32 accepted papers
Despite extensive research on tactile sensing, exploiting it to model and interpret the external world remains largely underexplored. We propose a unified framework that leverages vision-based tactile sensors to construct fine-grained object models, enhancing situational understanding. This frame wo
Autonomous driving needs fast, scalable 4D reconstruction and re-simulation for training and evaluation, yet most methods for dynamic driving scenes still rely on per-scene optimization, known camera calibration, or short frame windows, making them slow and impractical. We revisit this problem from
Transparent objects remain notoriously hard for perception systems: refraction, reflection and transmission break the assumptions behind stereo, ToF and purely discriminative monocular depth, causing holes and temporally unstable estimates. Our key observation is that modern video diffusion models a…
While Multimodal Large Language Models (MLLMs) excel at single-image understanding, they exhibit significantly degraded performance in multi-image reasoning scenarios. Multi-image reasoning presents fundamental challenges including complex inter-relationships between images and scattered critical in
Recent embodied intelligence suffers from data scarcity, while conventional simulators lack visual realism. Controllable video generation is emerging as a promising data engine, yet current action-conditioned methods still fall short: generated videos are limited in fidelity and temporal consistency
High-quality 4D reconstruction enables photorealistic and immersive rendering of the dynamic real world. However, unlike static scenes that can be fully captured with a single camera, high-quality dynamic scenes typically require dense arrays of tens or even hundreds of synchronized cameras. Depende
Long context large language models (LLMs) pose significant challenges for efficient serving due to the large memory footprint and high access overhead of KV cache.Retrieval-based KV cache reduction methods can mitigate these challenges, typically by offloading the complete KV cache to CPU and retrie…
Evaluation plays a crucial role in the advancement of information retrieval (IR) models. However, current benchmarks, which are based on predefined domains and human-labeled data, face limitations in addressing evaluation needs for emerging domains both cost-effectively and efficiently. To address t…
The modeling of complicated time-evolving physical dynamics from partial observations is a long-standing challenge. Particularly, observations can be sparsely distributed in a seemingly random or unstructured manner, making it difficult to capture highly nonlinear features in a variety of scientific…
Survival prediction in PD-1 inhibitor patients has received extensive attention in recent years. Existing diffusion models generally focus blurring on key lesion regions, and the masks are weakly matched to CT images during the sampling process, resulting in a relatively high risk of misdiagnosis. F…
Vision-based tactile sensors have recently gained prominence due to their superior resolution and ability to capture multi-dimensional contact information. However, even when sensors share the same sensing principle, variations in production factors can lead to differences in the color patterns of t
Embedding-based retrieval (EBR), the mainstream approach in information retrieval (IR), aims to help users obtain relevant information and plays a crucial role in retrieval-augmented generation (RAG) techniques of large language models (LLMs). Numerous methods have been proposed to significantly imp…
In recent decades, chemistry publications and patents have increased rapidly. A significant portion of key information is embedded in molecular structure figures, complicating large-scale literature searches and limiting the application of large language models in fields such as biology, chemistry,…
Estimating the 6D pose of arbitrary objects from a single reference image is a critical yet challenging task in robotics, especially considering the long-tail distribution of real-world instances. While category-level and model-based approaches have achieved notable progress, they remain limited in…
Current robotic systems can understand the categories and poses of objects well. But understanding physical properties like mass, friction, and hardness, in the wild, remains challenging. We propose a new method that reconstructs 3D objects using the Gaussian splatting representation and predicts va
This letter presents a mechanically intelligent gripper that is capable of passive and adaptive object prehension, passive object retention, and passive object release. Passive adaptive prehension is achieved through a compliant linkage with two Fin Ray fingers that enclose an object when the grippe
Recognizing objects in the 3D world is a significant challenge for robotics. Due to the lack of high-quality 3D data, directly training a general-purpose segmentation model in 3D is almost infeasible. Meanwhile, vision foundation models (VFM) have revolutionized the 2D computer vision field with out
Revolutionizing novel view synthesis, 3D Gaussian Splatting has unlocked new horizons in 3D visual representation. Despite the efficiency and impressive rendering capabilities of GS, the accurate inverse rendering of reflectant non-Lambertian surfaces remains a significant challenge, particularly in…
Recent advances in large reconstruction and generative models have significantly improved scene reconstruction and novel view generation. However, due to compute limitations, each inference with these large models is confined to a small area, making long-range consistent scene generation challenging…
Neural rendering techniques, including NeRF and Gaussian Splatting (GS), rely on photometric consistency to produce high-quality reconstructions. However, in real-world driving scenarios, it is challenging to guarantee perfect photometric consistency in acquired images. Appearance codes have been wi…
Event Extraction (EE) is widely used in the Chinese financial field to provide valuable structured information. However, there are two key challenges for Chinese financial EE in application scenarios. First, events need to be extracted from raw texts, which sets it apart from previous works like the…
We propose a real-time visual-inertial dense SLAM system that utilizes the online data streams from back-to-back dual fisheye cameras setup, providing 360◦ coverage of the environment. Firstly, we employ a sliding-window-based front-end to estimate real-time poses from the binocular fisheye images a…
Prompt engineering is an essential technique for enhancing the abilities of large language models (LLMs) by providing explicit and specific instructions. It enables LLMs to excel in various tasks, such as arithmetic reasoning, question answering, summarization, relation extraction, machine translati…
Graph-based fraud detection (GFD) can be regarded as a challenging semi-supervised node binary classification task. In recent years, Graph Neural Networks (GNN) have been widely applied to GFD, characterizing the anomalous possibility of a node by aggregating neighbor information. However, fraud gra…
As language models become increasingly integrated into our digital lives, Personalized Text Generation (PTG) has emerged as a pivotal component with a wide range of applications. However, the bias inherent in user written text, often used for PTG model training, can inadvertently associate different…
Conversational Recommender Systems (CRS) actively elicit user preferences to generate adaptive recommendations. Mainstream reinforcement learning-based CRS solutions heavily rely on handcrafted reward functions, which may not be aligned with user intent in CRS tasks. Therefore, the design of task-sp…
Semantic Role Labeling (SRL) aims at recognizing the predicate-argument structure of a sentence and can be decomposed into two subtasks: predicate disambiguation and argument labeling. Prior work deals with these two tasks independently, which ignores the semantic connection between the two tasks. I…
Most real-world optimization problems have multiple objectives. A system designer needs to find a policy that trades off these objectives to reach a desired operating point. This problem has been studied extensively in the setting of known objective functions. However, we consider a more practical b…
In this paper, we propose a tightly-coupled SLAM system fused with RGB, Depth, IMU and structured plane information. Traditional sparse points based SLAM systems always maintain a mass of map points to model the environment. Huge number of map points bring us a high computational complexity, making…
We propose a bandit algorithm that explores purely by randomizing its past observations. In particular, the sufficient optimism in the mean reward estimates is achieved by exploiting the variance in the past observed rewards. We name the algorithm Capitalizing On Rewards (CORe). The algorithm is gen…
Summarization is an important natural language processing (NLP) task in identifying key information from text. For conversations, the summarization systems need to extract salient contents from spontaneous utterances by multiple speakers. In a special task-oriented scenario, namely medical conversat…