nd International Conference on Machine Learning, 2016
2015
CSMA Using the Bethe Approximation: Scheduling and Utility Maximization.
IEEE Trans. Inf. Theory, 2015
Optimality of Spectral Algorithms for Community Detection in the Labeled Stochastic Block Model.
CoRR, 2015
Distributed Proportional Fair Load Balancing in Heterogenous Systems.
Proceedings of the 2015 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems, 2015
Fast and Memory Optimal Low-Rank Matrix Approximation.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015
2014
Accurate Community Detection in the Stochastic Block Model via Spectral Algorithms.
CoRR, 2014
Streaming, Memory Limited Algorithms for Community Detection.
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014
Provable per-link delay-optimal CSMA for general wireless network topology.
Proceedings of the 2014 IEEE Conference on Computer Communications, 2014
Distributed learning for utility maximization over CSMA-based wireless multihop networks.
Proceedings of the 2014 IEEE Conference on Computer Communications, 2014
Community Detection via Random and Adaptive Sampling.
Proceedings of The 27th Conference on Learning Theory, 2014
Distributed load balancing in heterogenous systems.
Proceedings of the 48th Annual Conference on Information Sciences and Systems, 2014
2013
CSMA using Statistical Physics toward Throughput and Utility Optimal CSMA.
CoRR, 2013
CSMA over time-varying channels: optimality, uniqueness and limited backoff rate.
Proceedings of the Fourteenth ACM International Symposium on Mobile Ad Hoc Networking and Computing, 2013
CSMA using the Bethe approximation for utility maximization.
Proceedings of the 2013 IEEE International Symposium on Information Theory, 2013
2012
The Economic Effects of Sharing Femtocells.
IEEE J. Sel. Areas Commun., 2012
From Glauber dynamics to Metropolis algorithm: Smaller delay in optimal CSMA.
Proceedings of the 2012 IEEE International Symposium on Information Theory, 2012
Proceedings of the IEEE International Conference on Communication Systems, 2012
2011
Open or close: On the sharing of femtocells.
Proceedings of the INFOCOM 2011. 30th IEEE International Conference on Computer Communications, 2011
Multi-channel MAC protocol for QoS support in ad-hoc network.
Proceedings of the 2011 IEEE Consumer Communications and Networking Conference, 2011
2010
Traffic density based power control scheme for femto AP.
Proceedings of the IEEE 21st International Symposium on Personal, 2010
On the pricing of femtocell services.
Proceedings of the Conference on the Future of the Internet 2010, 2010
2009
Decentralized power control scheme in femtocell networks: A game theoretic approach.
Proceedings of the IEEE 20th International Symposium on Personal, 2009