34 accepted papers
The scarcity of high-quality training data presents a fundamental bottleneck to scaling machine learning models. This challenge is particularly acute in recommendation systems, where extreme sparsity in user interactions leads to rugged optimization landscapes and poor generalization. We propose the…
Given an unnormalized probability density $\pi\propto\mathrm{e}^{-V}$, estimating its normalizing constant $Z=\int_{\mathbb{R}^d}\mathrm{e}^{-V(x)}\mathrm{d}x$ or free energy $F=-\log Z$ is a crucial problem in Bayesian statistics, statistical mechanics, and machine learning. It is challenging espec…
Accurate medical diagnosis often relies on both textual self-reported symptoms and structured medical examination results of patients. However, these examinations vary significantly in cost—measured in time, money, or patient discomfort---creating a challenging trade-off between diagnostic accuracy
Learning discrete neural samplers is challenging due to the lack of gradients and combinatorial complexity. While stochastic optimal control (SOC) and Schrödinger bridge (SB) provide principled solutions, efficient SOC solvers like adjoint matching (AM), which excel in continuous domains, remain une…
Diffusion large language models (dLLMs) are promising alternatives to autoregressive large language models (AR-LLMs), as they potentially allow higher inference throughput. Reinforcement learning (RL) is a crucial component for dLLMs to achieve comparable performance with AR-LLMs on important tasks,…
Fake news detection methods based on writing style have achieved remarkable progress. However, as adversaries increasingly imitate the style of authentic news, the effectiveness of such approaches is gradually diminishing. Recent research has explored incorporating large language models (LLMs) to en
Audio synthesis has broad applications in multimedia. Recent advancements have made it possible to generate relevant audios from inputs describing an audio scene, such as images or texts. However, the immersiveness and expressiveness of the generation are limited. One possible problem is that existi
Effective communication is crucial for multi-agent cooperation in partially observable environments. However, a fundamental trilemma exists among task performance, communication efficiency, and human interpretability. To resolve this, we propose a multi-agent communication framework via $\textbf{G}$…
Manipulators are essential for advancing orchard robotics tasks such as pruning and harvesting, which require precise, dexterous motion in cluttered and unstructured environments. Off-the-shelf industrial arms, while readily available, often lack the reach and dexterity required for these settings. …
Sampling from discrete distributions with multiple modes and energy barriers is fundamental to machine learning and computational physics. Recent discrete neural samplers like MDNS suffer from mode collapse and fail to sample high-energy barrier regions between modes, which is critical for free ener…
The task of learning a diffusion-based neural sampler for drawing samples from an unnormalized target distribution can be viewed as a stochastic optimal control problem on path measures. However, the training of neural samplers can be challenging when the target distribution is multimodal with signi…
Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these tasks remain challenging because diffusion models have intractable likelihoods, which creates a barrier for directly applying popular policy-gradient type met…
Cross-domain offline reinforcement learning leverages a source dataset to improve policy learning in a data-scarce target domain, but dynamics mismatch makes many source transitions kinematically infeasible and can cause negative transfer. Recent non-parametric geometric methods (e.g., standard opti…
Integrating large language models (LLMs) into recommender systems has created new opportunities for improving recommendation quality. However, a comprehensive benchmark is needed to thoroughly evaluate and compare the recommendation capabilities of LLMs with traditional recommender systems. In this…
Discrete diffusion models have emerged as a powerful generative modeling framework for discrete data with successful applications spanning from text generation to image synthesis. However, their deployment faces challenges due to the high dimensionality of the state space, necessitating the developm…
In this letter, we present a high-rate and robust multi-sensor fusion framework for state estimation of humanoid robots, named HR<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula>-KIL
We study the problem of learning a neural sampler to generate samples from discrete state spaces where the target probability mass function $\pi\propto\mathrm{e}^{-U}$ is known up to a normalizing constant, which is an important task in fields such as statistical physics, machine learning, combinato…
Recent research in cooperative Multi-Agent Reinforcement Learning (MARL) has shown significant interest in utilizing Graph Neural Networks (GNNs) for communication learning due to their strong ability to process feature and topological information of agents into message representations for downstrea
With the growing size of data and models in Large Recommendation Models, the time required for debugging has become increasingly prohibitive, underscoring the urgent need for effective guidance in parameter configuration. The Scaling Law (SL) offers analogous guidance in the Sequential Language doma…
We consider the outstanding problem of sampling from an unnormalized density that may be non-log-concave and multimodal. To enhance the performance of simple Markov chain Monte Carlo (MCMC) methods, techniques of annealing type have been widely used. However, quantitative theoretical guarantees of t…
In object manipulation, movements are inherently restricted by object geometry and dynamics. Humans use an intuitive understanding of physics while grasping objects, resulting in an efficient application of manipulation force. This involves a ‘common sense’ awareness of how objects behave in the phy
Recent advancement in computer vision has significantly lowered the barriers to artistic creation. Exemplar-based image translation methods have attracted much attention due to flexibility and controllability. However, these methods hold assumptions regarding semantics or require semantic informatio…
User Behavior Modeling (UBM) plays a critical role in user interest learning, which has been extensively used in recommender systems. Crucial interactive patterns between users and items have been exploited, which brings compelling improvements in many recommendation tasks. In this paper, we attempt…
Recently, reinforcement learning (RL) is often used for learning the strategy of peg-in-hole tasks. However, traditional state representation of PiH RL might be either redundant or abstract, which leads to unnecessary learning steps and incompatibility with mathematical training optimization. To iss
Crowdsourcing is a favorable computing paradigm for processing computer-hard tasks by harnessing human intelligence. However, generic crowdsourcing systems may lead to privacy-leakage through the sharing of worker data. To tackle this problem, we propose a novel approach, called iFedCrowd (incentive…
This paper describes NIO system for audio-visual diarization and recognition in the Multimodal Information Based Speech Processing (MISP) Challenge 2022. In our system, we proposed combining end-to-end audio-visual neural speaker diarization model and Channel-wise Av-fusion encoder with speaker sign…
In few-shot learning, methods are enslaved to the scarce labeled data, resulting in suboptimal embedding. Recent studies learn the embedding network by other large-scale labeled data. However, the trained network may give rise to the distorted embedding of target data. We argue two respects are requ…
Machine learning systems deployed in the wild are often trained on a source distribution but deployed on a different target distribution. Unlabeled data can be a powerful point of leverage for mitigating these distribution shifts, as it is frequently much more available than labeled data and can oft…
Click-through rate (CTR) estimation plays as a core function module in various personalized online services, including online advertising, recommender systems, and web search etc. From 2015, the success of deep learning started to benefit CTR estimation performance and now deep CTR models have been…
Distribution shifts—where the training distribution differs from the test distribution—can substantially degrade the accuracy of machine learning (ML) systems deployed in the wild. Despite their ubiquity in the real-world deployments, these distribution shifts are under-represented in the datasets w…
Intra-saliency and inter-saliency cues have been extensively studied for co-saliency detection (Co-SOD). Model-based methods produce coarse Co-SOD results due to hand-crafted intra- and inter-saliency features. Current data-driven models exploit inter-saliency cues, but undervalue the potential powe…
A robot in the future may initially has a good learning capability but an empty library of movements. It gradually enriches its library of movements through human demonstrations. Dynamic Movement Primitives (DMPs) has been proved to be an effective way to represent trajectories. Trajectories are cla…
To actively assist human walking and balance recovery, a unified active assistance control framework of the hip exoskeleton is proposed in this paper. At the beginning of this paper, the condition of active assistance is analyzed. And then, a novel virtual stiffness model is proposed based on the an…