45 accepted papers
For effective deployment in real-world environments, humanoid robots must autonomously navigate a diverse range of complex terrains with abrupt transitions. While the Vanilla mixture of experts (MoE) framework is theoretically capable of modeling diverse terrain features, in practice, the gating net…
The sharp, intricate contours of lunar regolith particles hold critical clues to the Moon
Leveraging offline data is a promising way to improve the sample efficiency of online reinforcement learning (RL). This paper expands the pool of usable data for offline-to-online RL by leveraging abundant non-curated data that is reward-free, of mixed quality, and collected across multiple embodime…
Foundation models have driven rapid progress in computer vision, yet the two dominant paradigm, vision-language foundation models (VLMs) and vision-only foundation models (VFMs), remain only partially compatible. VLMs offer language-grounded semantic alignment but are often visually coarse, while VF…
Recently, a line of works can generate impressive 3D objects from a single image, but they are limited by restricted representation resolution, making them unsuitable for 3D scene generation. In this work, we introduce \name, a novel method for high-quality 3D scene generation based on hierarchical …
Learning causal structures from temporal data is fundamental to many practical tasks, such as physical laws discovery and root causes localization. Real-world systems often exhibit long-term carry-over effects, where the value of a variable at the current time can be influenced by distant past va…
Navigation instruction generation for visually impaired (VI) individuals (NIG-VI) is critical yet relatively underexplored. This study focuses on generating precise, in-situ, step-by-step navigation instructions that are practically usable for VI users. Specifically, we propose LaF-GRPO (LLM-as-Foll
Body-surface health conditions, spanning diverse clinical departments, represent some of the most frequent diagnostic scenarios and a primary target for medical multimodal large language models (MLLMs). Yet existing medical benchmarks are either built from publicly available sources with limited ex…
Vision-Language Models such as CLIP exhibit strong zero-shot recognition capability by aligning images with textual concepts, yet they often underperform on multi-label recognition where multiple objects co-exist. A key bottleneck is that the CLS token, as a single global visual representation, is i…
Physical intelligence for aerial robots greatly enhances grasping and perching performance, but remains in emerging stages. This letter proposes a novel bistable soft gripper for aerial robots with high response speed (0.11s), large holding force (23.47N), and active/passive adaptive grasping and pe
Keyboard-based interaction may not accommodate various needs, especially for individuals with disabilities. While inertial sensor-based writing recognition is promising due to the sensors’ small size, wearability, and low cost, accurate recognition in the Chinese context is hampered by the difficult…
Task-agnostic prompt compression leverages the redundancy in natural language to reduce computational overhead and enhance information density within prompts, especially in long-context scenarios. Existing methods predominantly rely on information entropy as the metric to compress lexical units, aim…
In reinforcement learning (RL), world models serve as internal simulators, enabling agents to predict environment dynamics and future outcomes in order to make informed decisions. While previous approaches leveraging discrete latent spaces, such as DreamerV3, have demonstrated strong performance in…
Visual planning, by offering a sequence of intermediate visual subgoals to a goal-conditioned low-level policy, achieves promising performance on long-horizon manipulation tasks. To obtain the subgoals, existing methods typically resort to video generation models but suffer from model hallucination…
Motor Imagery (MI) is essential in Brain-Computer Interfaces (BCIs), highlighting the central role of electroencephalography (EEG) in this technology. However, the amount of raw EEG data is often limited. Raw EEG data contains significant noise caused by individual and task-specific differences. The…
Low-cost accelerometers play a crucial role in modern society due to their advantages of small size, ease of integration, wearability, and mass production, making them widely applicable in automotive systems, aerospace, and wearable technology. However, this widely used sensor suffers from severe ac…
In complex missions such as search and rescue, robots must make intelligent decisions in unknown environments, relying on their ability to perceive and understand their surroundings. High-quality and real-time reconstruction enhances situational awareness and is crucial for intelligent robotics. Tra
Inertial sensors are widely used in modern society, covering automotive, aerospace, robotics, and consumer electronics. However, these widely used sensors suffer from range limitations, causing signal saturation and information loss under high-dynamic motion conditions. To address this problem, we i…
LLMs encounter significant challenges in resource consumption nowadays, especially with long contexts. Despite extensive efforts dedicate to enhancing inference efficiency, these methods primarily exploit internal sparsity within the models, without leveraging external information for optimization.…
A brain-computer interface (BCI) offers an innovative solution for facilitating communication and control in individuals with paralysis. BCI reflects brain activity by decoding electroencephalogram (EEG) signals. Despite numerous techniques for classifying motor imagery (MI) EEG signals, challenges…
KV cache eviction has emerged as an effective solution to alleviate resource constraints faced by LLMs in long-context scenarios. However, existing token-level eviction methods often overlook two critical aspects: (1) their irreversible eviction strategy fails to adapt to dynamic attention patterns…
Trajectory optimization in multi-vehicle scenarios faces challenges due to its non-linear, non-convex properties and sensitivity to initial values, making interactions between vehicles difficult to control. In this paper, inspired by topological planning, we propose a differentiable local homotopy i
3D molecule generation is crucial for drug discovery and material science, requiring models to process complex multi-modalities, including atom types, chemical bonds, and 3D coordinates. A key challenge is integrating these modalities of different shapes while maintaining SE(3) equivariance for 3D c…
The non-consensual exploitation of facial manipulation has emerged as a pressing societal concern. In tandem with the identification of such fake content, recent research endeavors have advocated countering manipulation techniques through proactive interventions, specifically the incorporation of ad…
Imitation learning from human motion capture (MoCap) data provides a promising way to train humanoid robots. However, due to differences in morphology, such as varying degrees of joint freedom and force limits, exact replication of human behaviors may not be feasible for humanoid robots. Consequentl…
Recent progress has propelled the development of realistic talking-face videos for avatars. Yet, animating 3D cartoon avatars remains intricate due to the imprecise nature of facial-driven data. This often manifests as inconsistent mouth configurations and rigid facial expressions, curbing the anima…
Full-parameter fine-tuning is computationally prohibitive for large language models (LLMs), making parameter-efficient fine-tuning (PEFT) methods like low-rank adaptation (LoRA) increasingly popular. However, LoRA and its existing variants introduce significant latency in multi-tenant settings, hind…
Generative self-supervised learning, represented by graph autoencoders (GAEs), has begun to exhibit significant potential in addressing graph tasks. However, GAEs often rely on Graph Neural Networks (GNNs) for encoding and decoding, this can pose a computation challenge due to the inherent complexit…
Text-to-speech (TTS) methods have shown promising results in voice cloning, but they require a large number of labeled text-speech pairs. Minimally-supervised speech synthesis decouples TTS by combining two types of discrete speech representations(semantic & acoustic) and using two sequence-to-seque…
IEEE Automatic Mean Opinion Score (MOS) prediction is employed to evaluate the quality of synthetic speech. This study extends the application of predicted MOS to the task of Fake Audio Detection (FAD) as we expect that MOS can be used to assess how close synthesized speech is to the natural human v…
Low-rank adaptation (LoRA) and its mixture-of-experts (MOE) variants are highly effective parameter-efficient fine-tuning (PEFT) methods. However, they introduce significant latency in multi-tenant settings due to the LoRA modules and MOE routers added to multiple linear modules in the Transformer l…
*Relative overgeneralization* (RO) occurs in cooperative multi-agent learning tasks when agents converge towards a suboptimal joint policy due to overfitting to suboptimal behaviors of other agents. No methods have been proposed for addressing RO in multi-agent policy gradient (MAPG) methods althoug…
In the realm of parameter-efficient fine-tuning (PEFT) methods, while options like LoRA are available, there is a persistent demand in the industry for a PEFT approach that excels in both efficiency and performance within the context of single-backbone multi-tenant applications. This paper introduce…
Endowing robot hands with human-level dexterity is a long-lasting research objective. Bi-manual robot piano playing constitutes a task that combines challenges from dynamic tasks, such as generating fast while precise motions, with slower but contact-rich manipulation problems. Although reinforcemen…
Fact-checking is the task of verifying the factuality of a given claim by examining the available evidence. High-quality evidence plays a vital role in enhancing fact-checking systems and facilitating the generation of explanations that are understandable to humans. However, the provision of both su…
Inertial sensors, serving as attitude and motion sensing components, are extensively used in various portable devices spanning consumer electronics, sports health, aerospace, etc. However, the severe intrinsic errors of inertial sensors greatly restrict their capability to implement advanced functio…
As attitude and motion sensing components, inertial sensors are widely used in various portable devices, covering consumer electronics, sports health, aerospace, etc. But the severe intrinsic errors of inertial sensors heavily restrain their function implementation, especially the advanced functiona…
Reinforcement learning (RL) is able to solve complex sequential decision-making tasks but is currently limited by sample efficiency and required computation. To improve sample efficiency, recent work focuses on model-based RL which interleaves model learning with planning. Recent methods further uti…
The creation of long melody sequences requires effective expression of coherent musical structure. However, there is no clear representation of musical structure. Recent works on music generation have suggested various approaches to deal with the structural information of music, but generating a ful…
Multimodal sentiment analysis (MSA) and emotion recognition in conversation (ERC) are key research topics for computers to understand human behaviors. From a psychological perspective, emotions are the expression of affect or feelings during a short period, while sentiments are formed and held for a…
Emotion cause extraction (ECE) aims to extract the causes behind the certain emotion in text. Some works related to the ECE task have been published and attracted lots of attention in recent years. However, these methods neglect two major issues: 1) pay few attentions to the effect of document-level…
Fully immersive experiences in AR/VR depend on reconstructing the full body pose of the user without restricting their motion. In this paper we study the use of body-worn electromagnetic (EM) field-based sensing for the task of 3D human pose reconstruction. To this end, we present a method to estima…
We present a new approach to disentangle speaker voice and phone content by introducing new components to the VQ-VAE architecture for speech synthesis. The original VQ-VAE does not generalize well to unseen speakers or content. To alleviate this problem, we have incorporated a speaker encoder and sp…
Visual localization is critical to many applications in computer vision and robotics. To address single-image RGB localization, state-of-the-art feature-based methods match local descriptors between a query image and a pre-built 3D model. Recently, deep neural networks have been exploited to regress…
Recent neural waveform synthesizers such as WaveNet, WaveG-low, and the neural-source-filter (NSF) model have shown good performance in speech synthesis despite their different methods of waveform generation. The similarity between speech and music audio synthesis techniques suggests interesting ave…