137 accepted papers
Large Language Models (LLMs) show remarkable code generation capabilities but often produce imperfect code with subtle bugs. A critical bottleneck for improving code quality is the scarcity of high-quality test cases. Existing approaches, primarily based on Supervised Fine-Tuning (SFT) over static d…
Recent advancements in Large Language Models (LLMs) have successfully employed search-based strategies to enhance code generation. However, existing methods typically rely on static, sparse public test cases for verification, leading to pseudo-correctness—where solutions overfit the visible public t…
Active inverse source localization and characterization (ISLC) in dynamic fields requires sequential decision making under partial observability, where a mobile sensor must infer latent source parameters from sparse, noisy readings. We introduce a belief-contraction-driven approach that unifies infe
Recent end-to-end robotic manipulation research increasingly adopts architectures inspired by large language models to enable robust manipulation. However, a critical challenge arises from severe distribution shifts between robotic action data, primarily due to substantial numerical variations in ac
Current evaluation for Large Language Model (LLM) code agents predominantly focus on generating functional code in single-turn scenarios, which fails to evaluate the agent's capability for continuous code optimization and multi-turn iterative development. To bridge this gap, we introduce CATArena, a…
Humanoid Whole-Body Controllers trained with reinforcement learning (RL) have recently achieved remarkable performance, yet many target a single robot embodiment. Variations in dynamics, degrees of freedom (DoFs), and kinematic topology still hinder a single policy from commanding diverse humanoids.…
Uncertainty quantification (UQ) is an important technique for ensuring the trustworthiness of LLMs, given their tendency to hallucinate. Existing state-of-the-art UQ approaches for free-form generation rely heavily on sampling, which incurs high computational cost and variance. In this work, we prop…
The rapid advancement of humanoid robotics has intensified the need for robust and adaptable controllers to enable stable and efficient locomotion across diverse platforms. However, developing such controllers remains a significant challenge because existing solutions are tailored to specific robot …
Learning versatile whole-body skills by tracking various human motions is a fundamental step toward general-purpose humanoid robots. This task is particularly challenging because a single policy must master a broad repertoire of motion skills while ensuring stability over long-horizon sequences. To …
Reinforcement learning (RL) for large language models (LLMs) relies on imperfect reward supervision, necessitating constraints on policy updates to prevent overfitting. Nevertheless, the widely adopted KL constraint over-penalizes actions with low reference probabilities and lacks the sparsity to di…
Modern robotic manipulation primarily relies on visual observations in a 2D color space for skill learning but suffers from poor generalization. In contrast, humans, living in a 3D world, depend more on physical properties-such as distance, size, and shape-than on texture when interacting with objec…
In recent years, LLM-based multi-agent systems (MAS) have advanced rapidly, using a router to decompose tasks and delegate subtasks to specialized agents. A natural way to expand capability is to **scale up the agent pool** by continually integrating new functional agents or tool interfaces, but nai…
Offline Reinforcement Learning (RL) enables policy improvement from fixed datasets without online interactions, making it highly suitable for real-world applications lacking efficient simulators. Despite its success in the single-agent setting, offline multi-agent RL remains a challenge, especially
Ad hoc teamwork (AHT) requires agents to collaborate with previously unseen teammates, which is crucial for many real-world applications. The core challenge of AHT is to develop an ego agent that can predict and adapt to unknown teammates on the fly. Conventional RL-based approaches optimize a singl
Despite advances in physics-based 3D motion synthesis, current methods face key limitations: reliance on pre-reconstructed 3D Gaussian Splatting (3DGS) built from dense multi-view images with time-consuming per-scene optimization; physics integration via either inflexible, hand-specified attributes
The implicit policy of maintaining relatively stable acceptance rates at top AI conferences, despite exponentially growing submissions, introduces a critical structural vulnerability. This position paper characterizes a new systemic threat we term ***Agentic Denominator Gaming***, in which a malicio…
Is monolithic scaling the only path to AGI? This paper challenges the dogma that purely scaling a single model is enough to achieve universal super-intelligence. Instead, we identify Agentic AI as the necessary evolution for handling complex, real-world task distributions to achieve AGI in the human…
Offline reinforcement learning (RL) learns policies from fixed datasets, thereby avoiding costly or unsafe environment interactions. However, its reliance on finite static datasets inherently restricts the ability to generalize beyond the training distribution. Prior solutions based on synthetic dat…
Recent advances in vision-language-action (VLA) models have motivated the extension of their capabilities to embodied settings, where reinforcement learning (RL) offers a principled way to optimize task success through interaction. However, existing methods remain fragmented, lacking both a unified …
Real-world data collection for robotics is costly and resource-intensive, requiring skilled operators and expensive hardware. Simulations offer a scalable alternative but often fail to achieve sim-to-real generalization due to geometric and visual gaps. To address these challenges, we propose a 3D-p…
In this work, we reveal that Large Language Models (LLMs) possess intrinsic behavioral plasticity—akin to chameleons adapting their coloration to environmental cues—that can be *exposed* through token-conditional generation and *stabilized* via reinforcement learning. Specifically, by conditioning g…
Learning-based whole-body controllers have become a key driver for humanoid robots, yet most existing approaches require robot-specific training. In this paper, we study the problem of cross-embodiment humanoid control and show that a single policy can robustly generalize across a wide range of huma…
Deploying Large Language Models to data-scarce programming domains poses significant challenges, particularly for kernel synthesis on emerging Domain-Specific Architectures where a "Data Wall" limits available training data. While models excel on data-rich platforms like CUDA, they suffer catastroph…
Recent Vision-Language-Action (VLA) models show potential to generalize across embodiments but struggle to quickly align with a new robot’s action space when high-quality demonstrations are scarce, especially for bipedal humanoids. We present TrajBooster, a cross-embodiment framework that leverages …
Achieving generalizable whole-body motion control is essential for deploying humanoid robots in real-world environments. However, existing MLP-based policies trained under partial observations often suffer from limited expressiveness and struggle to maintain global consistency. These shortcomings ma
Advances in Large Language Models (LLMs) have enabled a new class of \textbf{\textit{self-evolving agents}} that autonomously improve through interaction with the environment, demonstrating strong capabilities. However, self-evolution also introduces novel risks overlooked by current safety research…
Locomotion is a fundamental skill for humanoid robots. However, most existing works made locomotion a single, tedious, unextendable, and passive movement. This limits the kinematic capabilities of humanoid robots. In contrast, humans possess versatile athletic abilities—running, jumping, hopping, an…
The rapid advancement of Large Language Models (LLMs) has catalyzed the development of multi-agent systems, where multiple LLM-based agents collaborate to solve complex tasks. However, existing systems predominantly rely on centralized coordination, which introduces scalability bottlenecks, limits…
Reinforcement Learning has revolutionized decision-making processes in dynamic environments, yet it often struggles with autonomously detecting and achieving goals without clear feedback signals. For example, in a Source Term Estimation problem, the lack of precise environmental information makes it…
Traversing risky terrains with sparse footholds poses a significant challenge for humanoid robots, requiring precise foot placements and stable locomotion. Existing approaches designed for quadrupedal robots often fail to generalize to humanoid robots due to differences in foot geometry and unstable…
Given the large volume of side information from different modalities, multimodal recommender systems have become increasingly vital, as they exploit richer semantic information beyond user-item interactions. Recent works highlight that leveraging Graph Convolutional Networks (GCNs) to explicitly mod…
To address these limitations, we propose BDC, a novel framework that Boosts reasoning exploration via multi-agent collaboration, Disentangles heterogeneous data into specialized experts, and Customizes solutions through dynamic model composition. BDC integrates a Monte Carlo Tree-of-Agents algorithm…
Code generation is a critical reasoning task for large language models (LLMs). Recent advancements have focused on optimizing the thought process of code generation, achieving significant improvements. However, such thought process lacks effective process supervision, making it hard to optimize the…
The performance of offline reinforcement learning (RL) is sensitive to the proportion of high-return trajectories in the offline dataset. However, in many simulation environments and real-world scenarios, there are large ratios of low-return trajectories rather than high-return trajectories, which m…
With the impressive reasoning and text generation capabilities of large language models (LLMs), methods leveraging multiple LLMs to debate each other have garnered increasing attention. However, existing debate-based approaches remain limited in effectiveness in structured and detailed domains repre…
Microscopic traffic simulation has become an important tool for autonomous driving training and testing. Although recent data-driven approaches advance realistic behavior generation, their learning still relies primarily on a single real-world dataset, which limits their diversity and thereby hinder
Second-order Online Kernel Learning (OKL) has attracted considerable research interest due to its promising predictive performance in streaming environments. However, existing second-order OKL approaches suffer from at least quadratic time complexity with respect to the pre-set budget, rendering the
Realignment becomes necessary when a language model (LM) fails to meet expected performance. We propose a flexible realignment framework that supports quantitative control of alignment degree during training and inference. This framework incorporates **Training-time Realignment (TrRa)**, which effic…
Recent advances in reinforcement learning (RL) have demonstrated the powerful exploration capabilities and multimodality of generative diffusion-based policies. While substantial progress has been made in offline RL and off-policy RL settings, integrating diffusion policies into on-policy frameworks…
Evaluating the performance of LLMs in multi-turn human-agent interactions presents significant challenges, particularly due to the complexity and variability of user behavior. In this paper, we introduce HammerBench, a novel benchmark framework for assessing LLMs’ function-calling capabilities in re…
Humans possess delicate dynamic balance mechanisms that enable them to maintain stability across diverse terrains and under extreme conditions. However, despite significant advances recently, existing locomotion algorithms for humanoid robots are still struggle to traverse extreme environments, espe
Obtaining a generalizable reward model is crucial in Reinforcement Learning from Human Feedback (RLHF) as it enables correctly evaluating unseen prompt-response pairs. However, existing reward models lack this ability, as they are typically trained by increasing the reward gap between chosen and rej…
Humanoid robots are promising to acquire various skills by imitating human behaviors. However, existing algorithms are only capable of tracking smooth, low-speed human motions, even with delicate reward and curriculum design. This paper presents a physics-based humanoid control framework, aiming to…
In-context learning with large language models (LLMs) delivers strong few-shot performance by choosing few-shot demonstrations from the entire training dataset. However, previous few-shot in-context learning methods, which calculate similarity scores for choosing demonstrations, incur high computati…
Agents built on large language models (LLMs) have excelled in turn-by-turn human-AI collaboration but struggle with simultaneous tasks requiring real-time interaction. Latency issues and the challenge of inferring variable human strategies hinder their ability to make autonomous decisions without ex…
Reinforcement Learning (RL) has shown its remarkable and generalizable capability in legged locomotion through sim-to-real transfer. However, while adaptive methods like domain randomization are expected to enhance policy robustness across diverse environments, they potentially compromise the policy
Recent advances in Multimodal Large Language Models (MLLMs) have enabled the development of mobile agents that can understand visual inputs and follow user instructions, unlocking new possibilities for automating complex tasks on mobile devices. However, applying these models to real-world mobile sc…
Debugging is a critical aspect of LLM’s coding ability. Early debugging efforts primarily focused on code-level analysis, which often falls short when addressing complex programming errors that require a deeper understanding of algorithmic logic. Recent advancements in large language models (LLMs) h
With the widespread deployment of generative language models, concerns about safety issues have continuously grown. High-quality fine-tuning data generated from red teaming plays a crucial role in the model’s safety. Recently, automated red teaming approaches have been proposed to create test cases.
Recent research on Reasoning of Large Language Models (LLMs) has sought to further enhance their performance by integrating meta-thinking—enabling models to monitor, evaluate, and control their reasoning processes for more adaptive and effective problem-solving. However, current single-agent work la…
An important challenge in multi-agent reinforcement learning is partial observability, where agents cannot access the global state of the environment during execution and can only receive observations within their field of view. To address this issue, previous works typically use the dimensional-wis…
Tree search methods have demonstrated impressive performance in code generation. Previous methods combine tree search with reflection that summarizes past mistakes to achieve iterative improvement. However, these methods face significant challenges. First, they search directly within the code langua
While large language models (LLMs) have significantly advanced mathematical reasoning, Process Reward Models (PRMs) have been developed to evaluate the logical validity of reasoning steps. However, PRMs still struggle with out-of-distribution (OOD) challenges. This paper identifies the OOD issues in…
Large language models have demonstrated impressive value in performing as autonomous agents when equipped with external tools and API calls. Nonetheless, effectively harnessing their potential for executing complex tasks crucially relies on enhancements in their function-calling capabilities. This p…
Diffusion policies have shown promise in learning complex behaviors from demonstrations, particularly for tasks requiring precise control and long-term planning. However, they face challenges in robustness when encountering distribution shifts. This paper explores improving diffusion-based imitation…
Large language models (LLMs) often succumb to users’ viewpoints when faced with conflicting perspectives. We identify two key biases underlying this issue : stance homogeneity bias and human preference bias. To address these biases, we propose a novel two-stage training framework: Multi-stance Discu
Survey papers are foundational to the scholarly progress of research communities, offering structured overviews that guide both novices and experts across disciplines. However, the recent surge of AI-generated surveys, especially enabled by large language models (LLMs), has transformed this traditio…
Evaluating large language models (LLMs) poses significant challenges, particularly due to issues of data contamination and the leakage of correct answers. To address these challenges, we introduce ThinkBench, a novel evaluation framework designed to robustly evaluate the reasoning capability of LLMs…
The practical use of reinforcement learning (RL) requires handling diverse settings, including online, offline, and offline-to-online learning. Instead of developing separate algorithms for each setting, we propose Uni-RL, a unified model-free RL framework that addresses all these scenarios within a…
Legged locomotion over various terrains is challenging and requires precise perception of the robot and its surroundings from both proprioception and vision. However, learning directly from high-dimensional visual input is often data-inefficient and intricate. To address this issue, traditional meth
Given a relational database (RDB), how can we predict missing column values in some target table of interest? Although RDBs store vast amounts of rich, informative data spread across interconnected tables, the progress of predictive machine learning models as applied to such tasks arguably falls we…
Recent works like Tree-of-Thought (ToT) and Reasoning via Planning (RAP) aim to augment the multi-step reasoning capabilities of LLMs by using tree-search algorithms. These methods rely on prompting a pre-trained model to serve as a value function and focus on problems with low search depth. As a re…
Reinforcement Learning (RL) has recently achieved remarkable success in robotic control. However, most works in RL operate in simulated environments where privileged knowledge (e.g., dynamics, surroundings, terrains) is readily available. Conversely, in real-world scenarios, robot agents usually rel…
In offline reinforcement learning (RL), the performance of the learned policy highly depends on the quality of offline datasets. However, the offline dataset contains very limited optimal trajectories in many cases. This poses a challenge for offline RL algorithms, as agents must acquire the ability…
One important property of DIstribution Correction Estimation (DICE) methods is that the solution is the optimal stationary distribution ratio between the optimized and data collection policy. In this work, we show that DICE-based methods can be viewed as a transformation from the behavior distributi…
Diffusion models have garnered widespread attention in Reinforcement Learning (RL) for their powerful expressiveness and multimodality. It has been verified that utilizing diffusion policies can significantly improve the performance of RL algorithms in continuous control tasks by overcoming the limi…
Robotic simulation today remains challenging to scale up due to the human efforts required to create diverse simulation tasks and scenes. Simulation-trained policies also face scalability issues as many sim-to-real methods focus on a single task. To address these challenges, this work proposes GenSi…
Learning a generalist embodied agent capable of completing multiple tasks poses challenges, primarily stemming from the scarcity of action-labeled robotic datasets. In contrast, a vast amount of human videos exist, capturing intricate tasks and interactions with the physical world. Promising prospec…
Offline reinforcement learning (RL) aims to learn policies from pre-existing datasets without further interactions, making it a challenging task. Q-learning algorithms struggle with extrapolation errors in offline settings, while supervised learning methods are constrained by model expressiveness. R…
In this study, we investigate the DIstribution Correction Estimation (DICE) methods, an important line of work in offline reinforcement learning (RL) and imitation learning (IL). DICE-based methods impose state-action-level behavior constraint, which is an ideal choice for offline learning. However,…
We present OmniH2O (Omni Human-to-Humanoid), a learning-based system for whole-body humanoid teleoperation and autonomy. Using kinematic pose as a universal control interface, OmniH2O enables various ways for a human to control a full-sized humanoid with dexterous hands, including using real-time te…
Argumentative essay generation (AEG) aims to generate complete texts on specific controversial topics or debates. Although current AEG methods can generate individual opinions, they often overlook the high-level connections between these opinions. This often leads to the generated results being mire…
Language models as intelligent agents push the boundaries of sequential decision-making agents but struggle with limited knowledge of environmental dynamics and exponentially huge action space. Recent efforts like GLAM and TWOSOME manually constrain the action space to a restricted subset and employ…
Although Retrieval-Augmented Large Language Models (RALMs) demonstrate their superiority in terms of factuality, they do not consistently outperform the original retrieval-free Language Models (LMs). Our experiments reveal that this example-level performance inconsistency exists not only between ret…
Recent progress in vision language foundation models has shown their ability to understand multimodal data and resolve complicated vision language tasks, including robotics manipulation. We seek a straightforward way of making use of existing vision-language models (VLMs) with simple fine-tuning on…
Zero-shot coordination (ZSC) is a new cooperative multi-agent reinforcement learning (MARL) challenge that aims to train an ego agent to work with diverse, unseen partners during deployment. The significant difference between the deployment-time partners' distribution and the training partners' dist…
E-commerce pre-sales dialogue aims to understand and elicit user needs and preferences for the items they are seeking so as to provide appropriate recommendations. Conversational recommender systems (CRSs) learn user representation and provide accurate recommendations based on dialogue context, but…
Diffusion models have demonstrated highly-expressive generative capabilities in vision and NLP. Recent studies in reinforcement learning (RL) have shown that diffusion models are also powerful in modeling complex policies or trajectories in offline datasets. However, these works have been limited to…
This paper introduces a distributed, GPU-centric experience replay system, GEAR, designed to perform scalable reinforcement learning (RL) with large sequence models (such as transformers). With such models, existing systems such as Reverb face considerable bottlenecks in memory, computation, and com…
Empathetic dialogue is an indispensable part of building harmonious social relationships and contributes to the development of a helpful AI. Previous approaches are mainly based on fine small-scale language models. With the advent of ChatGPT, the application effect of large language models (LLMs) in…
Over recent decades, sequential decision-making tasks are mostly tackled with expert systems and reinforcement learning. However, these methods are still incapable of being generalizable enough to solve new tasks at a low cost. In this article, we discuss a novel paradigm that leverages Transformer-…
Modeling multi-variate time-series (MVTS) data is a long-standing research subject and has found wide applications. Recently, there is a surge of interest in modeling spatial relations between variables as graphs, i.e., first learning one static graph for each dataset and then exploiting the graph s…
An intelligent conversational agent (a.k.a., chat-bot) could embrace conversational technologies to obtain user preferences online, to overcome inherent limitations of recommender systems trained over the offline historical user behaviors. In this paper, we propose CORE, a new offline-training and o…
Robots are traditionally bounded by a fixed embodiment during their operational lifetime, which limits their ability to adapt to their surroundings. Co-optimizing control and morphology of a robot, however, is often inefficient due to the complex interplay between the controller and morphology. In t…
While multi-agent trust region algorithms have achieved great success empirically in solving coordination tasks, most of them, however, suffer from a non-stationarity problem since agents update their policies simultaneously. In contrast, a sequential scheme that updates policies agent-by-agent pro…
With the development of the online education system, personalized education recommendation has played an essential role. In this paper, we focus on developing path recommendation systems that aim to generating and recommending an entire learning path to the given user in each session. Noticing that…
Deep reinforcement learning has recently emerged as an appealing alternative for legged locomotion over multiple terrains by training a policy in physical simulation and then transferring it to the real world (i.e., sim-to-real transfer). Despite considerable progress, the capacity and scalability o…
Real-world data usually exhibits a long-tailed distribution, with a few frequent labels and a lot of few-shot labels. The study of institution name normalization is a perfect application case showing this phenomenon: there are many institutions worldwide, with enormous variations of their names in t…
Visual imitation learning enables reinforcement learning agents to learn to behave from expert visual demonstrations such as videos or image sequences, without explicit, well-defined rewards. Previous reseaches either adopt supervised learning techniques or induce simple and coarse scalar rewards f…
Offline reinforcement learning (RL) aims at learning policies from previously collected static trajectory data without interacting with the real environment. Recent works provide a novel perspective by viewing offline RL as a generic sequence generation problem, adopting sequence models such as Tran…
CLIP has shown a remarkable zero-shot capability on a wide range of vision tasks. Previously, CLIP is only regarded as a powerful visual encoder. However, after being pre-trained by language supervision from a large amount of image-caption pairs, CLIP itself should also have acquired some few-shot a…
Goal-conditioned reinforcement learning (GCRL), related to a set of complex RL problems, trains an agent to achieve different goals under particular scenarios. Compared to the standard RL solutions that learn a policy solely depending on the states or observations, GCRL additionally requires the age…
Goal-oriented Reinforcement Learning (GoRL) is a promising approach for scaling up RL techniques on sparse reward environments requiring long horizon planning. Recent works attempt to build suitable abstraction graph of the environment and enhance GoRL with classical graphical methods such as shorte…
This paper introduces Honor of Kings Arena, a reinforcement learning (RL) environment based on the Honor of Kings, one of the world’s most popular games at present. Compared to other environments studied in most previous work, ours presents new generalization challenges for competitive reinforcement…
Prevailing methods for relation prediction in heterogeneous graphs aim at learning latent representations (i.e., embeddings) of observed nodes and relations, and thus are limited to the transductive setting where the relation types must be known during training. Here, we propose ANalogy SubGraphE…
Prediction over tabular data is an essential and fundamental problem in many important downstream tasks. However, existing methods either take a data instance of the table independently as input or do not fully utilize the multi-row features and labels to directly change and enhance the target data…
Large sequence models (SM) such as GPT series and BERT have displayed outstanding performance and generalization capabilities in natural language process, vision and recently reinforcement learning. A natural follow-up question is how to abstract multi-agent decision making also as an sequence model…
Program representation, which aims at converting program source code into vectors with automatically extracted features, is a fundamental problem in programming language processing (PLP). Recent work tries to represent programs with neural networks based on source code structures. However, such meth…
Offline reinforcement learning (RL) aims at learning effective policies from historical data without extra environment interactions. During our experience of applying offline RL, we noticed that previous offline RL benchmarks commonly involve significant reality gaps, which we have identified includ…
Span-based methods with the neural networks backbone have great potential for the nested named entity recognition (NER) problem. However, they face problems such as degenerating when positive instances and negative instances largely overlap. Besides, the generalization ability matters a lot in neste…
As the final stage of the multi-stage recommender system (MRS), re-ranking directly affects users’ experience and satisfaction by rearranging the input ranking lists, and thereby plays a critical role in MRS. With the advances in deep learning, neural re-ranking has become a trending topic and been…
While end-to-end neural machine translation (NMT) has achieved impressive progress, noisy input usually leads models to become fragile and unstable. Generating adversarial examples as the augmented data has been proved to be useful to alleviate this problem. Existing methods for adversarial example…
As a challenging multi-player card game, DouDizhu has recently drawn much attention for analyzing competition and collaboration in imperfect-information games. In this paper, we propose PerfectDou, a state-of-the-art Doudizhu AI system that summits the game, in an actor-critic framework with a propo…
Recent progress in state-only imitation learning extends the scope of applicability of imitation learning to real-world settings by relieving the need for observing expert actions. However, existing solutions only learn to extract a state-to-action mapping policy from the data, without considering h…
Quality Diversity (QD) algorithms in population-based reinforcement learning aim to optimize agents' returns and diversity among the population simultaneously. It is conducive to solving exploration problems in reinforcement learning and potentially getting multiple good and diverse strategies. Howe…
A good state representation is crucial to solving complicated reinforcement learning (RL) challenges. Many recent works focus on designing auxiliary losses for learning informative representations. Unfortunately, these handcrafted objectives rely heavily on expert knowledge and may be sub-optimal. I…
This paper introduces a novel Self-supervised Fine-grained Dialogue Evaluation framework (SelF-Eval). The core idea is to model the correlation between turn quality and the entire dialogue quality. We first propose a novel automatic data construction method that can automatically assign fine-grained…
It is challenging for reinforcement learning (RL) algorithms to succeed in real-world applications. Take financial trading as an example, the market information is noisy yet imperfect and the macroeconomic regulation or other factors may shift between training and evaluation, thus it requires both g…
Algorithmic decisions made by machine learning models in high-stakes domains may have lasting impacts over time. However, naive applications of standard fairness criterion in static settings over temporal domains may lead to delayed and adverse effects. To understand the dynamics of performance disp…
One of the challenges of graph-based semi-supervised learning over ordinary supervised learning for classification tasks lies in label utilization. The direct use of ground-truth labels in graphs for training purposes can result in a parametric model learning trivial degenerate solutions (e.g., an…
Offline reinforcement learning (RL) tasks require the agent to learn from a pre-collected dataset with no further interactions with the environment. Despite the potential to surpass the behavioral policies, RL-based methods are generally impractical due to the training instability and bootstrapping…
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…
Cycle-consistent training is widely used for jointly learning a forward and inverse mapping between two domains of interest without the cumbersome requirement of collecting matched pairs within each domain. In this regard, the implicit assumption is that there exists (at least approximately) a groun…
Recent work on non-autoregressive neural machine translation (NAT) aims at improving the efficiency by parallel decoding without sacrificing the quality. However, existing NAT methods are either inferior to Transformer or require multiple decoding passes, leading to reduced speedup. We propose the G…
Document-level relation extraction aims to identify relations between entities in a whole document. Prior efforts to capture long-range dependencies have relied heavily on implicitly powerful representations learned through (graph) neural networks, which makes the model less transparent. To tackle t…
Searching for novel molecules with desired chemical properties is crucial in drug discovery. Existing work focuses on developing neural models to generate either molecular sequences or chemical graphs. However, it remains a big challenge to find novel and diverse compounds satisfying several propert…
In Goal-oriented Reinforcement learning, relabeling the raw goals in past experience to provide agents with hindsight ability is a major solution to the reward sparsity problem. In this paper, to enhance the diversity of relabeled goals, we develop FGI (Foresight Goal Inference), a new relabeling st…
This paper investigates the model-based methods in multi-agent reinforcement learning (MARL). We specify the dynamics sample complexity and the opponent sample complexity in MARL, and conduct a theoretic analysis of return discrepancy upper bound. To reduce the upper bound with the intention of low…
Model-based reinforcement learning has attracted wide attention due to its superior sample efficiency. Despite its impressive success so far, it is still unclear how to appropriately schedule the important hyperparameters to achieve adequate performance, such as the real data ratio for policy optimi…
As a fundamental problem in algorithmic trading, order execution aims at fulfilling a specific trading order, either liquidation or acquirement, for a given instrument. Towards effective execution strategy, recent years have witnessed the shift from the analytical view with model-based market assump…
Aggregating crowd wisdom infers true labels for objects, from multiple noisy labels provided by various sources. Besides labels from sources, side information such as object features is also introduced to achieve higher inference accuracy. Usually, the learning-from-crowds framework is adopted. Howe…
Model-based reinforcement learning approaches leverage a forward dynamics model to support planning and decision making, which, however, may fail catastrophically if the model is inaccurate. Although there are several existing methods dedicated to combating the model error, the potential of the sing…
Neural architecture search (NAS) has shown encouraging results in automating the architecture design. Recently, DARTS relaxes the search process with a differentiable formulation that leverages weight-sharing and SGD for cost reduction of NAS. In DARTS, all candidate operations are trained simulta…
The Frank-Wolfe algorithm is a classic method for constrained optimization problems. It has recently been popular in many machine learning applications because its projection-free property leads to more efficient iterations. In this paper, we study projection-free algorithms for convex-strongly-co…
The CUR matrix decomposition is an important tool for low-rank matrix approximation. It approximates a data matrix though selecting a small number of columns and rows of the matrix. Those CUR algorithms with gap-dependent approximation bounds can obtain high approximation quality for matrices with…
The linear contextual bandits is a sequential decision-making problem where an agent decides among sequential actions given their corresponding contexts. Since large-scale data sets become more and more common, we study the linear contextual bandits in high-dimensional situations. Recent works focus…
Molecular graph generation is a fundamental problem for drug discovery and has been attracting growing attention. The problem is challenging since it requires not only generating chemically valid molecular structures but also optimizing their chemical properties in the meantime. Inspired by the rece…
Model-based reinforcement learning methods learn a dynamics model with real data sampled from the environment and leverage it to generate simulated data to derive an agent. However, due to the potential distribution mismatch between simulated data and real data, this could lead to degraded performan…
Centralized training with decentralized execution has become an important paradigm in multi-agent learning. Though practical, current methods rely on restrictive assumptions to decompose the centralized value function across agents for execution. In this paper, we eliminate this restriction by propo…
In multi-agent systems, complex interacting behaviors arise due to the high correlations among agents. However, previous work on modeling multi-agent interactions from demonstrations is primarily constrained by assuming the independence among policies and their reward structures. In this paper, we…
Interaction is fundamental in autonomous driving (AD). Despite more than a decade of intensive R&D in AD, how to dynamically interact with diverse road users in various contexts still remains unsolved. Multi-agent learning has recently seen big breakthroughs and has much to offer towards solving rea
Adam is shown not being able to converge to the optimal solution in certain cases. Researchers recently propose several algorithms to avoid the issue of non-convergence of Adam, but their efficiency turns out to be unsatisfactory in practice. In this paper, we provide a new insight into the non-conv…
In this paper, we study the generative models of sequential discrete data. To tackle the exposure bias problem inherent in maximum likelihood estimation (MLE), generative adversarial networks (GANs) are introduced to penalize the unrealistic generated samples. To exploit the supervision signal from…
In this paper we show that generative adversarial networks (GANs) without restriction on the discriminative function space commonly suffer from the problem that the gradient produced by the discriminator is uninformative to guide the generator. By contrast, Wasserstein GAN (WGAN), where the discrimi…
Class labels have been empirically shown useful in improving the sample quality of generative adversarial nets (GANs). In this paper, we mathematically study the properties of the current variants of GANs that make use of class label information. With class aware gradient and cross-entropy decomposi…
Existing multi-agent reinforcement learning methods are limited typically to a small number of agents. When the agent number increases largely, the learning becomes intractable due to the curse of the dimensionality and the exponential growth of agent interactions. In this paper, we present Mean Fie…
We introduce a new function-preserving transformation for efficient neural architecture search. This network transformation allows reusing previously trained networks and existing successful architectures that improves sample efficiency. We aim to address the limitation of current network transforma…