[ICML 2025] Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Models
☆15May 28, 2025Updated last year
Alternatives and similar repositories for SPARC
Users that are interested in SPARC are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2026] Official implementation of "Enhancing Multi-Image Understanding Through Delimiter Token Scaling"☆19Jul 10, 2026Updated 4 months ago
- Official source code for the paper "Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents"☆14Oct 3, 2026Updated last month
- [ICLR-2024] The PyTorch Implementation of InfoMax. The algorithms are based on our paper: "Data pruning by information maximization".☆14Jul 13, 2026Updated 4 months ago
- [CVPR 2025] Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding☆19Oct 4, 2025Updated last year
- ☆15Apr 9, 2026Updated 7 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Official implementation of NeurIPS 2025 paper "Visual Instruction Bottleneck Tuning"☆15Apr 10, 2026Updated 7 months ago
- The official implemention of StimuVAR: Spatiotemporal Stimuli-aware Video Affective Reasoning with Multimodal Large Language Models accep…☆10Jan 21, 2026Updated 9 months ago
- LELA entity linking system☆13Oct 23, 2026Updated 3 weeks ago
- Training-free open-vocabulary semantic segmentation using DINOv3 reference memory and retrieval-guided spatial prompting of frozen SAM 3.☆10Sep 27, 2026Updated last month
- [NeurIPS2024] Official code for (IMA) Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs☆23Oct 15, 2024Updated 2 years ago
- Official implementation of ICML 2025 paper "Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach"☆12May 27, 2025Updated last year
- [ECCV 2026] RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation☆19Jun 24, 2026Updated 4 months ago
- [NeurIPS 2024] Unsupervised Hierarchy-Agnostic Segmentation: Parsing Semantic Image Structure☆13Nov 27, 2025Updated 11 months ago
- Training and evaluation code for our paper "MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learnin…☆25Oct 29, 2026Updated 3 weeks ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- [ICLR 2026 Oral] TRACE: Your Diffusion Model Is Secretly an Instance Edge Detector☆19Mar 2, 2026Updated 8 months ago
- [ICRA 2024]This is the official repo of paper "HR-APR: APR-agnostic Framework with Uncertainty Estimation and Hierarchical Refinement for…☆11Feb 10, 2025Updated last year
- Official implementation of "Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data" (ICLR 2024)☆38Oct 16, 2024Updated 2 years ago
- Official code and dataset for our EMNLP 2024 Findings paper: Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Kn…☆19Dec 27, 2024Updated last year
- ☆18Jan 6, 2025Updated last year
- Enhancing Vision-Language Model with Unmasked Token Alignment (TMLR)☆11May 30, 2024Updated 2 years ago
- Official code of Diffusion -bridge☆13Oct 29, 2025Updated last year
- Official Pytorch implementation of "Listening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learners".☆19Oct 18, 2026Updated last month
- ☆15Nov 30, 2025Updated 11 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Synthetic Data Generation with Execution-Based Verification and Grounding for LLM Training.☆25Feb 7, 2025Updated last year
- [CVPR 2025] Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Att…☆86Oct 9, 2025Updated last year
- HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models☆17Mar 6, 2025Updated last year
- Task Singular Vectors: Reducing Task Interference in Model Merging. Merge models avoiding task interference through separable models.☆60Dec 15, 2025Updated 11 months ago
- [CVPR 2026] See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models☆13Apr 6, 2026Updated 7 months ago
- [CVPR 2025] TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models☆16May 21, 2026Updated 5 months ago
- Code and datasets for CVPR 2025 accepted paper Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment☆13Jun 11, 2025Updated last year
- Official Code for PicPersonaTOD☆20Sep 9, 2025Updated last year
- Audio Entailment: Deductive Reasoning for Audio Understanding☆17Dec 10, 2024Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Iterate on LLM-based structured generation forward and backward☆24Mar 20, 2025Updated last year
- Siamese Vision Transformers are Scalable Audio-visual Learners☆14Apr 1, 2024Updated 2 years ago
- KEEP:Official code for "KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning". A memory management system op…☆13Jul 9, 2026Updated 4 months ago
- The official code for ICLR 2024 paper: BarLeRIa: An Efficient Tuning Framework for Referring Image Segmentation☆10May 18, 2024Updated 2 years ago
- Expressive Speech Retrieval using Natural Language Descriptions of Speaking Style☆15Aug 18, 2025Updated last year
- SotA text-only image/video method (IJCAI 2023)☆14Jan 9, 2024Updated 2 years ago
- Official implementation of "DINO Adapted to X-Ray (DAX)"☆11Sep 30, 2025Updated last year
Are these results useful?