[ACL 2026 Main] See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLMs
☆27Jul 4, 2026Updated last month
Alternatives and similar repositories for LVSpec
Users that are interested in LVSpec are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [EMNLP 2025 Main] SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning☆48Apr 16, 2026Updated 3 months ago
- [ACL 2026 Findings] Living repository for the survey paper “Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques…☆26Apr 8, 2026Updated 3 months ago
- Implementation for paper "Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models".☆128May 17, 2026Updated 2 months ago
- Official page of ImmerIris: A Large-Scale Dataset and Benchmark for Off-Axis and Unconstrained Iris Recognition in Immersive Applications…☆30Jun 9, 2026Updated last month
- Implementation of our paper "RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO"☆54Jul 11, 2026Updated 3 weeks ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- EchoStyle: Unlocking High-Fidelity Video Stylization with Reverse Data Synthesis☆31Jul 2, 2026Updated last month
- ☆19Feb 18, 2025Updated last year
- [AAAI 2024] MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation☆21Feb 29, 2024Updated 2 years ago
- MMSpec: Benchmarking Speculative Decoding for Vision-Language Models☆43Jul 2, 2026Updated last month
- ☆15Jan 27, 2026Updated 6 months ago
- Training Code for ADMIS Teams in CVPR2024 FRCSyn Competition☆33Jan 5, 2026Updated 6 months ago
- Official implementation of "EponaV2: Driving World Model with Comprehensive Future Reasoning"☆34May 14, 2026Updated 2 months ago
- The official code of "Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling"☆66Jun 30, 2026Updated last month
- Rookie's guide☆14Aug 10, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆37Feb 12, 2026Updated 5 months ago
- ☆32Mar 9, 2026Updated 4 months ago
- The official implementation of MotionGrasp☆38Nov 15, 2025Updated 8 months ago
- [CVPR 2026 Highlight] Official implementation of BiCo: Composing Concepts from Images and Videos via Concept-prompt Binding☆86May 31, 2026Updated 2 months ago
- [NeurIPS 2025] Official Implementation of ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding.☆67Jan 28, 2026Updated 6 months ago
- Official code for **Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity** (PruneSI…☆13Mar 25, 2026Updated 4 months ago
- ☆35Nov 18, 2025Updated 8 months ago
- Official repository for: IDDR-NGP:Incorporating Detectors for Distractors Removal with Instant Neural Radiance Field☆23Jul 8, 2024Updated 2 years ago
- An out-of-the-box inference acceleration engine for Diffusion and DiT models☆59Mar 21, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ICLR 2026] Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language Models☆29Mar 21, 2026Updated 4 months ago
- ☆17Mar 24, 2025Updated last year
- The Official Implementation of Ada-KV [NeurIPS 2025]☆139Nov 26, 2025Updated 8 months ago
- Official Repo for paper "VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference"☆15Mar 28, 2026Updated 4 months ago
- [ICML2026] OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models☆26May 21, 2026Updated 2 months ago
- TurboServe: Serving Streaming Video Generation Efficiently and Economically☆38Jul 12, 2026Updated 3 weeks ago
- [ICLR 2026] Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision☆234May 31, 2026Updated 2 months ago
- A portable and efficient infrastracture for value profilers. Doc: https://vclinic.readthedocs.io/en/latest/index.html☆14Mar 4, 2026Updated 4 months ago
- DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation☆164Jun 26, 2026Updated last month
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆35Jun 3, 2025Updated last year
- ☆11Sep 27, 2022Updated 3 years ago
- Code for the ICLR 2024 paper Federated Text-driven Prompt Generation for Vision-Language Models (https://openreview.net/forum?id=NW31gAyl…☆27May 7, 2024Updated 2 years ago
- [CVPR 2026] Accelerating Streaming Video Large Language Models via Hierarchical Token Compression☆70Jun 8, 2026Updated last month
- Experiments with representation engineering☆14Feb 28, 2024Updated 2 years ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆52May 12, 2026Updated 2 months ago
- ERGO (Efficient Reasoning & Guided Observation) is a large vision-language model trained with reinforcement learning on efficiency object…☆19Feb 25, 2026Updated 5 months ago