25 accepted papers
Random frame-level data missing is a critical challenge in multimodal sentiment analysis. Existing methods are largely limited to passive completion via single-pass feedforward connections and static cross-modal fusion, which struggle to generate high-quality completed features. However, the brain i
Vision-language models (VLMs) such as CLIP have demonstrated remarkable zero-shot generalization, yet remain highly vulnerable to adversarial examples (AEs). While test-time defenses are promising, existing methods fail to provide sufficient robustness against strong attacks and are often hampered b…
Fine-tuning large language models for vertical domains remains a labor-intensive and expensive process, requiring domain experts to curate data, configure training, and iteratively diagnose model behavior. Despite growing interest in autonomous machine learning, no prior work has tackled end-to-end …
Studies have shown that catastrophic forgetting primarily stems from the difficulty of reactivating old memories; although parameter-efficient fine-tuning can mitigate forgetting while keeping most model parameters frozen, it still falls short in fully reawakening knowledge of prior tasks. In contra…
Abstract visual reasoning benchmarks such as ARC-AGI evaluate the ability to infer generalizable transformation rules from few graphical demonstrations, a capability where current deep learning models severely underperform. Mainstream LLMs achieve only 15.8% (DeepSeek-R1) and 34.5% (o3-mini-high) ac
Benchmarks serve as standardized test systems to distinguish capabilities among large language models (LLMs). Discriminative items enable high-ability LLMs to favor correct answers, while causing low-ability models to assign lower plausibility to these answers and tend toward incorrect answers. Curr
Reliable long-horizon precipitation nowcasting requires preserving fine-scale echo structures while maintaining coherent transport. Although Rectified Flow (RF) can generate detail-preserving future sequences, numerical ODE integration compounds velocity estimation errors and induces progressive off…
Prompt learning has recently emerged as a novel, parameter-efficient paradigm to tackle the missing modalities challenge. However, existing prompting methods often overlook the internal structural information within prompt vectors, limiting their effectiveness in guiding frozen backbone models under…
We introduce a new Reflective Generative Model (RGM), which obtains OpenAI o3-mini's performance via a novel Reflective Generative Form. This form focuses on high-quality reasoning trajectory selection and contains two novelties: 1) A unified interface for policy and process reward model: we share t…
Human-exosuit adaptation is a bi-directional process: exosuit-to-human locomotion adaptation maximizes the benefits of exosuit assistance, while human-to-exosuit adaptation accelerates the wearer's access to these benefits. To promote bi-directional adaptation, we investigated precise gait phase pre
Open-world reinforcement learning challenges agents to develop intelligent behavior in vast exploration spaces. Recent approaches like LS-Imagine have advanced the field by extending imagination horizons through jumpy state transitions, yet remain limited by fixed exploration mechanisms and static j…
Financial decision-making presents unique challenges for language models, requiring them to handle temporally evolving, risk-sensitive, and event-driven contexts. While large language models (LLMs) demonstrate strong general reasoning abilities, they often overlook key behavioral patterns underlying
Large language models (LLMs) have advanced general-purpose reasoning, showing strong performance across diverse tasks. However, existing methods often rely on implicit exploration, where the model follows stochastic and unguided reasoning paths—like walking without a map. This leads to unstable reas
Melody preservation is crucial in singing voice conversion (SVC). However, in many scenarios, audio is often accompanied with background music (BGM), which can cause audio distortion and interfere with the extraction of melody and other key features, significantly degrading SVC performance. Previous…
Visual place recognition(VPR) is a crucial technology for autonomous driving and robotic navigation. However, severe appearance and perspective changes often lead to degradation of algorithm performance. Current methods mainly utilize single-modality RGB images, which are sensitive to environmental…
Visual place recognition (VPR) is a challenging issue for robotics and autonomous systems, focusing on utilizing visual information for robot localization. Currently, hierarchical architecture is being employed by growing works, which embraces RANSAC-based geometric verification for re-ranking. Howe…
The validation of global climate models is crucial to ensure the accuracy and efficacy of model output. We introduce the spherical convolutional Wasserstein distance to more comprehensively measure differences between climate models and reanalysis data. This new similarity measure accounts for spati…
To improve the accuracy of torque estimation and compliance control of the force sensorless, we propose a torque fusion method based on extended Kalman filter (EKF), both the data of motor current and the harmonic reducer torsional deformation are involved. First, a nonlinear EKF is designed based o
Neuro-Rule Networks (NRNs) emerge as a promising neuro-symbolic method, enjoyed by the ability to equate fully-connected neural networks with logic rules. To support learning logic rules consisting of boolean variables, converting input features into binary representations is required. Different fro…
With diverse presentation attacks emerging continually, generalizable face anti-spoofing (FAS) has drawn growing attention. Most existing methods implement domain generalization (DG) on the complete representations. However, different image statistics may have unique properties for the FAS tasks. In…
Document-level relation extraction (DocRE) aims to identify semantic labels among entities within a single document. One major challenge of DocRE is to dig decisive details regarding a specific entity pair from long text. However, in many cases, only a fraction of text carries required information,…
Rule-based models, e.g., decision trees, are widely used in scenarios demanding high model interpretability for their transparent inner structures and good model expressivity. However, rule-based models are hard to optimize, especially on large data sets, due to their discrete parameters and structu…
With the ever growing popularity of deep learning, the tremendous complexity of deep neural networks is becoming problematic when one considers inference on resource constrained platforms. Binary networks have emerged as a potential solution, however, they exhibit a fundamentallimi-tation in realizi…
Neural codes are inevitably shaped by various kinds of biological constraints, \emph{e.g.} noise and metabolic cost. Here we formulate a coding framework which explicitly deals with noise and the metabolic costs associated with the neural representation of information, and analytically derive the op…
Computational energy versus computational precision represents a critical implementation-level tradeoff facing embedded DSP systems. Focusing on multiply-accumulate (MAC) hardware, which is used extensively in DSP implementations (e.g., FIR filtering), this paper proposes an approach that exploits f…