21 accepted papers
Asynchronous reinforcement learning (RL) has shown notable success in accelerating the post-training of large language models (LLMs). However, its decoupled data generation and training paradigm introduces a fundamental distributional mismatch between data generated by stale behavior policies and cu…
Human driving behavior is inherently personal, which is shaped by long-term habits and influenced by short-term intentions. Individuals differ in how they accelerate, brake, merge, yield, and overtake across diverse situations. However, existing end-to-end autonomous driving systems either optimize
Repository-level automated program repair (APR) requires long-horizon reasoning over interdependent decisions. However, most LLM-based approaches reconstruct repair reasoning independently for each issue, failing to reuse successful patterns from prior repairs, even though real-world repositories co…
Watermarking has emerged as a critical solution for the detection and provenance tracing of content generated by large language models. However, existing methods still suffer from significant limitations, including difficulties in achieving personalized attribution, substantial degradation of genera…
Large language model (LLM) generated texts now rival human quality, creating four text categories: purely machine-generated, machine-rewritten, machine-polished, and human-written content. Traditional detection methods face significant challenges in human-machine hybrid scenarios where LLMs perform
Multimodal Large Language Models (MLLMs) have garnered significant attention recently and demonstrate outstanding capabilities in various tasks such as OCR, VQA, captioning, etc. However, hallucination remains a persistent issue. While numerous methods have been proposed to mitigate hallucinations,
LLM-based multi-agent systems can fail even when planned actions are executed correctly because agents may misjudge their knowledge when evaluating plan feasibility, a phenomenon we term epistemic miscalibration in planning. Unlike execution errors, epistemic miscalibration is latent during planning…
In robotics applications, event cameras provide low-latency and high-dynamic-range sensing by asynchronously detecting brightness changes, making them well-suited for capturing fast motions and subtle cues in dynamic environments. However, most existing Spiking Neural Network (SNN)-based methods enh
The confluence of the advancement of Autonomous Vehicles (AVs) and the maturity of Vehicle-to-Everything (V2X) communication has enabled the capability of cooperative connected and automated vehicles (CAVs). Building on top of cooperative perception, this letter explores the feasibility and effectiv
Despite the impressive performance of general large language models(LLMs), many of their applications in specific domains (e.g., low-data and knowledge-intensive) still confront significant challenges. Supervised fine-tuning (SFT)---where a general LLM is further trained on a small labeled dataset t…
Despite their remarkable performance on various tasks, Large Language Models (LLMs) still struggle with logical reasoning, particularly in complex and multi-step reasoning processes. Among various efforts to enhance LLMs' reasoning capabilities, synthesizing large-scale, high-quality logical reason…
Sound Event Detection (SED) plays a vital role in comprehending and perceiving acoustic scenes. Previous methods have demonstrated impressive capabilities. However, they are deficient in learning features of complex scenes from heterogeneous dataset. In this paper, we introduce a novel dual-branch a…
Action understanding matters for intelligent agents and has attracted long-term attention. It can be formed as the mapping from the action physical space to the semantic space. Typically researchers built action datasets according to idiosyncratic choices to define classes and push the envelope of b…
Nonlinear dynamics bring difficulties to controller design for control-affine systems such as tractor-trailer vehicles, especially when the parameters in the dynamics are unknown. To address this constraint, we propose a derivative-based lifting function construction method, show that the correspond…
This study presents a novel evaluation framework for the Vision-Language Navigation (VLN) task. It aims to diagnose current models for various instruction categories at a finer-grained level. The framework is structured around the context-free grammar (CFG) of the task. The CFG serves as the basis f…
Neural Radiance Fields (NeRF) revolutionize the realm of visual media by providing photorealistic Free-Viewpoint Video (FVV) experiences offering viewers unparalleled immersion and interactivity. However the technology's significant storage requirements and the computational complexity involved in g…
Few-shot event detection (ED) has been widely studied, while this brings noticeable discrepancies, e.g., various motivations, tasks, and experimental settings, that hinder the understanding of models for future progress. This paper presents a thorough empirical study, a unified view of ED models, an…
In this work, we study the problem of Embodied Referring Expression Grounding, where an agent needs to navigate in a previously unseen environment and localize a remote object described by a concise high-level natural language instruction. When facing such a situation, a human tends to imagine what…
In this paper, we propose an effective yet efficient model PAIE for both sentence-level and document-level Event Argument Extraction (EAE), which also generalizes well when there is a lack of training data. On the one hand, PAIE utilizes prompt tuning for extractive objectives to take the best advan…
Recent studies demonstrate the deep networks, even robustified by the state-of-the-art adversarial training (AT), still suffer from large robust generalization gaps, in addition to the much more expensive training costs than standard training. In this paper, we investigate this intriguing problem fr…
Human trajectory prediction is crucial for service robots, autonomous driving and advanced driver assistant systems. Current top-performing methods mainly rely on intractable generative models to learn a distribution of future trajectories, and sample multiple plausible ones as prediction results. I