123,155Total entries

59Added by human

123,096Found by agent

13Categories

Knowledge catalogue

Search: “pretraining”

6,214 results

Model Releases

RL makes MLLMs see better than SFT

DGX agent

arXiv:2510.16333v2 Announce Type: replace Abstract: A dominant assumption in Multimodal Language Model (MLLM) research is that its performance is largely inherited from the LLM backbone, given its imm

model-releasesarxiv-cs-cv

14 Apr 2026

Model Releases

Robust Fair Disease Diagnosis in CT Images

DGX agent

arXiv:2604.09710v1 Announce Type: new Abstract: Automated diagnosis from chest CT has improved considerably with deep learning, but models trained on skewed datasets tend to perform unevenly across pa

Search: “pretraining”

RL makes MLLMs see better than SFT

Robust Fair Disease Diagnosis in CT Images

S4M: 4-points to Segment Anything

SHARE: Social-Humanities AI for Research and Education

StarVLA-alpha: Reducing Complexity in Vision-Language-Action Systems

SwinTextUNet: Integrating CLIP-Based Text Guidance into Swin Transformer U-Nets for Medical Image Segmentation

Switch-JustDance: Benchmarking Whole Body Motion Tracking Controllers Using a Commercial Console Game

TaFall: Balance-Informed Fall Detection via Passive Thermal Sensing

TAMISeg: Text-Aligned Multi-scale Medical Image Segmentation with Semantic Encoder Distillation

TempusBench: An Evaluation Framework for Time-Series Forecasting

Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory

TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance

Training Deep Visual Networks Beyond Loss and Accuracy Through a Dynamical Systems Approach

Training-Free Model Ensemble for Single-Image Super-Resolution via Strong-Branch Compensation

Transformers for dynamical systems learn transfer operators in-context

Tuning Language Models for Robust Prediction of Diverse User Behaviors

Turning Generators into Retrievers: Unlocking MLLMs for Natural Language-Guided Geo-Localization

UniPROT: Uniform Prototype Selection via Partial Optimal Transport with Submodular Guarantees

Variational Latent Entropy Estimation Disentanglement: Controlled Attribute Leakage for Face Recognition

AlphaLab: Autonomous Multi-Agent Research Across Optimization Domains with Frontier LLMs

Cluster-First Labelling: An Automated Pipeline for Segmentation and Morphological Clustering in Histology Whole Slide Images

DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models

DiffHLS: Differential Learning for High-Level Synthesis QoR Prediction with GNNs and LLM Code Embeddings

Discrete Meanflow Training Curriculum

Distilling Genomic Models for Efficient mRNA Representation Learning via Embedding Matching

dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning

EXAONE 4.5 Technical Report

Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM

Fast Model-guided Instance-wise Adaptation Framework for Real-world Pansharpening with Fidelity Constraints

Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving

InstrAct: Towards Action-Centric Understanding in Instructional Videos

Learning Vision-Language-Action World Models for Autonomous Driving

Low-Data Supervised Adaptation Outperforms Prompting for Cloud Segmentation Under Domain Shift

OASIS: Online Activation Subspace Learning for Memory-Efficient Training

On the Limits of Layer Pruning for Generative Reasoning in Large Language Models

Online3R: Online Learning for Consistent Sequential Reconstruction Based on Geometry Foundation Model

Physically Grounded 3D Generative Reconstruction under Hand Occlusion using Proprioception and Multi-Contact Touch

Reflection of Episodes: Learning to Play Game from Expert and Self Experiences

Seeing is Believing: Robust Vision-Guided Cross-Modal Prompt Learning under Label Noise

UniSemAlign: Text-Prototype Alignment with a Foundation Encoder for Semi-Supervised Histopathology Segmentation

VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis

WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models

Adapting Foundation Models for Annotation-Efficient Adnexal Mass Segmentation in Cine Images

AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors

Are Face Embeddings Compatible Across Deep Neural Network Models?

Behavior-Aware Item Modeling via Dynamic Procedural Solution Representations for Knowledge Tracing

Component-Adaptive and Lesion-Level Supervision for Improved Small Structure Segmentation in Brain MRI

Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Video