72 accepted papers
Large Reasoning Models (LRMs) like o3 and DeepSeek-R1 have achieved remarkable progress in natural language reasoning with long chain-of-thought. However, they remain computationally inefficient and struggle with accuracy when solving problems requiring complex mathematical operations. In this work,…
Dynamic data pruning accelerates deep learning by selectively omitting less informative samples during training. While per-sample loss is a common importance metric, obtaining it can be challenging or infeasible for complex models or loss functions, often requiring significant implementation effort.
Reasoning segmentation increasingly employs reinforcement learning to generate explanatory reasoning chains that guide Multimodal Large Language Models. While these geometric rewards are primarily confined to guiding the final localization, they are incapable of discriminating whether the reasoning
Directly modeling the explicit likelihood of the raw data distribution is a key topic in the machine learning area, which achieves the scaling success in Large Language Models by autoregressive modeling. However, continuous AR modeling over visual pixel data suffers from extremely long sequences and
Recently, continuous transform-based tensor representation has emerged as a promising tool for multi-dimensional data recovery. However, the existing continuous transforms are essentially single-layer linear mappings, which limits their ability to capture the complex relationships inherent in multi
Dynamic data pruning accelerates training by focusing on informative samples. However, comparing importance scores across different model states introduces inconsistency (score context drift), and variable selection rates bias gradient dynamics over time (temporal gradient bias). We introduce RePB (…
Self-speculative decoding (SSD) accelerates LLM inference by skipping layers to create an efficient draft model, yet existing methods often rely on static heuristics that ignore the dynamic computational overhead of attention in long-context scenarios. We propose KnapSpec, a training-free framework …
This paper focuses on the alignment of flow-matching models with human preference. A promising way is fine-tuning by directly backpropagating reward signals through the differentiable generation process of flow matching. However, backpropagating through long trajectories results in prohibitive memor
Critic-free methods like GRPO reduce memory demands by estimating advantages from multiple rollouts but tend to converge slowly, as critical learning signals are diluted by an abundance of uninformative samples and tokens. To tackle this challenge, we propose the **Dynamic Dual-Level Down-Sampling (…
LiDAR-based global localization provides accurate robot pose estimates against a prior map. Existing deep-learning methods, however, demand heavy computation and long training or inference times and degrade sharply when faced with domain shifts. This letter presents LighterBEV, a lightweight, fast,
LiDAR-based global localization provides accurate robot pose estimates against a prior map. Existing deep-learning methods, however, demand heavy computation and long training or inference times and degrade sharply when faced with domain shifts. This letter presents LighterBEV, a lightweight, fast, …
Recent research in long-form video generation has shifted from bidirectional to autoregressive models, yet these methods commonly suffer from error accumulation and a loss of long-term coherence. While attention sink frames have been introduced to mitigate this performance decay, they often induce a
Diffusion models have shown impressive performance in many visual generation and manipulation tasks. Many existing methods focus on training a model for a specific task, especially, text-to-video (T2V) generation, while many other works focus on finetuning the pretrained T2V model for image-to-video…
LiDAR place recognition is a critical component of LiDAR-based localization pipelines, tasked with identifying previously visited places across diverse environments and temporal conditions. A growing body of deep learning–based approaches has recently tackled this problem. However, their performance…
With the rapid growth of visual content in open-world environments, zero-shot hashing image retrieval (ZSHIR) has emerged to tackle the challenge of recognizing novel classes using attribute-level and semantic information. However, existing methods often rely on shallow fusion of multi-source cues
Diffusion models have revolutionized image and video generation, achieving unprecedented visual quality. However, their reliance on transformer architectures incurs prohibitively high computational costs, particularly when extending generation to long videos. Recent work has explored autoregressive…
Token merging accelerates Transformer inference by clustering similar tokens to reduce sequence length (retention ratio $r$), but distorts attention outputs, inducing covariate shift in residual streams and performance collapse under high compression. Existing heuristics, such as proportional attent…
The Unaligned Multi-view Clustering (UMC) aims to learn a discriminative cluster structure from unaligned multi-view data, where the features of samples are not completely aligned across multiple views. Most existing methods usually prioritize employing various alignment strategies to align sample r…
Graph contrastive learning (GCL) aims to learn self-supervised representations by distinguishing positive and negative sample pairs generated from multiple augmented graph views. Despite showing promising performance, GCL still suffers from two critical biases: (1) ***Similarity estimation bias*** a…
Process reward models (PRMs) provide more nuanced supervision compared to outcome reward models (ORMs) for optimizing policy models, positioning them as a promising approach to enhancing the capabilities of LLMs in complex reasoning tasks. Recent efforts have advanced PRMs from step-level to token-l…
To address complex mission tasks, multirotors benefit from in-flight reconfiguration that enhances their morphological adaptability. This paper presents the Center-Driven Scissor Extendable Airframe (CDSEA), a novel one-degree-of-freedom (DOF) morphing airframe designed to replace traditional fixed-
Large language models (LLMs) have demonstrated strong reasoning and tool-use capabilities, yet they often fail in real-world tool-interactions due to incorrect parameterization, poor tool selection, or misinterpretation of user intent. These issues often stem from an incomplete understanding of user
Automated Theorem Proving (ATP) in formal languages remains a formidable challenge in AI, demanding rigorous logical deduction and navigating vast search spaces. While large language models (LLMs) have shown promising performance, existing stepwise provers often suffer from biased search guidance, l…
Vision-based multi-drone multi-object tracking technology enables autonomous target situational awareness for unmanned aerial systems. Distributed observer drones dynamically estimate the spatio-temporal states of multiple targets through collaborative sensor fusion, enabling simultaneous localizati
While Large Language Models (LLMs) demonstrate strong performance across domains, their long-context capabilities are limited by transient neural activations causing information decay and unstructured feed-forward network (FFN) weights leading to semantic fragmentation. Inspired by the brain’s worki…
Activation sparsity refers to the existence of considerable weakly-contributed elements among activation outputs, serving as a promising paradigm for accelerating model inference. Nevertheless, most large language models (LLMs) adopt activation functions without intrinsic activation sparsity (e.g.,…
Pre-trained language models (PrLMs) demonstrate impressive performance on the sentiment analysis task. However, the large number of trainable parameters brings about heavy computational costs, which become more serious in multi-domain scenarios. In this paper, we propose to extract multi-layer featu…
Despite the significant advancements, existing object removal methods struggle with incomplete removal, incorrect content synthesis and blurry synthesized regions, resulting in low success rates. Such issues are mainly caused by the lack of high-quality paired training data, as well as the self-supe…
In-context learning, i.e., learning from context examples, is an impressive ability of Transformer. Training Transformers to possess this in-context learning skill is computationally intensive due to the occurrence of *learning plateaus*, which are periods within the training process where there is…
"Representation disentanglement may help AI fundamentally understand the real world and thus benefit both discrimination and generation tasks. It currently has at least three unresolved core issues: (i) heavy reliance on label annotation and synthetic data — causing poor generalization on natural sc…
Disentangled representation learning strives to extract the intrinsic factors within the observed data. Factoring these representations in an unsupervised manner is notably challenging and usually requires tailored loss functions or specific structural designs. In this paper, we introduce a new pers…
LiDAR Place Recognition (LPR) aims to identify previously visited places across different environments and times. Thanks to the recent advances in Deep Neural Networks (DNNs), LPR has experienced rapid development. However, DNN-based LPR methods may suffer from Catastrophic Forgetting (CF), where th
We present MicroCinema a straightforward yet effective framework for high-quality and coherent text-to-video generation. Unlike existing approaches that align text prompts with video directly MicroCinema introduces a Divide-and-Conquer strategy which divides the text-to-video into a two-stage proces…
Autonomous vehicles require online learning capabilities to enable long-term, unattended operation. However, long-term online learning is accompanied by the problem of forgetting previously learned knowledge. This paper introduces an online learning framework that includes a catastrophic forgetting…
Recently it has been shown that deep learning models for NLP tasks are prone to attacks that can even reconstruct the verbatim training texts. To prevent privacy leakage, researchers have investigated word-level perturbations, relying on the formal guarantees of differential privacy (DP) in the embe…
We present a Multi-Stereoscopic Visual-Inertial Odometry (VIO) system capable of integrating an arbitrary number of stereo cameras, exhibiting excellent robustness in the face of visually challenging scenarios. During system initialization, we introduce multi-view keyframes for simultaneous processi
Large language models (LLMs) can make predictions using *parametric knowledge* – knowledge encoded in the model weights – or *contextual knowledge* – knowledge presented in the context. In many scenarios, a desirable behavior is that LLMs give precedence to contextual knowledge when it conflicts wit…
Owe to the powerful generative priors the pre-trained text-to-image (T2I) diffusion models have become increasingly popular in solving the real-world image super-resolution problem. However as a consequence of the heavy quality degradation of input low-resolution (LR) images the destruction of local…
This paper revisits dynamic pruning through rank score thresholding in cluster-based sparse retrieval to skip the index partially at cluster and document levels during inference. It proposes a two-parameter pruning control scheme called ASC with a probabilistic guarantee on rank-safeness competitive…
Denoising diffusion (score-based) generative models have become a popular choice for modeling complex data. Recently, a deep connection between forward-backward stochastic differential equations (SDEs) and diffusion-based models has been established, leading to the development of new SDE variants su…
Contrastive learning has been widely studied in sentence representation learning. However, earlier works mainly focus on the construction of positive examples, while in-batch samples are often simply treated as negative examples. This approach overlooks the importance of selecting appropriate negati…
Image colorization is a challenging problem due to multi-modal uncertainty and high ill-posedness. Directly training a deep neural network usually leads to incorrect semantic colors and low color richness. While transformer-based methods can deliver better results, they often rely on manually design…
Targeting to understand the underlying explainable factors behind observations and modeling the conditional generation process on these factors, we connect disentangled representation learning to diffusion probabilistic models (DPMs) to take advantage of the remarkable modeling ability of DPMs. We p…
Efficient knowledge retrieval plays a pivotal role in ensuring the success of end-to-end task-oriented dialogue systems by facilitating the selection of relevant information necessary to fulfill user requests. However, current approaches generally integrate knowledge retrieval and response generatio…
Instruction-tuning can be substantially optimized through enhanced diversity, resulting in models capable of handling a broader spectrum of tasks. However, existing data employed for such tuning often exhibit an inadequate coverage of individual domains, limiting the scope for nuanced comprehension…
Predicting personality traits based on online posts has emerged as an important task in many fields such as social network analysis. One of the challenges of this task is assembling information from various posts into an overall profile for each user. While many previous solutions simply concatenate…
Recent advances in large language models (LLMs), such as ChatGPT, have showcased remarkable zero-shot performance across various NLP tasks. However, the potential of LLMs in personality detection, which involves identifying an individual's personality from their written texts, remains largely unexpl…
We introduce the task of correcting named entity recognition (NER) errors without re-training model. After an NER model is trained and deployed in production,it makes prediction errors, which usually need to be fixed quickly. To address this problem, we firstly construct a gazetteer containing named…
Fine-tuning large pre-trained language models on downstream tasks is apt to suffer from overfitting when limited training data is available. While dropout proves to be an effective antidote by randomly dropping a proportion of units, existing research has not examined its effect on the self-attentio…
The deep policy gradient method has demonstrated promising results in many large-scale games, where the agent learns purely from its own experience. Yet, policy gradient methods with self-play suffer convergence problems to a Nash Equilibrium (NE) in multi-agent situations. Counterfactual regret min…
Recently, Bert-based models have dominated the research of Chinese spelling correction (CSC). These methods have two limitations: (1) they have poor performance on multi-typo texts. In such texts, the context of each typo contains at least one misspelled character, which brings noise information. Su…
Transformer based re-ranking models can achieve high search relevance through context- aware soft matching of query tokens with document tokens. To alleviate runtime complexity of such inference, previous work has adopted a late interaction architecture with pre-computed contextual token representat…
As a common problem in the visual world, contextual bias means the recognition may depend on the co-occurrence context rather than the objects themselves, which is even more severe in multi-label tasks due to multiple targets and the absence of location. Although some studies have focused on tacklin…
The cell-free massive Multiple Input Multiple Output (MIMO) architecture is considered for millimeter Wave (mmWave) bands to overcome propagation challenges at higher frequencies such as significant pathloss, easy blockage, and shadowing. Instead of using a single and co-located extreme large antenn…
Chinese Grammatical Error Detection(CGED) aims at detecting grammatical errors in Chinese texts. One of the main challenges for CGED is the lack of annotated data. To alleviate this problem, previous studies proposed various methods to automatically generate more training samples, which can be rough…
From the intuitive notion of disentanglement, the image variations corresponding to different generative factors should be distinct from each other, and the disentangled representation should reflect those variations with separate dimensions. To discover the generative factors and learn disentangled…
Disentangled representation learning is one of the major goals of deep learning, and is a key step for achieving explainable and generalizable models. The key idea of the state-of-the-art VAE-based unsupervised representation disentanglement methods is to minimize the total correlation of the joint…
Obtaining the human-like perception ability of abstracting visual concepts from concrete pixels has always been a fundamental and important target in machine learning research fields such as disentangled representation learning and scene decomposition. Towards this goal, we propose an unsupervised t…
Blind face restoration (BFR) from severely degraded face images in the wild is a very challenging problem. Due to the high illness of the problem and the complex unknown degradation, directly training a deep neural network (DNN) usually cannot lead to acceptable results. Existing generative adversar…
Interactions between entities in knowledge graph (KG) provide rich knowledge for language representation learning. However, existing knowledge-enhanced pretrained language models (PLMs) only focus on entity information and ignore the fine-grained relationships between entities. In this work, we prop…
Existing text-based personality detection research mostly relies on data-driven approaches to implicitly capture personality cues in online posts, lacking the guidance of psychological knowledge. Psychological questionnaire, which contains a series of dedicated questions highly related to personalit…
Extractive text summarization aims at extracting the most representative sentences from a given document as its summary. To extract a good summary from a long text document, sentence embedding plays an important role. Recent studies have leveraged graph neural networks to capture the inter-sententia…
Chinese spelling correction (CSC) is a task to detect and correct spelling errors in texts. CSC is essentially a linguistic problem, thus the ability of language understanding is crucial to this task. In this paper, we propose a Pre-trained masked Language model with Misspelled knowledgE (PLOME) for…
Most of the recent work on personality detection from online posts adopts multifarious deep neural networks to represent the posts and builds predictive models in a data-driven manner, without the exploitation of psycholinguistic knowledge that may unveil the connections between one’s language use a…
This paper considers online convex optimization with long term constraints, where constraints can be violated in intermediate rounds, but need to be satisfied in the long run. The cumulative constraint violation is used as the metric to measure constraint violations, which excludes the situation tha…
Motion prediction of vehicles is critical but challenging due to the uncertainties in complex environments and the limited visibility caused by occlusions and limited sensor ranges. In this paper, we study a new task, safety-aware motion prediction with unseen vehicles for autonomous driving. Unlike…
As a critical sensor for high-level autonomous vehicles, LiDAR's limitations in adverse weather (e.g. rain, fog, snow, etc.) impede the deployment of self-driving cars in all weather conditions. In this paper, we model the performance of a popular 903nm ToF LiDAR under various fog conditions based o…
This paper focuses on designing, modeling and validating a novel scalable multicopter whose deformation mechanism, called SNIAE-SSE, relies on a combination of simple non-intersecting angulated elements (SNIAEs) and straight scissor-like elements (SSEs). The proposed SNIAE-SSE mechanism has the adva…
Multi-beam mobile satellite systems aim at providing broadband and high speed mobile services over a large area to achieve a high system throughput, where hybrid space-ground beamforming is one of the most promising candidates for ground-based beamforming techniques. It not only reduces the feeder l…
Time delay estimation (TDE) plays an important role in localizing and tracking radiating acoustic sources. Although many efforts have been devoted to this problem in the literature, the robustness of TDE with respect to noise and reverberation remains a great challenge for practical systems. In this…
Noise and reverberation can significantly affect the performance of time delay estimation (TDE) in room acoustic environments. The multichannel cross-correlation coefficient (MCCC) algorithm, which extends the traditional cross-correlation method from two to multiple channels, can exploit the spatia…
In this paper, we consider the recovery of piecewise sparse signals from incomplete noisy measurements via a greedy algorithm. Here piecewise sparse means that the signal can be approximated in certain domain with known number of nonzero entries in each piece/segment. This paper makes a two-fold con…