47 accepted papers
A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains difficult in many environments, which either lack verifiable rewar…
The performance of autonomous Web GUI agents heavily relies on the quality and quantity of their training data. However, a fundamental bottleneck persists: collecting interaction trajectories from real-world websites is expensive and difficult to verify. The underlying state transitions are hidden, …
Crystal property prediction, governed by quantum mechanical principles, is computationally prohibitive to solve exactly for large many-body systems using traditional density functional theory. While machine learning models have emerged as efficient approximations for large-scale applications, their…
We focus on the problem of Answer-Level Fine-Tuning (ALFT), where the goal is to optimize a language model based on the correctness or properties of its final answers, rather than the specific reasoning traces used to produce them. Directly optimizing answer-level objectives is computationally intra…
Human behaviors in the real world naturally encode rich, long-term contextual information that can be leveraged to train embodied agents for perception, understanding, and acting.However, existing capture systems typically rely on costly studio setups and wearable devices, limiting the large-scale c
Reinforcement Learning (RL) is pivotal for enhancing Large Language Model (LLM) reasoning, yet mainstream algorithms such as GRPO and DAPO remain constrained by a coarse-grained credit assignment paradigm, where all tokens within the same response receive the identical reward. In this paper, we prop…
Language agents have demonstrated remarkable potential in web search and information retrieval. However, these search agents assume user queries are complete and unambiguous, an assumption that diverges from reality where users begin with incomplete queries requiring clarification through interactio…
Biological foundation models (BioFMs), pretrained on large-scale biological sequences, have recently shown strong potential in providing meaningful representations for diverse downstream bioinformatics tasks. However, such models often rely on millions to billions of training sequences and billions
Due to the sheer size of software logs, developers rely on automated log analysis. Log parsing, which parses semi-structured logs into a structured format, is a prerequisite of automated log analysis. However, existing log parsers are unsatisfactory when applied in practice because they 1) ignore ca…
Recent large language models (LLMs) have shown rapid progress on reading-based question answering (QA), where the evidence is explicitly provided or trivially retrievable. In contrast, real-world questions are often not paired with accurate evidence documents. The useful evidence resides in a massiv…
We consider the question of how to employ next-token prediction algorithms in adversarial online decision making environments. Specifically, if we train a next-token prediction model on a distribution $\mathcal{D}$ over sequences of opponent actions, when is it the case that the induced online decis…
Mixture-of-Experts (MoE) architectures are evolving towards finer granularity to improve parameter efficiency. However, existing MoE designs face an inherent trade-off between the granularity of expert specialization and hardware execution efficiency. In this paper, we propose OmniMoE, a system-algo…
Training Large Language Models (LLMs) on long contexts is severely constrained by prohibitive GPU memory overhead, not training time. The primary culprits are the activations, whose memory footprints scale linearly with sequence length. We introduce OOMB, a highly memory-efficient training system th…
While reinforcement learning (RL) can empower large language model (LLM) agents by enabling self-improvement through interaction, its practical adoption remains challenging due to costly rollouts, limited task diversity, unreliable reward signals, and infrastructure complexity, all of which obstruct…
Researchers strategically choose where to submit their work in order to maximize its impact, and these publication decisions in turn determine venues
Multiple agents are increasingly combined to make decisions with the expectation of achieving complementary performance, where the decisions they make together outperform those made individually. However, knowing how to improve the performance of collaborating agents requires knowing what informatio…
Visualization, a domain-specific yet widely used form of imagery, is an effective way to turn complex datasets into intuitive insights, and its value depends on whether data are faithfully represented, clearly communicated, and aesthetically designed. However, evaluating visualization quality is cha…
Tactile sensors play a crucial role in enabling robots to interact effectively and safely with objects in everyday tasks. In particular, visuotactile sensors have seen increasing usage in two and three-fingered grippers due to their high-quality feedback. However, a significant gap remains in the de
Previous research has shown that constraining the gradient of loss function w.r.t. model-predicted probabilities can enhance the model robustness against noisy labels. These methods typically specify a fixed optimal threshold for gradient clipping through validation data to obtain the desired robust…
Simulating stylized human-scene interactions (HSI) in physical environments is a challenging yet fascinating task. Prior works emphasize long-term execution but fall short in achieving both diverse style and physical plausibility. To tackle this challenge, we introduce a novel hierarchical framework…
As Industrial Internet of Things (IIoT) software systems become increasingly complex, precise failure diagnosis has become both essential and challenging. Current log-based failure diagnosis methods lack scalability for different failure types. In IIoT software systems, the number of failure types i…
The Influence Function (IF) is a widely used technique for assessing the impact of individual training samples on model predictions. However, existing IF methods often fail to provide reliable influence estimates in deep neural networks, particularly when applied to noisy training data. This issue d…
While deep networks have achieved broad success in analyzing natural images, when applied to medical scans, they often fail in unexcepted situations. We investigate this challenge and focus on model sensitivity to domain shifts, such as data sampled from different hospitals or data confounded by dem…
Autoformalization, the task of automatically translating natural language descriptions into a formal language, poses a significant challenge across various domains, especially in mathematics. Recent advancements in large language models (LLMs) have unveiled their promising capabilities to formalize…
Chart question answering (ChartQA) tasks play a critical role in interpreting and extracting insights from visualization charts. While recent advancements in multimodal large language models (MLLMs) like GPT-4o have shown promise in high-level ChartQA tasks, such as chart captioning, their effective…
Self-attention and position embedding are two crucial modules in transformer-based Large Language Models (LLMs). However, the potential relationship between them is far from well studied, especially for long context window extending. In fact, anomalous behaviors that hinder long context extrapolatio…
Recent unsupervised anomaly detection methods often rely on feature extractors pretrained with auxiliary datasets or on well-crafted anomaly-simulated samples. However, this might limit their adaptability to an increasing set of anomaly detection tasks due to the priors in the selection of auxiliary…
Gridless direction-of-arrival (DOA) estimation with multiple frequencies can be applied to acoustic source localization. We formulate this as an atomic norm minimization (ANM) problem and derive a regularization-free semi-definite program (SDP) avoiding regularization bias. We also propose a fast SD…
We study the incentivized information acquisition problem, where a principal hires an agent to gather information on her behalf. Such a problem is modeled as a Stackelberg game between the principal and the agent, where the principal announces a scoring rule that specifies the payment, and then the…
Transformers achieve excellent performance in a variety of domains since they can capture long-distance dependencies through the self-attention mechanism. However, self-attention is computationally costly due to its quadratic complexity and high memory consumption. In this paper, we propose a novel…
Continuum robots driven by rods have a wide range of applications, such as detection and maintenance tasks in unstructured environments. However, their inherent nature of flexibility also limits their function. Thus, variable stiffness mechanisms for continuum robots have consistently attracted the
Direction of Arrival (DOA) estimation is widely applied in acoustic source localization. A multi-frequency model is suitable for characterizing the broadband structure in acoustic signals. In this work, we solve the continuous (gridless) line spectrum estimation problem by incorporating the multi-fr…
Deformable image registration (DIR), aiming to find spatial correspondence between images, is one of the most critical problems in the domain of medical image analysis. In this paper, we present a novel, generic, and accurate diffeomorphic image registration framework that utilizes neural ordinary d…
In offline reinforcement learning (RL), we seek to utilize offline data to evaluate (or learn) policies in scenarios where the data are collected from a distribution that substantially differs from that of the target policy to be evaluated. Recent theoretical advances have shown that such sample-eff…
Given only positive examples and unlabeled examples (from both positive and negative classes), we might hope nevertheless to estimate an accurate positive-versus-negative classifier. Formally, this task is broken down into two subtasks: (i) Mixture Proportion Estimation (MPE)---determining the fract…
Batch policy optimization considers leveraging existing data for policy construction before interacting with an environment. Although interest in this problem has grown significantly in recent years, its theoretical foundations remain under-developed. To advance the understanding of this problem, we…
This paper presents SSLIDE, Sound Source Localization for Indoors using DEep learning, which applies deep neural networks (DNNs) with encoder-decoder structure to localize sound sources with random positions in a continuous space. The spatial features of sound signals received by each microphone are…
Under label shift, the label distribution $p(y)$ might change but the class-conditional distributions $p(x|y)$ do not. There are two dominant approaches for estimating the label marginal. BBSE, a moment-matching approach based on confusion matrices, is provably consistent and provides interpretable…
Domain adaptation addresses the common situation in which the target distribution generating our test data differs from the source distribution generating our training data. While absent assumptions, domain adaptation is impossible, strict conditions, e.g. covariate or label shift, enable principled…
The ability to inferring latent psychological traits from human behavior is key to developing personalized human-interacting machine learning systems. Approaches to infer such traits range from surveys to manually-constructed experiments and games. However, these traditional games are limited becaus…
The smallest eigenvectors of the graph Laplacian are well-known to provide a succinct representation of the geometry of a weighted graph. In reinforcement learning (RL), where the weighted graph may be interpreted as the state transition process induced by a behavior policy acting on the environment…
A major challenge in understanding the generalization of deep learning is to explain why (stochastic) gradient descent can exploit the network architecture to find solutions that have good generalization performance when using high capacity models. We find simple but realistic examples showing that…
We present a novel framework that learns to predict human anatomy from body surface. Specifically, our approach generates a synthetic X-ray image of a person only from the person's surface geometry. Furthermore, the synthetic X-ray image is parametrized and can be manipulated by adjusting a set of b…
Planar object tracking is an actively studied problem in vision-based robotic applications. While several benchmarks have been constructed for evaluating state-of-the-art algorithms, there is a lack of video sequences captured in the wild rather than in constrained laboratory environment. In this pa…
We study a novel multi-armed bandit problem that models the challenge faced by a company wishing to explore new strategies to maximize revenue whilst simultaneously maintaining their revenue above a fixed baseline, uniformly over time. While previous work addressed the problem under the weaker requi…
We consider the problem of identifying a good option out of finite set of options under combinatorially structured, noisy feedback about the quality of the options in a sequential process: In each round, a subset of the options, from an available set of subsets, can be selected to receive noisy info…
We consider a sequential learning problem with Gaussian payoffs and side information: after selecting an action $i$, the learner receives information about the payoff of every action $j$ in the form of Gaussian observations whose mean is the same as the mean payoff, but the variance depends on the p…