Search Results for author:
Found 11 papers, 8 papers with code
Kimi-VL Technical Report
We present Kimi-VL, an efficient open-source Mixture-of-Experts (MoE) vision-language model (VLM) that offers advanced multimodal reasoning, long-context understanding, and strong agent capabilities - all while activating only 2. 8B parameters in its language decoder (Kimi-VL-A3B).
Muon is Scalable for LLM Training
Recently, the Muon optimizer based on matrix orthogonalization has demonstrated strong results in training small-scale language models, but the scalability to larger models has not been proven.
MoBA: Mixture of Block Attention for Long-Context LLMs
Scaling the effective context length is essential for advancing large language models (LLMs) toward artificial general intelligence (AGI).
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Moreover, we present effective long2short methods that use long-CoT techniques to improve short-CoT models, yielding state-of-the-art short-CoT reasoning results -- e. g., 60. 8 on AIME, 94. 6 on MATH500, 47. 3 on LiveCodeBench -- outperforming existing short-CoT models such as GPT-4o and Claude Sonnet 3. 5 by a large margin (up to +550%).
SEPT: Towards Scalable and Efficient Visual Pre-Training
To address these issues, we build a task-specific self-supervised pre-training framework from a data selection perspective based on a simple hypothesis that pre-training on the unlabeled samples with similar distribution to the target task can bring substantial performance gains.
Semantically Coherent Out-of-Distribution Detection
The proposed UDG can not only enrich the semantic knowledge of the model by exploiting unlabeled data in an unsupervised manner, but also distinguish ID/OOD samples to enhance ID classification and OOD detection tasks simultaneously.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Progressive Representative Labeling for Deep Semi-Supervised Learning
In this paper, we propose to label only the most representative samples to expand the labeled set.
Webly Supervised Image Classification with Metadata: Automatic Noisy Label Correction via Visual-Semantic Graph
VSGraph-LC starts from anchor selection referring to the semantic similarity between metadata and correct label concepts, and then propagates correct labels from anchors on a visual graph using graph neural network (GNN).
Ranked #9 on
Image Classification
on WebVision-1000
Webly Supervised Image Classification with Self-Contained Confidence
Therefore, a simple yet effective WSL framework is proposed.
Ranked #7 on
Image Classification
on WebVision-1000
Toward Characteristic-Preserving Image-based Virtual Try-On Network
Second, to alleviate boundary artifacts of warped clothes and make the results more realistic, we employ a Try-On Module that learns a composition mask to integrate the warped clothes and the rendered image to ensure smoothness.
Chinese/English mixed Character Segmentation as Semantic Segmentation
We take advantage of the successful architecture called fully convolutional networks (FCN) in the field of semantic segmentation.
