ICLR2026

ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference
Post-training quantization (PTQ) compresses the weights and activations of large language models (LLMs) into low-precision …
PDF Cite Project
OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM
Advancing machine intelligence requires developing the ability to perceive across multiple modalities, much as humans sense the world. …
PDF Cite Code Project Video
OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM
LongLive: Real-time Interactive Long Video Generation
We present LongLive, a frame-level autoregressive (AR) framework for real-time and interactive long video generation. Long video …
PDF Cite Code Project Video
LongLive: Real-time Interactive Long Video Generation
QeRL: Beyond Efficiency - Quantization-enhanced Reinforcement Learning for LLMs
We propose QeRL, a Quantization-enhanced Reinforcement Learning framework for large language models (LLMs). While RL is essential for …
PDF Cite Code
QeRL: Beyond Efficiency - Quantization-enhanced Reinforcement Learning for LLMs
StreamingVLM: Real-Time Understanding for Infinite Video Streams
Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding …
PDF Cite Code Project Slides Demo
Fast-dLLM v2: Efficient Block-Diffusion LLM
Autoregressive (AR) large language models (LLMs) have achieved remarkable performance across a wide range of natural language tasks, …
PDF Cite Code
SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720×1280 resolution and minute-length …
PDF Cite Code Project Demo
SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
3D Aware Region Prompted Vision Language Model
We present Spatial Region 3D (SR-3D) aware vision-language model that connects single-view 2D images and multi-view 3D data through a …
PDF Cite Code Dataset Project
3D Aware Region Prompted Vision Language Model
Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation
We present Locality-aware Parallel Decoding (LPD) to accelerate autoregressive image generation. Traditional autoregressive image …
PDF Cite Code
Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation. However, the …
PDF Cite Code Project Demo