Search Results for author:
Found 20 papers, 13 papers with code
Generating Descriptive and Rules-Adhering Spells for Dungeons & Dragons Fifth Edition
We examine the task of generating unique content for the spell system of the tabletop roleplaying game Dungeons and Dragons Fifth Edition using several generative language models.
Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing
In this work, we propose KVTP (Keyframe-oriented Vision Token Pruning), a novel framework that overcomes the drawbacks of token pruning and keyframe selection.
SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval
We introduce Speech Information Retrieval (SIR), a new long-context task for Speech Large Language Models (Speech LLMs), and present SPIRAL, a 1, 012-sample benchmark testing models' ability to extract critical details from approximately 90-second spoken inputs.
Towards Automated Model Design on Recommender Systems
Designing recommender systems using deep neural networks requires careful architecture design, and further optimization demands extensive co-design efforts on jointly optimizing model architecture and hardware.
Aria: An Open Multimodal Native Mixture-of-Experts Model
Information comes in diverse modalities.
Ranked #5 on
Video Question Answering
on TVBench
Implicit Filtering for Learning Neural Signed Distance Functions from 3D Point Clouds
The neural network typically fits the shape with a rough surface and omits fine-grained geometric details such as shape edges and corners.
Practical offloading for fine-tuning LLM on commodity GPU via learned sparse projectors
However, this approach is hampered by the limited bandwidth of commodity hardware, which constrains communication between the CPU and GPU, and by slower matrix multiplications on the CPU.
Yi: Open Foundation Models by 01.AI
The Yi model family is based on 6B and 34B pretrained language models, then we extend them to chat models, 200K long context models, depth-upscaled models, and vision-language models.
Ranked #1 on
Chatbot
on AlpacaEval
CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark
We introduce CMMMU, a new Chinese Massive Multi-discipline Multimodal Understanding benchmark designed to evaluate LMMs on tasks demanding college-level subject knowledge and deliberate reasoning in a Chinese context.
Why does Prediction Accuracy Decrease over Time? Uncertain Positive Learning for Cloud Failure Prediction
Using two real-world datasets of disk failure prediction and conducting node prediction experiments in Microsoft Azure, which is a top-tier cloud provider that serves millions of users, we demonstrate Uptake can significantly improve the failure prediction accuracy by 5% on average.
GridFormer: Point-Grid Transformer for Surface Reconstruction
Our method maximizes the spatial expressiveness of grid features and maintains computational efficiency.
MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response
Large Language Models (LLMs) have shown immense potential in multimodal applications, yet the convergence of textual and musical domains remains not well-explored.
Diffusion-based Time Series Data Imputation for Microsoft 365
However, they suffer from poor data quality like data missing in model training and prediction, which limits the performance.
ImDiffusion: Imputed Diffusion Models for Multivariate Time Series Anomaly Detection
To the best of our knowledge, ImDiffusion represents a pioneering approach that combines imputation-based techniques with time series anomaly detection, while introducing the novel use of diffusion models to the field.
Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications
In many machine learning systems that jointly learn from multiple modalities, a core research question is to understand the nature of multimodal interactions: how modalities combine to provide new task-relevant information that was not present in either alone.
High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning
Many real-world problems are inherently multimodal, from spoken language, gestures, and paralinguistics humans use to communicate, to force, proprioception, and visual sensors on robots.
CBNet: A Composite Backbone Network Architecture for Object Detection
With multi-scale testing, we push the current best single model result to a new record of 60. 1% box AP and 52. 3% mask AP without using extra training data.
Ranked #2 on
Instance Segmentation
on COCO test-dev
(using extra training data)
Some q-supercongruences from Rahman's summation formula
Inspired by the recent work on $q$-congruences and the quadratic summation formula of Rahman, we provide some new $q$-supercongruences.
Combinatorics 33D15, 11A07, 11B65
CBNet: A Novel Composite Backbone Network Architecture for Object Detection
In existing CNN based detectors, the backbone network is a very important component for basic feature extraction, and the performance of the detectors highly depends on it.
Ranked #49 on
Instance Segmentation
on COCO test-dev
