Related papers: Latent Flow Transformer
Large language and vision models (LLVMs) have been driven by the generalization power of large language models (LLMs) and the advent of visual instruction tuning. Along with scaling them up directly, these models enable LLVMs to showcase…
Recent byte-level language models (LMs) match the performance of token-level models without relying on subword vocabularies, yet their utility is limited by slow, byte-by-byte autoregressive generation. We address this bottleneck in the…
The growing complexity of network traffic and demand for ultra-low latency communication require smarter packet traffic management. Existing Deep Learning-based queuing approaches struggle with dynamic network scenarios and demand high…
Prompt tuning is an emerging way of adapting pre-trained language models to downstream tasks. However, the existing studies are mainly to add prompts to the input sequence. This way would not work as expected due to the intermediate…
General-purpose Large Language Models (LLMs) are frequently fine-tuned through supervised fine-tuning (SFT) to enhance performance in specific domains. Better results can be achieved by distilling the chain-of-thought of a larger model at…
We introduce the Latent Fourier Transform (LatentFT), a framework that provides novel frequency-domain controls for generative music models. LatentFT combines a diffusion autoencoder with a latent-space Fourier transform to separate musical…
Recent advances in generative models, such as diffusion and flow matching, have shown strong performance in audio tasks. However, speech enhancement (SE) models are typically trained on limited datasets and evaluated under narrow…
Large Language Models (LLMs) have demonstrated strong capabilities in natural language understanding and reasoning, while recent extensions that incorporate visual inputs enable them to process multimodal information. Despite these…
Large language models (LLMs) demonstrate strong performance as text embedding models when finetuned with supervised contrastive training. However, their large size balloons inference time and memory requirements. In this paper, we show that…
Traffic flow forecasting aims to predict future traffic flows based on the historical traffic conditions and the road network. It is an important problem in intelligent transportation systems, with a plethora of methods been proposed.…
Deep learning-based image enhancement methods face a fundamental trade-off between computational efficiency and representational capacity. For example, although a conventional three-dimensional Look-Up Table (3D LUT) can process a degraded…
Modern diffusion/flow-based models for image generation typically exhibit two core characteristics: (i) using multi-step sampling, and (ii) operating in a latent space. Recent advances have made encouraging progress on each aspect…
Transition Matching (TM) is an emerging paradigm for generative modeling that generalizes diffusion and flow-matching models as well as continuous-state autoregressive models. TM, similar to previous paradigms, gradually transforms noise…
How is knowledge stored in an LLM's weights? We study this via layer pruning: if removing a certain layer does not affect model performance in common question-answering benchmarks, then the weights in that layer are not necessary for…
Resource limitations often constrain the parameter counts of Large Language Models (LLMs), hindering their performance. While existing methods employ parameter sharing to reuse the same parameter set under fixed budgets, such approaches…
Recent diffusion and flow matching models have demonstrated strong capabilities in image generation and editing by progressively removing noise through iterative sampling. While this enables flexible inversion for semantic-preserving edits,…
Large language models (LLMs) excel across many tasks, yet inference is still dominated by strictly token-by-token autoregression. Existing acceleration methods largely patch this pipeline and miss core human-reading ingredients:…
Large-scale Dynamic Networks (LDNs) are becoming increasingly important in the Internet age, yet the dynamic nature of these networks captures the evolution of the network structure and how edge weights change over time, posing unique…
Pre-trained Transformer models like T5 and BART have advanced the state of the art on a wide range of text generation tasks. Compressing these models into smaller ones has become critically important for practical use. Common neural network…
Speech generation models based on large language models (LLMs) typically operate on discrete acoustic codes, which differ fundamentally from text tokens due to their multicodebook structure. At each timestep, models must predict N codebook…