Related papers: Why Any-Order Autoregressive Models Need Two-Strea…
Masked diffusion models (MDMs) are a potential alternative to autoregressive models (ARMs) for language generation, but generation quality depends critically on the generation order. Prior work either hard-codes an ordering (e.g., blockwise…
When trained on tasks requiring an understanding of hierarchical structure, transformers have been found to represent this hierarchy in distinct ways: in the geometry of the residual stream, and in stack-like attention patterns maintaining…
Predicting the next pickup location of individual users is a fundamental problem in intelligent mobility systems, which requires modeling personalized travel behaviors under complex spatiotemporal contexts. Existing methods mainly learn…
Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end (E2E) Automatic Speech Recognition (ASR). The joint CTC/Attention model has achieved great success by…
The reasoning pattern of Large language models (LLMs) remains opaque, and Reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps. This work…
Two-stage adaptive robust optimization (ARO) is a powerful approach for planning under uncertainty, balancing first-stage decisions with recourse decisions made after uncertainty is realized. To account for uncertainty, modelers typically…
When training transformers on graph-structured data, incorporating information about the underlying topology is crucial for good performance. Topological masking, a type of relative position encoding, achieves this by upweighting or…
Segment anything model (SAM) has shown impressive general-purpose segmentation performance on natural images, but its performance on camouflaged object detection (COD) is unsatisfactory. In this paper, we propose SAM-COD that performs…
We investigate a monotonic multihead attention (MMA) by extending hard monotonic attention to Transformer-based automatic speech recognition (ASR) for online streaming applications. For streaming inference, all monotonic attention (MA)…
Multimedia or spoken content presents more attractive information than plain text content, but the former is more difficult to display on a screen and be selected by a user. As a result, accessing large collections of the former is much…
Recently, the open-vocabulary semantic segmentation problem has attracted increasing attention and the best performing methods are based on two-stream networks: one stream for proposal mask generation and the other for segment…
Online Active Learning (OAL) aims to manage unlabeled datastream by selectively querying the label of data. OAL is applicable to many real-world problems, such as anomaly detection in health-care and finance. In these problems, there are…
Although end-to-end (E2E) trainable automatic speech recognition (ASR) has shown great success by jointly learning acoustic and linguistic information, it still suffers from the effect of domain shifts, thus limiting potential applications.…
Large-scale live-streaming recommendation requires precise modeling of non-stationary content semantics under strict real-time serving constraints. In industrial deployment, two common approaches exhibit fundamental limitations: discrete…
Lane segment topology reasoning constructs a comprehensive road network by capturing the topological relationships between lane segments and their semantic types. This enables end-to-end autonomous driving systems to perform road-dependent…
We propose a novel end-to-end document understanding model called SeRum (SElective Region Understanding Model) for extracting meaningful information from document images, including document analysis, retrieval, and office automation. Unlike…
Tensor Attention extends traditional attention mechanisms by capturing high-order correlations across multiple modalities, addressing the limitations of classical matrix-based attention. Meanwhile, Rotary Position Embedding…
Emergent communication enables partially observant Autonomous Mobile Robots (AMRs) to coordinate effectively in decentralized multi-agent reinforcement learning (MARL) settings. However, existing approaches often struggle with unstable…
Recent diffusion-based image editing methods commonly rely on text or high-level instructions to guide the generation process, offering intuitive but coarse control. In contrast, we focus on explicit, prompt-free editing, where the user…
Reduced order models (ROMs) play a critical role in fluid mechanics by providing low-cost predictions, making them an attractive tool for engineering applications. However, for ROMs to be widely applicable, they must not only generalise…