35 accepted papers
Connectionist models and symbolic models have long embodied two divergent paradigms: the former excel at differentiable representation learning yet struggle with transparency, while the latter deliver explicit rule-based reasoning but resist gradient-based optimization. We introduce Arboreal Neural …
We introduce CMPhysBench, designed to assess the proficiency of Large Language Models (LLMs) in Condensed Matter Physics, as a novel Benchmark. CMPhysBench is composed of more than 520 graduate-level meticulously curated questions covering both representative subfields and foundational theoretical f…
Accurately recognizing distracted driving activities in real-world scenarios is essential for improving road and pedestrian safety. However, existing approaches are prone to attending to irrelevant scene context and are susceptible to interference from redundant frames, compromising their robustness
End-to-end autonomous driving (AD) systems increasingly adopt vision-language-action (VLA) models, yet they ignore the passenger's emotional state, which is central to comfort and AD acceptance. We introduce Open-Domain End-to-End (OD-E2E) AD, where an autonomous vehicle must interpret free-form nat
Decision-focused learning (DFL) has emerged as a powerful end-to-end alternative to conventional predict-then-optimize (PTO) pipelines by directly optimizing predictive models through downstream decision losses. Existing DFL frameworks are limited by their strictly sequential structure, referred to
Recently, diffusion models have been applied to reformulate the regressive portrait matting task as a gradual denoising-driven generative process, alleviating the inherent limitations of discriminative models via iterative error correction. However, due to the lack of high-quality ground-truth matte
Although Large Language Models (LLMs) excel at code generation, recent research reveals that they exhibit an insufficient grasp of core programming concepts, such as data flow and control flow. This limitation undermines their robustness when encountering variations in these concepts in practice; ho
Next Best View (NBV) selection is critical for achieving high-quality 3D reconstruction in unknown environments. This paper presents an active NBV selection approach tailored for Gaussian Splatting (GS), a widely adopted 3D reconstruction technique that has recently gained significant attention and …
Detecting AI-generated images remains a persistent challenge, as existing detectors often struggle to generalize to forgeries produced by previously unseen generative models. This generalization gap mainly stems from entanglement with semantic content and overfitting to model-specific artifacts. Mor
Efficient Distillation (EDistill) compresses large language models (LLMs) by structured pruning parameters and tuning lightweight modules with high training efficiency. Although these EDistilled LLMs achieve state-of-the-art (SOTA) performance on general ability benchmarks relative to similarly size…
In human-robot collaboration, shared autonomy enhances human performance through precise, intuitive support. Effective robotic assistance requires accurately inferring human intentions and understanding task structures to determine optimal support timing and methods. In this paper, we present SUBTA,…
Adversarial scenario generation is a cost-effective approach for safety assessment of autonomous driving systems. However, existing methods are often constrained to a single, fixed trade-off between competing objectives such as adversariality and realism. This yields behavior-specific models that c…
The combination of self-supervised learning and adversarial training (AT) can significantly improve the adversarial robustness of self-supervised models. However, the robustness of self-supervised adversarial training (self-AT) still lags behind that of state-of-the-art (SOTA) supervised AT (sup-AT)…
The emergence of Satellite-Terrestrial Integrated Networks (STIN) has significantly expanded terrestrial network coverage but introduced new security threats. Current Intrusion Detection Systems (IDSs) for STIN mostly consider the distributed nature of satellites, overlooking the computational limit…
Self-supervised learning (SSL) is a technique used to learn feature representations from unlabeled data. However, existing SSL frameworks either rely too heavily on domain knowledge due to their design based on feature invariance, leading to a lack of domain transferability, or they are based on aut…
In the geospatial domain, universal representation models are significantly less prevalent than their extensive use in natural language processing and computer vision. This discrepancy arises primarily from the high costs associated with the input of existing representation models, which often requi…
Underwater gliders (UG) experience unexpected yaw during each dormancy stage of the controller, necessitating additional adjustments, which manifests as repeated yawing throughout the entire profiling time. Repeated yawing is frequently observed during the long-term deployment of the UGs, which can
Shared autonomy allows for combining the global planning capabilities of a human operator with the strengths of a robot such as repeatability and accurate control. In a real-time teleoperation setting, one possibility for shared autonomy is to let the human operator decide for the rough movement and
Vision-language models (VLMs) excel in many downstream tasks but struggle with spatial reasoning, which is crucial for navigation and interaction with physical environments. Specifically, many spatial reasoning tasks rely on fundamental two-dimensional (2D) capabilities, yet our evaluation shows tha
Diffusion models have shown significant potential for image style transfer tasks. However, achieving effective stylization while preserving content in a training-free setting remains a challenging issue due to the tightly coupled representation space and inherent randomness of the models. In this pa
A text corpus centered on events is foundational to research concerning the detection, representation, reasoning, and harnessing of online events. The majority of current event-based datasets mainly target sentence-level tasks, thus to advance event-related research spanning from sentence to documen…
The ever-increasing complexity and scale of 5G communication networks pose huge challenges to network operations. Root cause analysis is considered as a promising method for fault detection. However, it still suffers challenges of severely uneven distribution of fault data, low accuracy in root caus…
Citywalk, a recently popular form of urban travel, requires genuine personalization and understanding of fine-grained requests compared to traditional itinerary planning. In this paper, we introduce the novel task of Open-domain Urban Itinerary Planning (OUIP), which generates personalized urban iti…
The increasing complexity and openness of 5G networks naturally enlarge the attack surface and introduce new vulnerabilities, thereby posing challenges to the performance of existing intrusion detection systems (IDSs). Current IDSs solely rely on statistical features, which may suffer from low accur…
Self-supervised learning (SSL) has rapidly advanced in recent years, approaching the performance of its supervised counterparts through the extraction of representations from unlabeled data. However, dimensional collapse, where a few large eigenvalues dominate the eigenspace, poses a significant obs…
Multi-View Representation Learning (MVRL) aims to learn a unified representation of an object from multi-view data. Deep Canonical Correlation Analysis (DCCA) and its variants share simple formulations and demonstrate state-of-the-art performance. However, with extensive experiments, we observe the…
The widespread adoption of Large Language Models (LLMs) has led to an increase in AI-generated text on the Internet, presenting a crucial challenge to differentiate AI-created content from human-written text. This challenge is critical to prevent issues of authenticity, trust, and potential copyrigh…
We present UnionFormer a novel framework that integrates tampering clues across three views by unified learning for image manipulation detection and localization. Specifically we construct a BSFI-Net to extract tampering features from RGB and noise views achieving enhanced responsiveness to boundary…
Existing methods for generating adversarial code examples face several challenges: limted availability of substitute variables, high verification costs for these substitutes, and the creation of adversarial samples with noticeable perturbations. To address these concerns, our proposed approach, RNNS…
This article shows that an attention mechanism, the Multi-Local Attention, can improve a depression detection approach based on Long Short-Term Memory Networks. Besides leading to higher performance metrics (e.g., Accuracy and F1 Score), Multi-Local Attention improves two other aspects of the approa…
Recent studies have shown the effectiveness of retrieval augmentation in many generative NLP tasks. These retrieval-augmented methods allow models to explicitly acquire prior external knowledge in a non-parametric manner and regard the retrieved reference instances as cues to augment text generation…
Transforming the large amounts of unstructured text on the Internet into structured event knowledge is a critical, yet unsolved goal of NLP, especially when addressing document-level text. Existing methods struggle in Document-level Event Extraction (DEE) due to its two intrinsic challenges: (a) Nes…
Multi-view-based 3D object recognition is important in robot-environment interaction. However, recent methods simply extract features from each view via convolutional neural networks (CNNs) and then fuse these features together to make predictions. These methods ignore the inherent ambiguities of ea…
Matrix completion is often applied to data with entries missing not at random (MNAR). For example, consider a recommendation system where users tend to only reveal ratings for items they like. In this case, a matrix completion method that relies on entries being revealed at uniformly sampled row and…
Binary embedding is an effective way for nearest neighbor (NN) search as binary code is storage efficient and fast to compute. It tries to convert real-value signatures into binary codes while preserving similarity of the original data. However, it greatly decreases the discriminability of original…