Related papers: APAO: Adaptive Prefix-Aware Optimization for Gener…
Sequential dependencies present a fundamental bottleneck in deploying large-scale autoregressive models, particularly for real-time applications. While traditional optimization approaches like pruning and quantization often compromise model…
We address the problem of temporal sentence localization in videos (TSLV). Traditional methods follow a top-down framework which localizes the target segment with pre-defined segment proposals. Although they have achieved decent…
Developing a single foundation model with the capability to excel across diverse tasks has been a long-standing objective in the field of artificial intelligence. As the wave of general-purpose foundation models sweeps across various…
As neural networks are increasingly deployed in dynamic environments, they face the challenge of catastrophic forgetting, the tendency to overwrite previously learned knowledge when adapting to new tasks, resulting in severe performance…
Foundation models have impressive performance and generalization capabilities across a wide range of applications. The increasing size of the models introduces great challenges for the training. Tensor parallelism is a critical technique…
Filtered ANN search is an increasingly important problem in vector retrieval, yet systems face a difficult trade-off due to the execution order: Pre-filtering (filtering first, then ANN over the passing subset) requires expensive…
Optimizing reranking in advertising feeds is a constrained combinatorial problem, requiring simultaneous maximization of platform revenue and preservation of user experience. Recent generative ranking methods enable listwise optimization…
Modern causal language models, followed by rapid developments in discrete diffusion models, can now produce a wide variety of interesting and useful content. However, these families of models are predominantly trained to output tokens with…
Class-incremental learning is a challenging problem, where the goal is to train a model that can classify data from an increasing number of classes over time. With the advancement of vision-language pre-trained models such as CLIP, they…
Optimizing Retrieval-Augmented Generation (RAG) configurations for specific tasks is a complex and resource-intensive challenge. Motivated by this challenge, frameworks for RAG hyper-parameter optimization (HPO) have recently emerged, yet…
Large language models (LLMs) have achieved great success across diverse tasks, and fine-tuning is sometimes needed to further enhance generation quality. Most existing methods rely on human supervision or parameter retraining, both of which…
Optimal designs are usually model-dependent and likely to be sub-optimal if the postulated model is not correctly specified. In practice, it is common that a researcher has a list of candidate models at hand and a design has to be found…
Foundation models contain a wealth of information from their vast number of training samples. However, most prior arts fail to extract this information in a precise and efficient way for small sample sizes. In this work, we propose a…
Text-to-Image (T2I) generation has achieved remarkable progress in recent years. Meanwhile, reinforcement learning methods, particularly those based on Group Relative Policy Optimization (GRPO), have attracted widespread attention and been…
Recently, generative retrieval-based recommendation systems have emerged as a promising paradigm. However, most modern recommender systems adopt a retrieve-and-rank strategy, where the generative model functions only as a selector during…
Generative recommendation has emerged as a promising paradigm that formulates the recommendations into a text-to-text generation task, harnessing the vast knowledge of large language models. However, existing studies focus on considering…
Photonic reservoir computing is an emergent technology toward beyond-Neumann computing. Although photonic reservoir computing provides superior performance in environments whose characteristics are coincident with the training datasets for…
Large reasoning models (LRMs) exhibit diverse high-level reasoning patterns (e.g., direct solution, reflection-and-verification, and exploring multiple solutions), yet prevailing training recipes implicitly bias models toward a limited set…
Recent years have seen a rapid surge in research leveraging Large Language Models (LLMs) for recommendation. These methods typically employ supervised fine-tuning (SFT) to adapt LLMs to recommendation scenarios, and utilize beam search…
Given an input sequence (or prefix), modern language models often assign high probabilities to output sequences that are repetitive, incoherent, or irrelevant to the prefix; as such, model-generated text also contains such artifacts. To…