Search Results for author:
Found 13 papers, 3 papers with code
SchemaAgent: A Multi-Agents Framework for Generating Relational Database Schema
In this paper, we propose SchemaAgent, a unified LLM-based multi-agent framework for the automated generation of high-quality database schema.
Video-VoT-R1: An efficient video inference model integrating image packing and AoE architecture
In the field of video-language pretraining, existing models face numerous challenges in terms of inference efficiency and multimodal data processing.
KunlunBaize: LLM with Multi-Scale Convolution and Multi-Token Prediction Under TransformerX Framework
This framework incorporates a learnable dense residual skip connection mechanism, a TransformerX module a transformer based component integrating multiscale convolution and adaptive activation functions and a multitoken prediction interaction module.
MoChat: Joints-Grouped Spatio-Temporal Grounding LLM for Multi-Turn Motion Comprehension and Description
Despite continuous advancements in deep learning for understanding human motion, existing models often struggle to accurately identify action timing and specific body parts, typically supporting only single-round interaction.
Denoising Reuse: Exploiting Inter-frame Motion Consistency for Efficient Video Latent Generation
Our key discovery is that coarse-grained noises in earlier denoising steps have demonstrated high motion consistency across consecutive video frames.
Large Language Model-Based Agents for Software Engineering: A Survey
The recent advance in Large Language Models (LLMs) has shaped a new paradigm of AI agents, i. e., LLM-based agents.
Joint Beamforming and Antenna Design for Near-Field Fluid Antenna System
In this letter, we study the energy efficiency maximization problem for a fluid antenna system (FAS) in near field communications.
Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models
To describe such modular-level learning capabilities, we introduce a novel concept dubbed modular neural tangent kernel (mNTK), and we demonstrate that the quality of a module's learning is tightly associated with its mNTK's principal eigenvalue $\lambda_{\max}$.
Balancing reaction-diffusion network for cell polarization pattern with stability and asymmetry
Once again, a generic set of kinetic parameters moves the interface towards either the anterior or posterior end, yet a polarized pattern can be stabilized through spatial tuning of one or more parameters coupled to intracellular or extracellular cues.
Adaptive Distributionally Robust Planning for Renewable-Powered Fast Charging Stations Under Decision-Dependent EV Diffusion Uncertainty
When deploying fast charging stations (FCSs) to support long-distance trips of electric vehicles (EVs), there exist indirect network effects: while the gradual diffusion of EVs directly influences the timing and capacities of FCS allocation, the decisions for FCS allocations, in turn, impact the drivers' willingness to adopt EVs.
ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation
Third, we find that generating the entire class all at once (i. e. holistic generation strategy) is the best generation strategy only for GPT-4 and GPT-3. 5, while method-by-method generation (i. e. incremental and compositional) is better strategies for the other models with limited ability of understanding long instructions and utilizing the middle information.
A new parsimonious method for classifying Cancer Tissue-of-Origin Based on DNA Methylation 450K data
The biological functions in cancer development of 50 selected genes is also explored through enrichment analysis and the results show that 12 out of 16 of our top features have already been identified to be specific with cancer and we also propose some more genes to be tested for future studies.
