Search Results for author:
Found 55 papers, 16 papers with code
AI WALKUP: A Computer-Vision Approach to Quantifying MDS-UPDRS in Parkinson's Disease
Parkinson's Disease (PD) is the second most common neurodegenerative disorder.
Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning
As intelligent agents, LLMs need to have the capabilities of task planning, long-term memory, and the ability to leverage external tools to achieve satisfactory performance.
Horizon-Free Regret for Linear Markov Decision Processes
A recent line of works showed regret bounds in reinforcement learning (RL) can be (nearly) independent of planning horizon, a. k. a.~the horizon-free bounds.
ResLoRA: Identity Residual Mapping in Low-Rank Adaption
As one of the most popular parameter-efficient fine-tuning (PEFT) methods, low-rank adaptation (LoRA) is commonly applied to fine-tune large language models (LLMs).
RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering
Based on our findings, we propose Time-Aware Adaptive Retrieval (TA-ARE), a simple yet effective method that helps LLMs assess the necessity of retrieval without calibration or additional training.
HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition
Large language models (LLMs) have emerged as a promising alternative to expensive human evaluations.
We Choose to Go to Space: Agent-driven Human and Multi-Robot Collaboration in Microgravity
We present SpaceAgents-1, a system for learning human and multi-robot collaboration (HMRC) strategies under microgravity conditions.
Text Diffusion with Reinforced Conditioning
Diffusion models have demonstrated exceptional capability in generating high-quality images, videos, and audio.
Improving Domain Adaptation through Extended-Text Reading Comprehension
To enhance the domain-specific capabilities of large language models, continued pre-training on a domain-specific corpus is a prevalent method.
BS-PLCNet: Band-split Packet Loss Concealment Network with Multi-task Learning Framework and Multi-discriminators
Packet loss is a common and unavoidable problem in voice over internet phone (VoIP) systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
SELM: Speech Enhancement Using Discrete Tokens and Language Models
Given the intrinsic similarity between speech generation and speech enhancement, harnessing semantic information holds potential advantages for speech enhancement tasks.
Optimal Multi-Distribution Learning
Focusing on a hypothesis class of Vapnik-Chervonenkis (VC) dimension $d$, we propose a novel algorithm that yields an $varepsilon$-optimal randomized hypothesis with a sample complexity on the order of $(d+k)/\varepsilon^2$ (modulo some logarithmic factor), matching the best-known lower bound.
OSM vs HD Maps: Map Representations for Trajectory Prediction
While High Definition (HD) Maps have long been favored for their precise depictions of static road elements, their accessibility constraints and susceptibility to rapid environmental changes impede the widespread deployment of autonomous driving, especially in the motion forecasting task.
Turn-Level Active Learning for Dialogue State Tracking
Dialogue state tracking (DST) plays an important role in task-oriented dialogue systems.
CITB: A Benchmark for Continual Instruction Tuning
In this work, we establish a CIT benchmark consisting of learning and evaluation protocols.
Democratizing Reasoning Ability: Tailored Learning from Large Language Model
In this paper, we propose a tailored learning approach to distill such reasoning ability to smaller LMs to facilitate the democratization of the exclusive reasoning ability.
Auto Search Indexer for End-to-End Document Retrieval
Generative retrieval, which is a new advanced paradigm for document retrieval, has recently attracted research interests, since it encodes all documents into the model and directly generates the retrieved documents.
How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances
Although large language models (LLMs) are impressive in solving various tasks, they can quickly be outdated after deployment.
An Exploration of Task-decoupling on Two-stage Neural Post Filter for Real-time Personalized Acoustic Echo Cancellation
Utilization of speaker representation has extended the frontier of AEC, thus attracting many researchers' interest in personalized acoustic echo cancellation (PAEC).
Calibrating LLM-Based Evaluator
Recent advancements in large language models (LLMs) on language modeling and emergent capabilities make them a promising reference-free evaluator of natural language generation quality, and a competent alternative to human evaluation.
Universal scaling relation and criticality in metabolism and growth of Escherichia coli
The metabolic network plays a crucial role in regulating bacterial metabolism and growth, but it is subject to inherent molecular stochasticity.
Classification with Deep Neural Networks and Logistic Loss
In this paper, we aim to fill this gap by establishing a novel and elegant oracle-type inequality, which enables us to deal with the boundedness restriction of the target function, and using it to derive sharp convergence rates for fully connected ReLU DNN classifiers trained with logistic loss.
TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis
The gradual nature of a diffusion process that synthesizes samples in small increments constitutes a key ingredient of Denoising Diffusion Probabilistic Models (DDPM), which have presented unprecedented quality in image synthesis and been recently explored in the motion domain.
Settling the Sample Complexity of Online Reinforcement Learning
While a number of recent works achieved asymptotically minimal regret in online RL, the optimality of these results is only guaranteed in a ``large-sample'' regime, imposing enormous burn-in cost in order for their algorithms to operate optimally.
Sharper Model-free Reinforcement Learning for Average-reward Markov Decision Processes
In the online setting, we propose model-free RL algorithms based on reference-advantage decomposition.
Dual-Alignment Pre-training for Cross-lingual Sentence Embedding
Recent studies have shown that dual encoder models trained with the sentence-level translation ranking task are effective methods for cross-lingual sentence embedding.
Pre-training Language Model as a Multi-perspective Course Learner
Besides, two self-correction courses are proposed to bridge the chasm between the two encoders by creating a "correction notebook" for secondary-supervision.
Two-stage Neural Network for ICASSP 2023 Speech Signal Improvement Challenge
Achieving 0. 446 in the final score and 0. 517 in the P. 835 score, our system ranks 4th in the non-real-time track.
Two-step Band-split Neural Network Approach for Full-band Residual Echo Suppression
This paper describes a Two-step Band-split Neural Network (TBNN) approach for full-band acoustic echo cancellation.
Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments
We further initiate the study on model-free algorithms with variance-dependent regret bounds by designing a reference-function-based algorithm with a novel capped-doubling reference update schedule.
Decoupling MaxLogit for Out-of-Distribution Detection
We demonstrate the effectiveness of our logit-based OOD detection methods on CIFAR-10, CIFAR-100 and ImageNet and establish state-of-the-art performance.
RoChBert: Towards Robust BERT Fine-tuning for Chinese
Despite of the superb performance on a wide range of tasks, pre-trained language models (e. g., BERT) have been proved vulnerable to adversarial texts.
Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning
Meanwhile, we show that to achieve $\tilde{O}(\mathrm{poly}(S, A, H)\sqrt{K})$ regret, the number of batches is at least $\Omega\left(H/\log_A(K)+ \log_2\log_2(K) \right)$, which matches our upper bound up to logarithmic terms.
Predicting Blossom Date of Cherry Tree With Support Vector Machine and Recurrent Neural Network
Our project probes the relationship between temperatures and the blossom date of cherry trees.
Hybrid Supervised and Reinforcement Learning for the Design and Optimization of Nanophotonic Structures
From higher computational efficiency to enabling the discovery of novel and complex structures, deep learning has emerged as a powerful framework for the design and optimization of nanophotonic circuits and components.
A Pilot Study of Relating MYCN-Gene Amplification with Neuroblastoma-Patient CT Scans
Neuroblastoma is one of the most common cancers in infants, and the initial diagnosis of this disease is difficult.
GANimator: Neural Motion Synthesis from a Single Sequence
We present GANimator, a generative model that learns to synthesize novel motions from a single, short motion sequence.
Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topics
Recent work incorporates pre-trained word embeddings such as BERT embeddings into Neural Topic Models (NTMs), generating highly coherent topics.
Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies
This paper gives the first polynomial-time algorithm for tabular Markov Decision Processes (MDP) that enjoys a regret bound \emph{independent on the planning horizon}.
Long-Tailed Classification with Gradual Balanced Loss and Adaptive Feature Generation
The real-world data distribution is essentially long-tailed, which poses great challenge to the deep model.
Ranked #14 on
Long-tail Learning
on CIFAR-100-LT (ρ=10)
PromptBERT: Improving BERT Sentence Embeddings with Prompts
We propose PromptBERT, a novel contrastive learning method for learning better sentence representation.
Callee: Recovering Call Graphs for Binaries with Transfer and Contrastive Learning
Recovering binary programs' call graphs is crucial for inter-procedural analysis tasks and applications based on them. transfer One of the core challenges is recognizing targets of indirect calls (i. e., indirect callees).
Improving Non-autoregressive Generation with Mixup Training
While pre-trained language models have achieved great success on various natural language understanding tasks, how to effectively leverage them into non-autoregressive generation tasks remains a challenge.
Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits
We study the optimal batch-regret tradeoff for batch linear contextual bandits.
Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks
The task requires models to generate personalized responses for a speaker given a few conversations from the speaker and a social network.
A New Metric on Symmetric Group and Applications to Block Permutation Codes
In this paper, by introducing a novel metric closely related to the block permutation metric, we build a bridge between some advanced algebraic methods and codes in the block permutation metric.
Information Theory Combinatorics Information Theory
Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP
With the new confidence sets, we obtain the follow regret bounds: For linear bandits, we obtain an $\tilde{O}(poly(d)\sqrt{1 + \sum_{k=1}^{K}\sigma_k^2})$ data-dependent regret bound, where $d$ is the feature dimension, $K$ is the number of rounds, and $\sigma_k^2$ is the \emph{unknown} variance of the reward at the $k$-th round.
Almost Optimal Model-Free Reinforcement Learningvia Reference-Advantage Decomposition
We study the reinforcement learning problem in the setting of finite-horizon1episodic Markov Decision Processes (MDPs) with S states, A actions, and episode length H. We propose a model-free algorithm UCB-ADVANTAGE and prove that it achieves \tilde{O}(\sqrt{H^2 SAT}) regret where T=KH and K is the number of episodes to play.
Nearly Minimax Optimal Reward-free Reinforcement Learning
In the planning phase, the agent needs to return a near-optimal policy for arbitrary reward functions.
Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon
Episodic reinforcement learning generalizes contextual bandits and is often perceived to be more difficult due to long planning horizon and unknown state-dependent transitions.
Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity
In this paper we consider the problem of learning an $\epsilon$-optimal policy for a discounted Markov Decision Process (MDP).
Almost Optimal Model-Free Reinforcement Learning via Reference-Advantage Decomposition
We study the reinforcement learning problem in the setting of finite-horizon episodic Markov Decision Processes (MDPs) with $S$ states, $A$ actions, and episode length $H$.
Regret Minimization for Reinforcement Learning by Evaluating the Optimal Bias Function
We present an algorithm based on the \emph{Optimism in the Face of Uncertainty} (OFU) principle which is able to learn Reinforcement Learning (RL) modeled by Markov decision process (MDP) with finite state-action space efficiently.
HAXMLNet: Hierarchical Attention Network for Extreme Multi-Label Text Classification
Extreme multi-label text classification (XMTC) addresses the problem of tagging each text with the most relevant labels from an extreme-scale label set.
AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification
We propose a new label tree-based deep learning model for XMTC, called AttentionXML, with two unique features: 1) a multi-label attention mechanism with raw text as input, which allows to capture the most relevant part of text to each label; and 2) a shallow and wide probabilistic label tree (PLT), which allows to handle millions of labels, especially for "tail labels".
