41 accepted papers
Test-time scaling (TTS) has demonstrated remarkable potential in enhancing the reasoning capabilities of Large Language Models (LLMs) and Large Vision-Language Models (LVLMs). However, its application has primarily been limited to domains such as mathematics and programming, owing to their reasoning
This work presents Prior Depth Anything, a framework that combines incomplete but precise metric information in depth measurement with relative but complete geometric structures in depth prediction, generating accurate, dense, and detailed metric depth maps for any scene. To this end, we design a co…
Maximizing conditional mutual information (CMI) has recently been shown to enhance the effectiveness of teacher networks in knowledge distillation (KD). Prior work achieves this by fine-tuning a pretrained teacher to maximize a proxy of its CMI. However, fine-tuning large-scale teachers is often imp…
Neural audio codec (NAC) is essential for reconstructing high-quality speech signals and generating discrete representations for downstream speech language models. However, ensuring accurate semantic modeling while maintaining high-fidelity reconstruction under ultra-low bitrate constraints remains…
The huge parameters and extensive training corpora of Large Language Models (LLMs) empower them to tackle complex tasks. Yet, their massive size incurs substantial inference costs, hindering deployment on resource‑constrained edge devices. Low‑bit quantization provides a way to compress models and i
Transformers have demonstrated remarkable in-context learning abilities, adapting to new tasks from just a few examples without parameter updates. However, theoretical understanding of this phenomenon typically assumes fixed dependency structures, while real-world sequences exhibit flexible, context…
Enabling multi-task adaptation in pre-trained Low-Rank Adaptation (LoRA) models is crucial for enhancing their generalization capabilities. Most existing pre-trained LoRA fusion methods decompose weight matrices, sharing similar parameters, while fusion divergent ones. However, this paradigm inevit
In natural scenarios, vision models often encounter the challenge of complex degradation scenarios(e.g., rain, snow, fog, or motion blur). These degradations severely corrupt image features, causing existing models to treat rarely seen or unseen degraded images as “unfamiliar”, thereby losing their
Accurate 3D instance segmentation is crucial for high-quality scene understanding in the 3D vision domain. However, 3D instance segmentation based on 2D-to-3D lifting approaches struggle to produce precise instance-level segmentation, due to accumulated errors introduced during the lifting process f
We introduce SpatialHand, a novel framework for generative object insertion with precise 3D control. Current generative object manipulation methods primarily operate within the 2D image plane, but often fail to grasp 3D scene complexities, leading to ambiguities in an object's 3D position, orientati…
Diffusion models have been widely adopted in image and video generation. However, their complex network architecture leads to high inference overhead for its generation process. Existing diffusion quantization methods primarily focus on the quantization of the model structure while ignoring the impa
We study the challenge of achieving theoretically grounded feature recovery using Sparse Autoencoders (SAEs) for the interpretation of Large Language Models. Existing SAE training algorithms often lack rigorous mathematical guarantees and suffer from practical limitations such as hyperparameter sen…
Bandeira et al. (2022) introduced the Franz-Parisi (FP) criterion for characterizing the computational hard phases in statistical detection problems. The FP criterion, based on an annealed version of the celebrated Franz-Parisi potential from statistical physics, was shown to be equivalent to low-de…
In this work, we tackle the following question: Can neural networks trained with gradient-based methods achieve the optimal statistical-computational tradeoff in learning Gaussian single-index models? Prior research has shown that any polynomial-time algorithm under the statistical query (SQ) frame…
RGB-D has gradually become a crucial data source for understanding complex scenes in assisted driving. However, existing studies have paid insufficient attention to the intrinsic spatial properties of depth maps. This oversight significantly impacts the attention representation, leading to predictio
Gaussian Splatting SLAM (GS-SLAM) offers a notable improvement over traditional SLAM methods, in enabling photorealistic 3D reconstruction that conventional approaches often struggle to achieve. However, existing GS-SLAM systems perform poorly under persistent and severe motion blur commonly encount
3D gaussian splatting has advanced simultaneous localization and mapping (SLAM) technology by enabling realtime positioning and the construction of high-fidelity maps. However, the uncertainty in gaussian position and initialization parameters introduces challenges, often requiring extensive iterati
We study how multi-head softmax attention models are trained to perform in-context learning on linear data. Through extensive empirical experiments and rigorous theoretical analysis, we demystify the emergence of elegant attention patterns: a diagonal and homogeneous pattern in the key-query weight…
Low-rank Adaptation (LoRA) has demonstrated remarkable capabilities for task specific fine-tuning. However, in scenarios that involve multiple tasks, training a separate LoRA model for each one results in considerable inefficiency in terms of storage and inference. Moreover, existing parameter gener
Ultra-wideband (UWB) is gaining popularity with devices like AirTags for precise home item localization but faces significant challenges when scaled to large environments like seaports. The main challenges are calibration and localization under obstructed conditions, which are common in logistics en
Open-Vocabulary semantic segmentation (OVSS) and domain generalization in semantic segmentation (DGSS) highlight a subtle complementarity that motivates Open-Vocabulary Domain-Generalized Semantic Segmentation (OV-DGSS). OV-DGSS aims to generate pixel-level masks for unseen categories while maintain…
A high-performance image compression algorithm is crucial for real-time information transmission across numerous fields. Despite rapid progress in image compression, computational inefficiency and poor redundancy modeling still pose significant bottlenecks, limiting practical applications. Inspired…
Existing research in Stock Trend Prediction (STP) focuses on temporal features extracted from a temporal sequence of stock data with a look-back window, which frequently leads to the omission of important periodic patterns, such as weekly and monthly variations in stock prices. Furthermore, these me
In recent years, Wi-Fi sensing has attracted much attention due to the widespread deployment of communication devices. Due to advancements in signal processing algorithms, contactless sensing technology based on Wi-Fi signals has now been widely applied. However, the limited bandwidth of Wi-Fi syste…
Vision Foundation Models (VFMs) have delivered remarkable performance in Domain Generalized Semantic Segmentation (DGSS). However, recent methods often overlook the fact that visual cues are susceptible, whereas the underlying geometry remains stable, rendering depth information more robust. In this…
Accurate segmentation of lesions is crucial for disease diagnosis and treatment planning. However, blurring and low contrast in the imaging process can affect segmentation results. We have observed that noninvasive medical imaging shares considerable similarities with natural images under low light
Retrieval Augmented Generation (RAG) has gained widespread adoption owing to its capacity to empower large language models (LLMs) to integrate external knowledge. However, existing RAG frameworks are primarily designed for text-based LLMs and rely on Automatic Speech Recognition to process speech in…
In this work, from a theoretical lens, we aim to understand why large language model (LLM) empowered agents are able to solve decision-making problems in the physical world. To this end, consider a hierarchical reinforcement learning (RL) model where the LLM Planner and the Actor perform high-level…
Visual Odometry (VO) is vital for the navigation of autonomous systems, providing accurate position and orientation estimates at reasonable costs. While traditional VO methods excel in some conditions, they struggle with challenges like variable lighting and motion blur. Deep learning-based VO, thou
In-context learning (ICL) is a cornerstone of large language model (LLM) functionality, yet its theoretical foundations remain elusive due to the complexity of transformer architectures. In particular, most existing work only theoretically explains how the attention mechanism facilitates ICL under c…
Medical images usually suffer from image degradation in clinical practice, leading to decreased performance of deep learning-based models. To resolve this problem, most previous works have focused on filtering out degradation-causing low-quality images while ignoring their potential value for models…
We study the incentivized information acquisition problem, where a principal hires an agent to gather information on her behalf. Such a problem is modeled as a Stackelberg game between the principal and the agent, where the principal announces a scoring rule that specifies the payment, and then the…
Deep learning has had remarkable success in robotic perception, but its data-centric nature suffers when it comes to generalizing to ever-changing environments. By contrast, physics-based optimization generalizes better, but it does not perform as well in complicated tasks due to the lack of high-le…
In a Markov decision process (MDP), an agent interacts with the environment via perceptions and actions. During this process, the agent aims to maximize its own gain. Hence, appropriate regulations are often required, if we hope to take the external costs/benefits of its actions into consideration.…
Pneumatic-driven soft manipulator has great flexibility and adaptability, which makes it can do some complex tasks that traditional robots can't do such as minimally invasive surgery, detection, search and rescue, et al. However, due to the low stiffness of pneumatic-drive soft manipulator, it faces
Event extraction aims to identify an event and then extract the arguments participating in the event. Despite the great success in sentence-level event extraction, events are more naturally presented in the form of documents, with event arguments scattered in multiple sentences. However, a major bar…
"In computer vision, pre-training models based on large-scale supervised learning have been proven effective over the past few years. However, existing works mostly focus on learning from the individual tasks with the single data source e.g., ImageNet for classification or COCO for detection). This…
Localizing persons and recognizing their actions from videos is a challenging task towards high-level video under-standing. Recent advances have been achieved by modeling direct pairwise relations between entities. In this paper, we take one step further, not only model direct relations between pair…
The rapid progress of photorealistic synthesis techniques has reached at a critical point where the boundary between real and manipulated images starts to blur. Thus, benchmarking and advancing digital forgery analysis have become a pressing issue. However, existing face forgery datasets either have…
Actor-critic (AC) algorithms, empowered by neural networks, have had significant empirical success in recent years. However, most of the existing theoretical support for AC algorithms focuses on the case of linear function approximations, or linearized neural networks, where the feature representat…