[ICLR 2026] Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision

[ICLR 2026] The official implementation associated with the paper "3DGEER: 3D Gaussian Rendering Made Exact and Efficient for Generic Cameras"

[ICLR'26] AutoGEO: a Generative Engine Optimization framework to automatically learn generative engine preferences, and rewrite web contents for more traction.

[ICLR 2026] Code for "gen2seg: Generative Models Enable Generalizable Instance Segmentation"

[ICLR 2026] Official code of "Segment any Events with Language"

ICLR 2026-MVAR: Visual Autoregressive Modeling with Scale and Spatial Markovian Conditioning

[ICLR 2026] Meta-RL Induces Exploration in Language Agents

[ICLR 2026] Learning to Parallel: Accelerating Diffusion Large Language Models via Learnable Parallel Decoding

[ICLR 2026] This is the official PyTorch implementation of "QVGen: Pushing the Limit of Quantized Video Generative Models".

[ICLR 2026] Official implementation of the paper "Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs"

LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts (ICLR 2026 Oral)

[ICLR 2026] MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding

🦅 FALCON: an effective vision-language-action model injects rich 3D spatial tokens into the action head, enabling robust spatial understanding and SOTA performance across diverse manipulation tasks. || Accepted at ICLR 2026.

[ICLR 2026] Official implementation (Claude Agent reproduce supported) of paper "mtLoRA: Scalable Multi-Task Low-Rank Model Adaptation" +2.3% over SOTA with 47% fewer parameters

[ICLR 2026] StableToken: A state-of-the-art noise-robust semantic speech tokenizer featuring Voting-LFQ for resilient SpeechLLMs.

[ICLR 2026] RoRE: Rotary Ray Embedding for Generalised Multi-Modal Scene Understanding

The official code of "TripleSumm: Adaptive Triple-Modality Fusion for Video Summarization" (ICLR 2026)

[ICLR'26] Official code for "A-TPT: Angular Diversity Calibration Properties for Test-Time Prompt Tuning of Vision-Language Models"

[ICLR 2026] Official code of PPE: Positional Preservation Embedding for Token Compression in Multimodal Large Language Models.

Official Code for ICLR'26 Work LapFlow