87 accepted papers
Reinforcement learning (RL) based post-training for large language models (LLMs) is computationally expensive, as it generates many rollout sequences that could frequently share long token prefixes. Existing RL frameworks usually process these sequences independently, repeatedly recomputing identica…
Monocular depth estimation foundation models provide robust depth priors with exceptional generalization capabilities; however, their predictions typically lack a reliable metric scale and contain local inconsistencies in a zero-shot setting, which limit their deployment in unconstrained real-world
Large Language Models (LLMs) have shown promising results in automating formal verification. However, existing approaches treat proof generation as a static, end-to-end prediction over source code, relying on limited verifier feedback and lacking access to concrete program behaviors. We present EXVE…
A clean map of the surrounding environment is essential for autonomous driving systems to ensure reliable localization and safe path planning. However, the existence of dynamic objects introduces ghost traces into the map, significantly degrading its quality. To address this issue, we propose Enhanc…
Ego-vision-based navigation in cluttered environments is crucial for mobile systems, particularly agile quadrotors. While learning-based methods have shown promise recently, head-to-head comparisons with cutting-edge optimization-based approaches are scarce, leaving open the question of where and to…
Mainstream 3D human pose estimation methods directly predict 3D coordinates of joints from 2D keypoints, suffering from severe depth ambiguity. Pose textual descriptions contain abundant semantic information, which facilitates the model to learn the spatial relationship among different body parts, p
Accurate motion control in the face of disturbances within complex environments remains a major challenge in robotics. Classical model-based approaches often struggle with nonlinearities and unstructured disturbances, while reinforcement learning (RL)-based methods can be fragile when encountering u…
Reinforcement Learning (RL) has proven highly effective for autoregressive language models, but adapting these methods to diffusion large language models (dLLMs) presents fundamental challenges. The core difficulty lies in likelihood approximation: while autoregressive models naturally provide token…
Multimodal autoregressive (AR) models, based on next-token prediction and transformer architecture, have demonstrated remarkable capabilities in various multimodal tasks including text-to-image (T2I) generation. Despite their strong performance in general T2I tasks, our research reveals that these m
Reinforcement learning (RL) has emerged as a central paradigm for training large language models (LLMs) in reasoning tasks. Yet recent studies question RL’s ability to incentivize reasoning capacity beyond the base model. This raises a key challenge: how can RL be adapted to solve harder reasoning p…
Recent advancements in LLM-based agents have demonstrated remarkable capabilities in handling knowledge-intensive tasks using external tools. One representative example is search agent. Existing open-source search agents heavily rely on advanced commercial LLMs: they either collect trajectories from…
Recent advancements in Vision Language Models (VLMs) have expanded their capabilities to interactive agent tasks, yet existing benchmarks remain limited to single-agent or text-only environments. In contrast, real-world scenarios often involve multiple agents interacting within rich visual and textu
Precise and agile flight maneuvers are essential for quadrotor applications, yet traditional control methods are limited by their reliance on flat trajectories or computationally intensive optimization. Reinforcement learning (RL)-based policies offer a promising alternative by directly mapping obse…
Reinforcement learning (RL) has become a trending paradigm for training large language models (LLMs), particularly for reasoning tasks. Effective RL for LLMs requires massive parallelization and poses an urgent need for efficient training systems. Most existing large-scale RL systems for LLMs are sy…
We introduce ESGenius , a comprehensive benchmark for evaluating and enhancing the proficiency of Large Language Models (LLMs) in Environmental, Social, and Governance (ESG) and sustainability-focused question answering. ESGenius comprises two key components: (i) ESGenius-QA , a collection of 1,136
Estimating 2D camera motion is a fundamental computer vision task that models the projection of 3D camera movements onto the 2D image plane. Current methods rely on either homography-based approaches, limited to planar scenes, or meshflow techniques that use grid-based local homographies but struggl…
Ego-vision-based navigation in cluttered environments is crucial for mobile systems, particularly agile quadrotors. While learning-based methods have shown promise recently, head-to-head comparisons with cutting-edge optimization-based approaches are scarce, leaving open the question of where and to
The rapid advancement of autonomous driving technology, particularly in autonomous trucking on highways, shows great value for enhancing efficiency and reducing costs in the logistics industry. In this work, we define the full-trip speed planning problem for autonomous trucks under delivery time and
Large Reasoning Models (LRMs) demonstrate remarkable problem-solving capabilities through extended Chain-of-Thought (CoT) reasoning but often produce excessively verbose and redundant reasoning traces. This inefficiency incurs high inference costs and limits practical deployment. While existing fine…
Large language model (LLM) agents have recently demonstrated impressive capabilities in various domains like open-ended conversation and multi-step decision-making. However, it remains challenging for these agents to solve strategic language games, such as Werewolf, which demand both strategic decis…
We present a large language model (LLM) based system to empower quadrupedal robots with problem-solving abilities for long-horizon tasks beyond short-term motions. Long-horizon tasks for quadrupeds are challenging since they require both a high-level understanding of the semantics of the problem for
This paper tackles the challenging task of maintaining formation among multiple unmanned aerial vehicles (UAVs) while avoiding both static and dynamic obstacles during directed flight. The complexity of the task arises from its multi-objective nature, the large exploration space, and the sim-to-real
Accurate motion control in the face of disturbances within complex environments remains a major challenge in robotics. Classical model-based approaches often struggle with nonlinearities and unstructured disturbances, while reinforcement learning (RL)-based methods can be fragile when encountering u
Improving the multi-step reasoning ability of large language models (LLMs) with offline reinforcement learning (RL) is essential for quickly adapting them to complex tasks. While Direct Preference Optimization (DPO) has shown promise in aligning LLMs with human preferences, it is less suitable for m…
We study the use of Process Reward Models (PRMs) for guiding Long Chain-of-Thought (CoT) reasoning in large language models. Although PRMs deliver fine-grained feedback in standard tasks, PRM-guided beam search does not consistently outperform PRM-free approaches in long CoT reasoning. We trace this…
Despite significant advancements in large language models (LLMs) that enhance robot agents' understanding and execution of natural language (NL) commands, ensuring the agents adhere to user-specified constraints remains challenging, particularly for complex commands and long-horizon tasks. To addres
Achieving coordinated teamwork among legged robots requires both fine-grained locomotion control and long-horizon strategic decision-making. Robot soccer offers a compelling testbed for this challenge, combining dynamic, competitive, and multi-agent interactions. In this work, we present a hierarchi…
Large Vision-Language Action (VLA) models have shown significant potential for embodied AI. However, their predominant training via supervised fine-tuning (SFT) limits generalization due to susceptibility to compounding errors under distribution shifts. Reinforcement learning (RL) offers a path to…
Precise and agile flight maneuvers are essential for quadrotor applications, yet traditional control methods are limited by their reliance on flat trajectories or computationally intensive optimization. Reinforcement learning (RL)-based policies offer a promising alternative by directly mapping obse
Learning Nash equilibrium (NE) in complex zero-sum games with multi-agent reinforcement learning (MARL) can be extremely computationally expensive. Curriculum learning is an effective way to accelerate learning, but an under-explored dimension for generating a curriculum is the difficulty-to-learn o…
Recent advancements in differentiable simulators highlight the potential of policy optimization using simulation gradients. Yet, these approaches are largely contingent on the continuity and smoothness of the simulation, which precludes the use of certain simulation engines, such as Mujoco. To tackl…
Emergent-scene safety is the key milestone for fully autonomous driving, and reliable on-time prediction is essential to maintain safety in emergency scenarios. However, these emergency scenarios are long-tailed and hard to collect, which restricts the system from getting reliable predictions. In th…
Recent deep neural networks (DNNs) have came to rely on vast amounts of training data, providing an opportunity for malicious attackers to exploit and contaminate the data to carry out backdoor attacks. However, existing backdoor attack methods make unrealistic assumptions, assuming that all trainin…
"Drawing on recent advancements in diffusion models for text-to-image generation, identity-preserved personalization has made significant progress in accurately capturing specific identities with just a single reference image. However, existing methods primarily integrate reference images within the…
Reinforcement Learning from Human Feedback (RLHF) is currently the most widely used method to align large language models (LLMs) with human preferences. Existing RLHF methods can be roughly categorized as either reward-based or reward-free. Novel applications such as ChatGPT and Claude leverage rewa…
We aim to control a robot to physically behave in the real world following any high-level language command like "cartwheel" or "kick". Although human motion datasets exist, this task remains particularly challenging since generative models can produce physically unrealistic motions, which will be mo…
Agents built with large language models (LLMs) have shown great potential across a wide range of domains. However, in complex decision-making tasks, pure LLM-based agents tend to exhibit intrinsic bias in their choice of actions, which is inherited from the model's training data and results in subop…
Can a quadrupedal robot perform bipedal motions like humans? Although developing human-like behaviors is more often studied on costly bipedal robot platforms, we present a solution over a lightweight quadrupedal robot that unlocks the agility of the quadruped in an upright standing pose and is capab…
Model-free reinforcement learning is a promising approach for autonomously solving challenging robotics control problems, but faces exploration difficulty without information about the robot’s morphology. The under-exploration of multiple modalities with symmetric states leads to behaviors that are…
Fuel efficiency is a crucial aspect of long-distance cargo transportation by oil-powered trucks that economize on costs and decrease carbon emissions. Current predictive control methods depend on an accurate model of vehicle dynamics and engine, including weight, drag coefficient, and the Brake-spec…
In this work, we introduce <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">OmniDrones</i> , an efficient and flexible platform tailored for reinforcement learning in drone control, built on Nvidia's Omniverse Isaac Sim. It employs a bottom-up design
It has been a popular trend in AI to pretrain foundation models on massive data. However, collecting sufficient offline training trajectories for robot learning is particularly expensive since valid control actions are required. Therefore, most existing robotic datasets are collected from human expe…
Executing contact-rich manipulation tasks necessitates the fusion of tactile and visual feedback. However, the distinct nature of these modalities poses significant challenges. In this paper, we introduce a system that leverages visual and tactile sensory inputs to enable dexterous in-hand manipulat…
The ever-growing complexity of reinforcement learning (RL) tasks demands a distributed system to efficiently generate and process a massive amount of data. However, existing open-source libraries suffer from various limitations, which impede their practical use in challenging scenarios where large-s…
Previous literature on policy diversity in reinforcement learning (RL) either focuses on the online setting or ignores the policy performance. In contrast, offline RL, which aims to learn high-quality policies from batched data, has yet to fully leverage the intrinsic diversity of the offline datase…
Reinforcement learning has been used to approach well-known NP-hard combinatorial problems in graph theory. Among these, Hamiltonian cycle problems are exceptionally difficult to analyze, even when restricted to individual instances of structurally complex graphs. In this paper, we use Monte Carlo T…
Truss layout design, namely finding a lightweight truss layout satisfying all the physical constraints, is a fundamental problem in the building industry. Generating the optimal layout is a challenging combinatorial optimization problem, which can be extremely expensive to solve by exhaustive search…
In this study, we delve into the task of few-shot Generative Domain Adaptation (GDA), which involves transferring a pre-trained generator from one domain to a new domain using only a few reference images. Inspired by the way human brains acquire knowledge in new domains, we present an innovative gen…
Bimanual manipulation is important for building intelligent robots that unlock richer skills than single arms. We consider a multi-object bimanual rearrangement task, where a reinforcement learning (RL) agent aims to jointly control two arms to rearrange these objects as fast as possible. Solving th…
In complex reinforcement learning (RL) problems, policies with similar rewards may have substantially different behaviors. It remains a fundamental challenge to optimize rewards while also discovering as many *diverse* strategies as possible, which can be crucial in many practical applications. Our…
In recent years, graph Transformers (GTs) have been demonstrated as a robust architecture for a wide range of graph learning tasks. However, the quadratic complexity of GTs limits their scalability on large-scale data, in comparison to Graph Neural Networks (GNNs). In this work, we propose the Kerne…
There is a recent trend of applying multi-agent reinforcement learning (MARL) to train an agent that can cooperate with humans in a zero-shot fashion without using any human data. The typical workflow is to first repeatedly run self-play (SP) to build a policy pool and then train the final adaptive…
We study the problem of training a Reinforcement Learning (RL) agent that is collaborative with humans without using human data. Although such agents can be obtained through self-play training, they can suffer significantly from the distributional shift when paired with unencountered partners, such…
Deep models have the risk of utilizing spurious clues to make predictions, e.g., recognizing actions via classifying the background scene. This problem severely degrades the open-set action recognition performance when the testing samples exhibit scene distributions different from the training sampl…
Many recent breakthroughs of deep reinforcement learning (RL) are mainly built upon large-scale distributed training of model-free methods using millions to billions of samples. On the other hand, state-of-the-art model-based RL methods can achieve human-level sample efficiency but often take a much…
We present Reward-Switching Policy Optimization (RSPO), a paradigm to discover diverse strategies in complex RL environments by iteratively finding novel policies that are both locally optimal and sufficiently different from existing ones. To encourage the learning policy to consistently converge to…
We consider the problem of building a reinforcement learning (RL) agent that can both accomplish non-trivial tasks, like winning a real-time strategy game, and strictly follow high-level language commands from humans, like “attack”, even if a command is sub-optimal. We call this novel yet important…
Can a robot autonomously learn to design and construct a bridge from varying-sized blocks without a blueprint? It is a challenging task with long horizon and sparse reward - the robot has to figure out physically stable design schemes and feasible actions to manipulate and transport blocks. Due to d…
"We tackle the problem of cooperative visual exploration where multiple agents need to jointly explore unseen regions as fast as possible based on visual signals. Classical planning-based methods often suffer from expensive computation overhead at each step and a limited expressiveness of complex co…
Pre-trained language models have become a crucial part of ranking systems and achieved very impressive effects recently. To maintain high performance while keeping efficient computations, knowledge distillation is widely used. In this paper, we focus on two key questions in knowledge distillation fo…
It has been a recent trend to leverage the power of supervised learning (SL) towards more effective reinforcement learning (RL) methods. We propose a novel phasic solution by alternating online RL and offline SL for tackling sparse-reward goal-conditioned problems. In the online phase, we perform RL…
Learning generalizable policies that can adapt to unseen environments remains challenging in visual Reinforcement Learning (RL). Existing approaches try to acquire a robust representation via diversifying the appearances of in-domain observations for better generalization. Limited by the specific ob…
Many advances in cooperative multi-agent reinforcement learning (MARL) are based on two common design principles: value decomposition and parameter sharing. A typical MARL algorithm of this fashion decomposes a centralized Q-function into local Q-networks with parameters shared across agents. Such a…
Contrastive learning models have achieved great success in unsupervised visual representation learning, which maximize the similarities between feature representations of different views of the same image, while minimize the similarities between feature representations of views of different images.…
Proximal Policy Optimization (PPO) is a ubiquitous on-policy reinforcement learning algorithm but is significantly less utilized than off-policy learning algorithms in multi-agent settings. This is often due to the belief that PPO is significantly less sample efficient than off-policy methods in mul…
"Online action detection aims at detecting the ongoing action in a streaming video. In this paper, we proposed an uncertainty-based spatial-temporal attention for online action detection. By explicitly modeling the distribution of model parameters, we extend the baseline models in a probabilistic ma…
We propose a simple, general and effective technique, Reward Randomization for discovering diverse strategic policies in complex multi-agent games. Combining reward randomization and policy gradient, we derive a new algorithm, Reward-Randomized Policy Gradient (RPG). RPG is able to discover a set of…
Autonomous assembly has been a desired functionality of many intelligent robot systems. We study a new challenging assembly task, designing and constructing a bridge without a blueprint. In this task, the robot needs to first design a feasible bridge architecture for arbitrarily wide cliffs and then…
We present Native Chinese Reader (NCR), a new machine reading comprehension MRC) dataset with particularly long articles in both modern and classical Chinese. NCR is collected from the exam questions for the Chinese course in China’s high schools, which are designed to evaluate the language profic…
Efficient exploration under sparse rewards remains a key challenge in deep reinforcement learning. Previous exploration methods (e.g., RND) have achieved strong results in multiple hard tasks. However, if there are multiple novel areas to explore, these methods often focus quickly on one without suf…
We propose a novel learning paradigm, Self-Imitation via Reduction (SIR), for solving compositional reinforcement learning problems. SIR is based on two core ideas: task reduction and self-imitation. Task reduction tackles a hard-to-solve task by actively reducing it to an easier task whose solution…
One practical requirement in solving dynamic games is to ensure that the players play well from any decision point onward. To satisfy this requirement, existing efforts focus on equilibrium refinement, but the scalability and applicability of existing techniques are limited. In this paper, we propos…
We introduce an automatic curriculum algorithm, Variational Automatic Curriculum Learning (VACL), for solving challenging goal-conditioned cooperative multi-agent reinforcement learning problems. We motivate our curriculum learning paradigm through a variational perspective, where the learning objec…
Through multi-agent competition, the simple objective of hide-and-seek, and standard reinforcement learning algorithms at scale, we find that agents create a self-supervised autocurriculum inducing multiple distinct rounds of emergent strategy, many of which require sophisticated tool use and coordi…
Intrinsically motivated reinforcement learning aims to address the exploration challenge for sparse-reward tasks. However, the study of exploration methods in transition-dependent multi-agent settings is largely absent from the literature. We aim to take a step towards solving this problem. We prese…
Multi-task learning is a very challenging problem in reinforcement learning. While training multiple tasks jointly allow the policies to share parameters across different tasks, the optimization problem becomes non-trivial: It remains unclear what parameters in the network should be reused across t…
Object detection is an essential step towards holistic scene understanding. Most existing object detection algorithms attend to certain object areas once and then predict the object locations. However, scientists have revealed that human do not look at the scene in fixed steadiness. Instead, human e…
We introduce a new memory architecture, Bayesian Relational Memory (BRM), to improve the generalization ability for semantic visual navigation agents in unseen environments, where an agent is given a semantic target to navigate towards. BRM takes the form of a probabilistic relation graph over seman…
Sampling with Markov chain Monte Carlo methods typically amounts to discretizing some continuous-time dynamics with numerical integration. In this paper, we establish the convergence rate of sampling algorithms obtained by discretizing smooth It\^o diffusions exhibiting fast $2$-Wasserstein contract…
Teaching an agent to navigate in an unseen 3D environment is a challenging task, even in the event of simulated environments. To generalize to unseen environments, an agent needs to be robust to low-level variations (e.g. color, texture, object changes), and also high-level variations (e.g. layout c…
Despite the recent successes of probabilistic programming languages (PPLs) in AI applications, PPLs offer only limited support for random variables whose distributions combine discrete and continuous elements. We develop the notion of measure-theoretic Bayesian networks (MTBNs) and use it to provide…
Effective implementations of sampling-based probabilistic inference often require manually constructed, model-specific proposals. Inspired by recent progresses in meta-learning for training learning agents that can generalize to unseen environments, we propose a meta-learning approach to building ef…
The region-based Convolutional Neural Network (CNN) detectors such as Faster R-CNN or R-FCN have already shown promising results for object detection by combining the region proposal subnetwork and the classification subnetwork together. Although R-FCN has achieved higher detection speed while keepi…
Gesture is a natural interface in interacting with wearable devices such as VR/AR helmet and glasses. The main challenge of gesture recognition in egocentric vision arises from the global camera motion caused by the spontaneous head movement of the device wearer. In this paper, we address the proble…
We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as…
We introduce the value iteration network (VIN): a fully differentiable neural network with a `planning module' embedded within. VINs can learn to plan, and are suitable for predicting outcomes that involve planning-based reasoning, such as policies for reinforcement learning. Key to our approach is…
Linear discriminant analysis (LDA) represents a simple yet powerful technique for partitioning a p-dimensional feature vector into one of K classes based on a linear projection learned from N labeled observations. However, it is well-established that in the high-dimensional setting (p > N) the under…