[NeurIPS'25] FreqExit: Enabling Early-Exit Inference for Visual Autoregressive Models via Frequency-Aware Guidance
☆21Dec 15, 2025Updated 10 months ago
Alternatives and similar repositories for FreqExit
Users that are interested in FreqExit are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Implementation of RankE: End-to-End Discrete Text-to-Image Post-Training via Rank-Consistent Alignment☆21May 27, 2026Updated 5 months ago
- [CPAL 2026 oral] Offical implementation of "ROSE: Reordered SparseGPT for More Accurate One-Shot Large Language Models Pruning”☆18Jul 31, 2026Updated 2 months ago
- Survey and resources on large-small model collaboration for domain-specific AI.☆23Jul 3, 2026Updated 3 months ago
- Webpage: https://chuny9743.github.io/AI4WaterEnv_Webpage/☆36Aug 22, 2026Updated 2 months ago
- [ICML 2026] PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks☆25May 13, 2026Updated 5 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆43Jun 8, 2026Updated 4 months ago
- [CVPR 2026] EarlyTom: Early Token Compression Completes Fast Video Understanding☆39Jun 22, 2026Updated 4 months ago
- [ICLR 2026] MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding☆22Feb 27, 2026Updated 8 months ago
- [TMLR 2026] Is Oracle Pruning the True Oracle?☆35Jul 1, 2026Updated 3 months ago
- LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs☆42Oct 3, 2026Updated 3 weeks ago
- [ICLR 2026] Offical implementation of "OBS-Diff".☆67Mar 5, 2026Updated 7 months ago
- [arXiv 2026] dVoting: Fast Voting for dLLMs☆31Feb 13, 2026Updated 8 months ago
- [ECCV 2026 Tutorial] Efficient MLLM Inference via Approximated and Exact Computing☆21Sep 23, 2026Updated last month
- [arxiv 2025] SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-Shot☆22Oct 8, 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.
- [NeurIPS 2026] dMoE: dLLMs with Learnable Block Experts☆49Sep 29, 2026Updated last month
- Collection of recent works on AI Agents.☆17Jun 5, 2025Updated last year
- ☆16Jul 3, 2026Updated 3 months ago
- VidKV: Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models☆25Mar 26, 2025Updated last year
- [NeurIPS 2025] Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs☆37Sep 21, 2025Updated last year
- [CVPR 2026] OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models☆109Apr 20, 2026Updated 6 months ago
- DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels☆13Jun 8, 2026Updated 4 months ago
- ☆34Mar 5, 2026Updated 7 months ago
- [ICLR 2026] RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning☆48Sep 29, 2026Updated last month
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- OmniAgent: Audio-Guided Active Perception Agent for Omnimodal Audio-Video Understanding☆27Apr 9, 2026Updated 6 months ago
- [ICLR 2026] Autoregressive Image Generation with Randomized Parallel Decoding☆94Feb 16, 2026Updated 8 months ago
- [TMLR 2026] Survey: https://arxiv.org/pdf/2507.20198☆404Jul 27, 2026Updated 3 months ago
- [CVPR 2026] ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Maps☆88Sep 29, 2026Updated last month
- [NeurIPS 2025] HoliTom: Holistic Token Merging for Fast Video Large Language Models☆86Oct 10, 2025Updated last year
- Official implementation of Prism-MoE, an efficient dense-to-MoE conversion framework for visual autoregressive generation. ICML 2026 Post…☆31Jul 3, 2026Updated 3 months ago
- [ICLR 2025] Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching☆19Apr 21, 2025Updated last year
- [ICLR 2025 Spotlight] Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model☆16Apr 23, 2025Updated last year
- Training with Block Minifloat number representation☆18May 2, 2021Updated 5 years 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.
- ☆25Jun 12, 2026Updated 4 months ago
- [ACL 2025] Cautious Next Token Prediction☆16Jul 24, 2025Updated last year
- [TMLR 2025] Efficient Reasoning Models: A Survey☆324Oct 20, 2026Updated last week
- A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.☆90Oct 26, 2025Updated last year
- ☆28Jul 2, 2026Updated 3 months ago
- [CVPR 2025] DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models☆118Nov 22, 2025Updated 11 months ago
- Official implementation of ARC-Decode, a training-free speculative decoding framework with risk-bounded acceptance. ICML 2026 Poster.☆24Jul 3, 2026Updated 3 months ago