Search Results for author:
Found 22 papers, 10 papers with code
FastCuRL: Curriculum Reinforcement Learning with Progressive Context Extension for Efficient Training R1-like Reasoning Models
In this paper, we propose \textbf{\textsc{FastCuRL}}, a simple yet efficient \textbf{Cu}rriculum \textbf{R}einforcement \textbf{L}earning approach with context window extending strategy to accelerate the reinforcement learning training efficiency for R1-like reasoning models while enhancing their performance in tackling complex reasoning tasks with long chain-of-thought rationales, particularly with a 1. 5B parameter language model.
GRP: Goal-Reversed Prompting for Zero-Shot Evaluation with LLMs
To address the above issue, in this paper, we propose a Goal-Reversed Prompting (GRP) approach for pairwise evaluation that shifts the original task from selecting the better answer to choosing the worse one.
Quark: Real-time, High-resolution, and General Neural View Synthesis
Our feed-forward network generalizes across a wide variety of datasets and scenes and produces state-of-the-art quality for a real-time method.
Can Many-Shot In-Context Learning Help LLMs as Evaluators? A Preliminary Empirical Study
However, this kind of evaluation approach is affected by potential biases within LLMs, raising concerns about the accuracy and reliability of the evaluation results of LLMs.
Learning 1D Causal Visual Representation with De-focus Attention Networks
The issue of "over-focus" hinders the model's ability to extract diverse visual features and to receive effective gradients for optimization.
Counting-Stars: A Multi-evidence, Position-aware, and Scalable Benchmark for Evaluating Long-Context Large Language Models
Despite recent efforts to develop large language models with robust long-context capabilities, the lack of long-context benchmarks means that relatively little is known about their performance.
Memory efficient location recommendation through proximity-aware representation
Sequential location recommendation plays a huge role in modern life, which can enhance user experience, bring more profit to businesses and assist in government administration.
Bot or Human? Detecting ChatGPT Imposters with A Single Question
Large language models (LLMs) like GPT-4 have recently demonstrated impressive capabilities in natural language understanding and generation.
STOA-VLP: Spatial-Temporal Modeling of Object and Action for Video-Language Pre-training
Although large-scale video-language pre-training models, which usually build a global alignment between the video and the text, have achieved remarkable progress on various downstream tasks, the idea of adopting fine-grained information during the pre-training stage is not well explored.
Consistent Style Transfer
Recently, attentional arbitrary style transfer methods have been proposed to achieve fine-grained results, which manipulates the point-wise similarity between content and style features for stylization.
StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation
We introduce a high resolution, 3D-consistent image and shape generation technique which we call StyleSDF.
Data Pricing in Machine Learning Pipelines
We also investigate pricing in the step of collaborative training of machine learning models, and overview pricing machine learning models for end users in the step of machine learning deployment.
Embedded Discriminative Attention Mechanism for Weakly Supervised Semantic Segmentation
In inference, we directly use the activation masks from the DA layer as pseudo-labels for segmentation.
Giant $c$-axis nonlinear anomalous Hall effect in T$_d$-MoTe$_2$ and WTe$_2$
While the anomalous Hall effect can manifest even without an external magnetic field, time reversal symmetry is nonetheless still broken by the internal magnetization of the sample.
Mesoscale and Nanoscale Physics
Roles of the Narrow Electronic Band near the Fermi Level in 1T-TaS$_2$-Related Layered Materials
In contrast, in bulk 1T-TaS$_2$, there is an interlayer CDW coupling induced insulating gap.
Mesoscale and Nanoscale Physics Materials Science
RL-CSDia: Representation Learning of Computer Science Diagrams
Another type of diagrams such as from Computer Science is composed of graphics containing complex topologies and relations, and research on this type of diagrams is still blank.
Time-Travel Rephotography
Many historical people were only ever captured by old, faded, black and white photos, that are distorted due to the limitations of early cameras and the passage of time.
Consistent Video Depth Estimation
We present an algorithm for reconstructing dense, geometrically consistent depth for all pixels in a monocular video.
KeystoneDepth: Visualizing History in 3D
This paper introduces the largest and most diverse collection of rectified stereo image pairs to the research community, KeystoneDepth, consisting of tens of thousands of stereographs of historical people, events, objects, and scenes between 1860 and 1963.
Machine Learning Techniques for Brand-Influencer Matchmaking on the Instagram Social Network
The social media revolution has changed the way that brands interact with consumers.
Fast Non-local Stereo Matching based on Hierarchical Disparity Prediction
This is partially because our DTs overcome the extreme greediness of the MST.
Purine: A bi-graph based deep learning framework
In this paper, we introduce a novel deep learning framework, termed Purine.
