Search Results for author:
Found 23 papers, 10 papers with code
LettinGo: Explore User Profile Generation for Recommendation System
This work enhances profile generation as a key innovation for next-generation recommendation systems.
RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning
Instead of relying on handcrafted rules or stylistic rewrites, our method trains a language model to generate structured, self-reflective prompts by optimizing for image-level outcomes.
MAIN: Mutual Alignment Is Necessary for instruction tuning
Instruction tuning has enabled large language models (LLMs) to achieve remarkable performance, but its success heavily depends on the availability of large-scale, high-quality instruction-response pairs.
GeAR: Generation Augmented Retrieval
However, such scalar similarity is difficult to reflect enough information and impedes our comprehension of the retrieval results.
Context-DPO: Aligning Language Models for Context-Faithfulness
Reliable responses from large language models (LLMs) require adherence to user instructions and retrieved information.
StreamAdapter: Efficient Test Time Adaptation from Contextual Streams
The superior task adaptation and context encoding capabilities of StreamAdapter on both language understanding and generation tasks provides a new perspective for adapting LLMs at test time using context, allowing for more efficient adaptation across scenarios and more cost-effective inference
MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning
Parameter-efficient fine-tuning (PEFT) has been widely employed for domain adaptation, with LoRA being one of the most prominent methods due to its simplicity and effectiveness.
When Graph meets Multimodal: Benchmarking on Multimodal Attributed Graphs Learning
However, the absence of meaningful benchmark datasets and standardized evaluation procedures for MAG representation learning has impeded progress in this field.
Unleash LLMs Potential for Recommendation by Coordinating Twin-Tower Dynamic Semantic Token Generator
Owing to the unprecedented capability in semantic understanding and logical reasoning, the pre-trained large language models (LLMs) have shown fantastic potential in developing the next-generation recommender systems (RSs).
E5-V: Universal Embeddings with Multimodal Large Language Models
We propose a single modality training approach for E5-V, where the model is trained exclusively on text pairs.
ASI++: Towards Distributionally Balanced End-to-End Generative Retrieval
Generative retrieval, a promising new paradigm in information retrieval, employs a seq2seq model to encode document features into parameters and decode relevant document identifiers (IDs) based on search queries.
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
Low-rank adaptation is a popular parameter-efficient fine-tuning method for large language models.
ResLoRA: Identity Residual Mapping in Low-Rank Adaption
As one of the most popular parameter-efficient fine-tuning (PEFT) methods, low-rank adaptation (LoRA) is commonly applied to fine-tune large language models (LLMs).
HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition
Large language models (LLMs) have emerged as a promising alternative to expensive human evaluations.
Text Diffusion with Reinforced Conditioning
Diffusion models have demonstrated exceptional capability in generating high-quality images, videos, and audio.
Improving Domain Adaptation through Extended-Text Reading Comprehension
To enhance the domain-specific capabilities of large language models, continued pre-training on a domain-specific corpus is a prevalent method.
Democratizing Reasoning Ability: Tailored Learning from Large Language Model
In this paper, we propose a tailored learning approach to distill such reasoning ability to smaller LMs to facilitate the democratization of the exclusive reasoning ability.
Auto Search Indexer for End-to-End Document Retrieval
Generative retrieval, which is a new advanced paradigm for document retrieval, has recently attracted research interests, since it encodes all documents into the model and directly generates the retrieved documents.
Calibrating LLM-Based Evaluator
Recent advancements in large language models (LLMs) on language modeling and emergent capabilities make them a promising reference-free evaluator of natural language generation quality, and a competent alternative to human evaluation.
A Deep Model for Partial Multi-Label Image Classification with Curriculum Based Disambiguation
In this paper, we study the partial multi-label (PML) image classification problem, where each image is annotated with a candidate label set consists of multiple relevant labels and other noisy labels.
MMINR: Multi-frame-to-Multi-frame Inference with Noise Resistance for Precipitation Nowcasting with Radar
To address this problem, we propose a novel Multi-frame-to-Multi-frame Inference (MMI) model with Noise Resistance (NR) named MMINR.
Rainformer: Features Extraction Balanced Network for Radar-Based Precipitation Nowcasting
The experimental results show that Rainformer outperforms seven state of the arts methods on the benchmark database and provides more insights into the high-intensity rainfall prediction task.
Ranked #5 on
Weather Forecasting
on SEVIR
RRLFSOR: An Efficient Self-Supervised Learning Strategy of Graph Convolutional Networks
Graph Convolutional Networks (GCNs) are widely used in many applications yet still need large amounts of labelled data for training.
