[NeurIPS 2025] Official Implementation of paper "Sherlock: Self-Correcting Reasoning in Vision-Language Models"

[ICLR 2026 Oral] Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMs

A curated list of papers on time series foundation models, LLM4TS and agentic time series systems.

[CVPR 2026] [Best Paper Finalist] [Oral] Official repository of Vision Test-Time Training

Atari-style POMDPs

Towards Holistic evaluation of Generative Diffusion Transformers!

Official implementation of "Recursive Flow Matching"

Strong Stochastic Flow Maps.

[CVPR2026] LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

Patched Attention for Nonlinear Dynamics [ICLR 2026]

This is the official implementation of our NeurIPS 2025 paper "Gated Integration of Low-Rank Adaptation for Continual Learning of Large Language Models".

Code, data and weights for the paper **What drives success in physical planning with Joint-Embedding Predictive World Models?**

Incremental BPE tokenization for all prefixes

(ICML'26 spotlight): Steer Like the LLM: Activation Steering that Mimics Prompting

Official implementation of: "Dream-MPC: Gradient-Based Model Predictive Control with Latent Imagination" by Spieler & Behnke. ICML 2026

Chronos: Pretrained Models for Time Series Forecasting

[CVPR 2026 Oral] VGGT Omega

Official code for ICLR 2026 Oral: Plug-and-Play Compositionality for Boosting Continual Learning with Foundation Models

The offical repo for "LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling"

[ICLR 2026] Official code for TraceRL: Revolutionizing post-training for Diffusion LLMs, powering the SOTA TraDo series.

[CVPR 2026 Highlight, the CVPR Compute Gold Star] Offical code for "FastGS: Training 3D Gaussian Splatting in 100 Seconds"

Official Repo of "D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models"

Source code for paper Reviving Error Correction in Modern Deep Time-Series Forecasting

repository for training action-conditioned latent diffusion world models for robot video generation

RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios