13 accepted papers
Visual AutoRegressive modeling (VAR) suffers from substantial computational cost due to the massive token count involved. Failing to account for the continuous evolution of modeling dynamics, existing VAR token reduction methods face three key limitations: heuristic stage partition, non-adaptive sch…
Visual AutoRegressive modeling (VAR) based on next-scale prediction has revitalized autoregressive visual generation. Although its full-context dependency, i.e., modeling all previous scales for next-scale prediction, facilitates more stable and comprehensive representation learning by leveraging co
The quest for analytical solutions to differential equations has traditionally been constrained by the need for extensive mathematical expertise. Machine learning methods like genetic algorithms have shown promise in this domain, but are hindered by significant computational time and the complexity…
Depression is a severe mental illness, and extracting emotional information from video-audio signals for multimodal depression recognition is a challenging problem. Recent methods use the self-attention (SA) mechanism from Transformers to capture the dynamic relationships between different modalitie…
Mathematical formulas are the language of communication between humans and nature. Discovering latent formulas from observed data is an important challenge in artificial intelligence, commonly known as symbolic regression(SR). The current mainstream SR algorithms regard SR as a combinatorial optimiz…
Large Language Models (LLMs) excel in various Natural Language Processing (NLP) tasks but remain vulnerable to misinformation, particularly in multi-turn dialogues where misleading context accumulates. Existing benchmarks, such as TruthfulQA and FEVER, assess factual accuracy in isolated queries but
Magnetic tactile sensors (MTSs) exhibit high sensitivity, flexibility, and ability to operate without direct contact, demonstrating outstanding performance in human-machine interaction and tactile feedback. However, the existing MTSs lack numerical models that can accurately calculate the force magn
Symbolic regression (SR) is a powerful technique for discovering the underlying mathematical expressions from observed data. Inspired by the success of deep learning, recent deep generative SR methods have shown promising results. However, these methods face difficulties in processing high-dimension…
Soft robots have garnered considerable attention recently due to their versatility, compliance, and myriad applications. However, the inherent low stiffness of soft robots also limits their stability and force output capability. Hence, variable stiffness technology has emerged as a solution, which e
The principle of continual relation extraction (CRE) involves adapting to emerging novel relations while preserving old knowledge. Existing CRE approaches excel in preserving old knowledge but falter when confronted with contaminated data streams, likely due to an artificial assumption of no annotat…
Due to the increasing behavioral and structural complexity of robots, it is challenging to predict the execution outcome after error detection. Anomaly detection methods can help detect errors and prevent potential failures. However, not every fault leads to a failure due to the system’s fault toler…
Symbolic regression (SR) is an important technique for discovering hidden mathematical expressions from observed data. Transformer-based approaches have been widely used for machine translation due to their high performance, and are recently highly expected to be used for SR. They input the data poi…
Adversarial robustness has attracted much attention recently, and the mainstream solution is adversarial training. However, the tradition of generating adversarial perturbations for each input embedding (in the settings of NLP) scales up the training computational complexity by the number of gradien…