Search Results for author:
Found 22 papers, 10 papers with code
Adapting Decoder-Based Language Models for Diverse Encoder Downstream Tasks
Decoder-based transformers, while revolutionizing language modeling and scaling to immense sizes, have not completely overtaken encoder-heavy architectures in natural language processing.
RRM: Robust Reward Model Training Mitigates Reward Hacking
Our RRM improves the performance of a pairwise reward model trained on Gemma-2-9b-it, on RewardBench, increasing accuracy from 80. 61% to 84. 15%.
LAMPO: Large Language Models as Preference Machines for Few-shot Ordinal Classification
We introduce LAMPO, a novel paradigm that leverages Large Language Models (LLMs) for solving few-shot multi-class ordinal classification tasks.
Principled Architecture-aware Scaling of Hyperparameters
However, most designs or optimization methods are agnostic to the choice of network structures, and thus largely ignore the impact of neural architectures on hyperparameters.
LiPO: Listwise Preference Optimization through Learning-to-Rank
In this work, we formulate the LM alignment as a \textit{listwise} ranking problem and describe the LiPO framework, where the policy can potentially learn more effectively from a ranked list of plausible responses given the prompt.
Beyond Yes and No: Improving Zero-Shot LLM Rankers via Scoring Fine-Grained Relevance Labels
We propose to incorporate fine-grained relevance labels into the prompt for LLM rankers, enabling them to better differentiate among documents with different levels of relevance to the query and thus derive a more accurate ranking.
Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting
Ranking documents using Large Language Models (LLMs) by directly feeding the query and candidate documents into the prompt is an interesting and practical problem.
Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonization
For example, even in the commonly adopted instructional videos, a speaker can sometimes refer to something that is not visually present in the current frame; and the semantic misalignment would only be more unpredictable for the raw videos from the internet.
Grasping the Arrow of Time from the Singularity: Decoding Micromotion in Low-dimensional Latent Spaces from StyleGAN
To study the motion features in the latent space of StyleGAN, in this paper, we hypothesize and demonstrate that a series of meaningful, natural, and versatile small, local movements (referred to as "micromotion", such as expression, head movement, and aging effect) can be represented in low-rank spaces extracted from the latent space of a conventionally pre-trained StyleGAN-v2 model for face generation, with the guidance of proper "anchors" in the form of either short text or video clips.
Auto-X3D: Ultra-Efficient Video Understanding via Finer-Grained Neural Architecture Search
Efficient video architecture is the key to deploying video recognition systems on devices with limited computing resources.
Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics
This work targets designing a principled and unified training-free framework for Neural Architecture Search (NAS), with high performance, low cost, and in-depth interpretation.
Stronger NAS with Weaker Predictors
We propose a paradigm shift from fitting the whole architecture space using one strong predictor, to progressively fitting a search path towards the high-performance sub-space through a set of weaker predictors.
Weak NAS Predictor Is All You Need
Rather than expecting a single strong predictor to model the whole space, we seek a progressive line of weak predictors that can connect a path to the best architecture, thus greatly simplifying the learning task of each predictor.
Uncertainty-Aware Physically-Guided Proxy Tasks for Unseen Domain Face Anti-spoofing
Face anti-spoofing (FAS) seeks to discriminate genuine faces from fake ones arising from any type of spoofing attack.
DAVID: Dual-Attentional Video Deblurring
To train and evaluate on more diverse blur severity levels, we propose a Challenging DVD dataset generated from the raw DVD video set by pooling frames with different temporal windows.
DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
We present a new end-to-end generative adversarial network (GAN) for single image motion deblurring, named DeblurGAN-v2, which considerably boosts state-of-the-art deblurring efficiency, quality, and flexibility.
Ranked #2 on
Deblurring
on BASED
Segmentation-Aware Image Denoising without Knowing True Segmentation
Several recent works discussed application-driven image restoration neural networks, which are capable of not only removing noise in images but also preserving their semantic-aware details, making them suitable for various high-level computer vision tasks as the pre-processing step.
Bridging the Gap Between Computational Photography and Visual Recognition
From the observed results, it is evident that we are in the early days of building a bridge between computational photography and visual recognition, leaving many opportunities for innovation in this area.
Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions
The current trend of pushing CNNs deeper with convolutions has created a pressing demand to achieve higher compression gains on CNNs where convolutions dominate the computation and parameter amount (e. g., GoogLeNet, ResNet and Wide ResNet).
Deep $k$-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions
The current trend of pushing CNNs deeper with convolutions has created a pressing demand to achieve higher compression gains on CNNs where convolutions dominate the computation and parameter amount (e. g., GoogLeNet, ResNet and Wide ResNet).
Gaze Prediction in Dynamic 360° Immersive Videos
This paper explores gaze prediction in dynamic $360^circ$ immersive videos, emph{i. e.}, based on the history scan path and VR contents, we predict where a viewer will look at an upcoming time.
Personalized Saliency and its Prediction
Specifically, we propose to decompose a personalized saliency map (referred to as PSM) into a universal saliency map (referred to as USM) predictable by existing saliency detection models and a new discrepancy map across users that characterizes personalized saliency.
