Search Results for author:
Found 18 papers, 3 papers with code
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
We introduce phi-3-mini, a 3. 8 billion parameter language model trained on 3. 3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal testing, rivals that of models such as Mixtral 8x7B and GPT-3. 5 (e. g., phi-3-mini achieves 69% on MMLU and 8. 38 on MT-bench), despite being small enough to be deployed on a phone.
Ranked #5 on
MMR total
on MRR-Benchmark
(using extra training data)
i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data
The convergence of text, visual, and audio data is a key step towards human-like artificial intelligence, however the current Vision-Language-Speech landscape is dominated by encoder-only models which lack generative abilities.
Energy Efficiency Maximization in IRS-Aided Cell-Free Massive MIMO System
In this paper, we consider an intelligent reflecting surface (IRS)-aided cell-free massive multiple-input multiple-output system, where the beamforming at access points and the phase shifts at IRSs are jointly optimized to maximize energy efficiency (EE).
i-Code: An Integrative and Composable Multimodal Learning Framework
Human intelligence is multimodal; we integrate visual, linguistic, and acoustic signals to maintain a holistic worldview.
Florence: A New Foundation Model for Computer Vision
Computer vision foundation models, which are trained on diverse, large-scale dataset and can be adapted to a wide range of downstream tasks, are critical for this mission to solve real-world computer vision applications.
Ranked #1 on
Action Recognition In Videos
on Kinetics-600
Ubiquitous proximity to a critical state for collective neural activity in the CA1 region of freely moving mice
By independently altering the coupling distribution and the network structure of the statistical model, the network structures are found to be vital to maintain the proximity to the critical state.
Replication Markets: Results, Lessons, Challenges and Opportunities in AI Replication
We will discuss opportunities and challenges of using these approaches to monitor and improve the credibility of research areas in Computer Science, AI, and ML.
Forecast Aggregation via Peer Prediction
In this paper, we study the problem of aggregating forecasts without having historical performance data.
Fair Classification and Social Welfare
By showing that these constraints often fail to translate into improved outcomes for these groups, we cast doubt on their effectiveness as a means to ensure justice.
Welfare and Distributional Impacts of Fair Classification
Current methodologies in machine learning analyze the effects of various statistical parity notions of fairness primarily in light of their impacts on predictive accuracy and vendor utility loss.
Surrogate Scoring Rules
We show that, with a single bit of information about the prior distribution of the random variables, SSR in a multi-task setting recover SPSR in expectation, as if having access to the ground truth.
Learning to Compose with Professional Photographs on the Web
Photo composition is an important factor affecting the aesthetics in photography.
Quantitative Analysis of Automatic Image Cropping Algorithms: A Dataset and Comparative Study
Automatic photo cropping is an important tool for improving visual quality of digital photos without resorting to tedious manual selection.
A Bandit Framework for Strategic Regression
We propose a Strategic Regression-Upper Confidence Bound (SR-UCB) framework, an UCB-style index combined with a simple payment rule, where the index of a worker approximates the quality of his past contributions and is used by the learner to determine whether the worker receives future work.
Eliciting Categorical Data for Optimal Aggregation
Our model generalizes both categories and enables the joint exploration of optimal elicitation and aggregation.
Learning to Incentivize: Eliciting Effort via Output Agreement
In crowdsourcing when there is a lack of verification for contributed answers, output agreement mechanisms are often used to incentivize participants to provide truthful answers when the correct answer is hold by the majority.
Integrating Dashcam Views Through Inter-Video Mapping
In this paper, an inter-video mapping approach is proposed to integrate video footages from two dashcams installed on a preceding and its following vehicle to provide the illusion that the driver of the following vehicle can see-through the preceding one.
Low-Cost Learning via Active Data Procurement
Our results in a sense parallel classic sample complexity guarantees, but with the key resource being money rather than quantity of data: With a budget constraint $B$, we give robust risk (predictive error) bounds on the order of $1/\sqrt{B}$.
