Search Results for author:
Found 42 papers, 10 papers with code
Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues
Existing methods target instructions from real instruction dialogues as a learning goal and fine-tune a user simulator for posing instructions.
UNIAA: A Unified Multi-modal Image Aesthetic Assessment Baseline and Benchmark
To further evaluate the IAA capability of MLLMs, we construct the UNIAA-Bench, which consists of three aesthetic levels: Perception, Description, and Assessment.
End-to-end training of Multimodal Model and ranking Model
In this paper, we propose an industrial multimodal recommendation framework named EM3: End-to-end training of Multimodal Model and ranking Model, which sufficiently utilizes multimodal information and allows personalized ranking tasks to directly train the core modules in the multimodal model to obtain more task-oriented content features, without overburdening resource consumption.
Motion Inversion for Video Customization
In this research, we present a novel approach to motion customization in video generation, addressing the widespread gap in the thorough exploration of motion representation within video generative models.
DouRN: Improving DouZero by Residual Neural Networks
Deep reinforcement learning has made significant progress in games with imperfect information, but its performance in the card game Doudizhu (Chinese Poker/Fight the Landlord) remains unsatisfactory.
DragAnything: Motion Control for Anything using Entity Representation
We introduce DragAnything, which utilizes a entity representation to achieve motion control for any object in controllable video generation.
A Survey on Applications of Reinforcement Learning in Spatial Resource Allocation
Given these advancements, there has been a surge in novel methods employing reinforcement learning to tackle spatial resource allocation problems.
ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors
The safety of Large Language Models (LLMs) has gained increasing attention in recent years, but there still lacks a comprehensive approach for detecting safety issues within LLMs' responses in an aligned, customizable and explainable manner.
Enhancing Role-playing Systems through Aggressive Queries: Evaluation and Improvement
Experiments on models improved by RoleAD indicate that our adversarial dataset ameliorates this deficiency, with the improvements demonstrating a degree of generalizability in ordinary scenarios.
ChemLLM: A Chemical Large Language Model
ChemLLM beats GPT-3. 5 on all three principal tasks in chemistry, i. e., name conversion, molecular caption, and reaction prediction, and surpasses GPT-4 on two of them.
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
In light of recent advances in multimodal Large Language Models (LLMs), there is increasing attention to scaling them from image-text data to more informative real-world videos.
Ranked #59 on
Visual Question Answering
on MM-Vet
Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion
In practice, users often desire the ability to control object motion and camera movement independently for customized video creation.
Rethinking Cross-Attention for Infrared and Visible Image Fusion
The DIIM is designed by modifying the vanilla cross-attention mechanism, which can promote the extraction of the discrepancy information of the source images.
Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint
To address it, we propose a new RL method named \textbf{RLMEC} that incorporates a generative model as the reward model, which is trained by the erroneous solution rewriting task under the minimum editing constraint, and can produce token-level rewards for RL training.
I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models
I2V-Adapter adeptly propagates the unnoised input image to subsequent noised frames through a cross-frame attention mechanism, maintaining the identity of the input image without any changes to the pretrained T2V model.
Paragraph-to-Image Generation with Information-Enriched Diffusion Model
In this paper, we introduce an information-enriched diffusion model for paragraph-to-image generation task, termed ParaDiffusion, which delves into the transference of the extensive semantic comprehension capabilities of large language models to the task of image generation.
Ask One More Time: Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarios
Although chain-of-thought (CoT) prompting combined with language models has achieved encouraging results on complex reasoning tasks, the naive greedy decoding used in CoT prompting usually causes the repetitiveness and local optimality.
DialogBench: Evaluating LLMs as Human-like Dialogue Systems
In this paper, we propose DialogBench, a dialogue evaluation benchmark that contains 12 dialogue tasks to probe the capabilities of LLMs as human-like dialogue systems should have.
USDC: Unified Static and Dynamic Compression for Visual Transformer
To alleviate two disadvantages of two categories of methods, we propose to unify the static compression and dynamic compression techniques jointly to obtain an input-adaptive compressed model, which can further better balance the total compression ratios and the model performances.
ASP: Automatic Selection of Proxy dataset for efficient AutoML
Deep neural networks have gained great success due to the increasing amounts of data, and diverse effective neural network designs.
Parrot: Enhancing Multi-Turn Chat Models by Learning to Ask Questions
In this paper, we address these challenges by introducing Parrot, a highly scalable solution designed to automatically generate high-quality instruction-tuning data, which are then used to enhance the effectiveness of chat models in multi-turn conversations.
KwaiYiiMath: Technical Report
Recent advancements in large language models (LLMs) have demonstrated remarkable abilities in handling a variety of natural language processing (NLP) downstream tasks, even on mathematical tasks requiring multi-step reasoning.
Ranked #87 on
Arithmetic Reasoning
on GSM8K
(using extra training data)
Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
Specifically, we introduce a well-designed visual tokenizer to translate the non-linguistic image into a sequence of discrete tokens like a foreign language that LLM can read.
Resource Constrained Model Compression via Minimax Optimization for Spiking Neural Networks
We propose an improved end-to-end Minimax optimization method for this sparse learning problem to better balance the model performance and the computation efficiency.
Safe Reinforcement Learning with Dead-Ends Avoidance and Recovery
In this paper, we propose a method to construct a boundary that discriminates safe and unsafe states.
Cyclic Delay-Doppler Shift: A Simple Transmit Diversity Technique for Delay-Doppler Waveforms in Doubly Selective Channels
Delay-Doppler waveform design has been considered as a promising solution to achieve reliable communication under high-mobility channels for the space-air-ground-integrated networks (SAGIN).
ClusterLog: Clustering Logs for Effective Log-based Anomaly Detection
With the increasing prevalence of scalable file systems in the context of High Performance Computing (HPC), the importance of accurate anomaly detection on runtime logs is increasing.
Optimal Settings for Cryptocurrency Trading Pairs
2) It satisfies the connectivity constraint, that is, all currencies are guaranteed to be tradable.
Modeling Randomly Walking Volatility with Chained Gamma Distributions
2) If the variational inference(VI) is used for state estimation, it runs much faster than Monte Carlo(MC) methods since the calculation of the posterior uses only basic arithmetic operations.
PICASSO: Unleashing the Potential of GPU-centric Training for Wide-and-deep Recommender Systems
However, we observe that GPU devices in training recommender systems are underutilized, and they cannot attain an expected throughput improvement as what it has achieved in CV and NLP areas.
AMCAD: Adaptive Mixed-Curvature Representation based Advertisement Retrieval System
Moreover, to deploy AMCAD in Taobao, one of the largest ecommerce platforms with hundreds of million users, we design an efficient two-layer online retrieval framework for the task of graph based advertisement retrieval.
Juvenile state hypothesis: What we can learn from lottery ticket hypothesis researches?
The original lottery ticket hypothesis performs pruning and weight resetting after training convergence, exposing it to the problem of forgotten learning knowledge and potential high cost of training.
M6-T: Exploring Sparse Expert Models and Beyond
Mixture-of-Experts (MoE) models can achieve promising results with outrageous large amount of parameters but constant computation cost, and thus it has become a trend in model scaling.
Graph Intention Network for Click-through Rate Prediction in Sponsored Search
Moreover, it is difficult for user to jump out of their specific historical behaviors for possible interest exploration, namely weak generalization problem.
SCMA Codebook Design Based on Uniquely Decomposable Constellation Groups
Thus, BER performance of the proposed codebook design approach outperforms that of the existing codebook design schemes in both uncoded and coded SCMA systems, especially for large-size codebooks.
Tunable ferroelectricity in hBN intercalated twisted double-layer graphene
Van der Waals (vdW) assembly of two-dimensional materials has been long recognized as a powerful tool to create unique systems with properties that cannot be found in natural compounds.
Mesoscale and Nanoscale Physics Materials Science
Singlino-dominated dark matter in $Z_3$-NMSSM
Approximate analytical formulas describing the dark matter abundance and cross section in the scattering with nucleons are used to illustrate a dependence on theoretical parameters in neutralino and Higgs sectors.
High Energy Physics - Phenomenology
Radiative Decays of Charged Leptons in the Seesaw Effective Field Theory with One-loop Matching
For the first time, the Wilson coefficients of all the relevant six-dimensional operators are computed by carrying out the one-loop matching between the effective theory and full seesaw model, and applied to calculate the total rates of radiative decays of charged leptons.
High Energy Physics - Phenomenology High Energy Physics - Experiment
RLScheduler: An Automated HPC Batch Job Scheduler Using Reinforcement Learning
Today high-performance computing (HPC) platforms are still dominated by batch jobs.
A bi-diffusion based layer-wise sampling method for deep learning in large graphs
The Graph Convolutional Network (GCN) and its variants are powerful models for graph representation learning and have recently achieved great success on many graph-based applications.
Projecting "better than randomly": How to reduce the dimensionality of very large datasets in a way that outperforms random projections
However, the recent development of randomized principal component analysis (RPCA) has opened up the possibility of obtaining approximate principal components on very large datasets.
Gear Training: A new way to implement high-performance model-parallel training
The training of Deep Neural Networks usually needs tremendous computing resources.
