Jan Kautz

ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge

RLP: Reinforcement as a Pretraining Objective

3D Aware Region Prompted Vision Language Model

Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning

DLER: Doing Length pEnalty Right — Incentivizing More Intelligence per Token via Reinforcement Learning

Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

Compact GSPN: Scaling Spatial Propagation to Vision Foundation Models

BroRL: Scaling Reinforcement Learning via Broadened Exploration

TinyEye: Sharpening Visual Reasoning of Tiny Models with Offline Policy Optimization

iGRPO: Self‑Feedback–Driven LLM Reasoning

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning

Hymba: A Hybrid-head Architecture for Small Language Models

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models

Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

Gated Delta Networks: Improving Mamba2 with Delta Rule

Scaling RL to Long Videos

GSPN-2: Efficient Parallel Sequence Modeling

Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models

LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement

LongVILA: Scaling Long-Context Visual Language Models for Long Videos

LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing

Minifinetuning: Low-Data Generation Domain Adaptation through Corrective Self-Distillation

NaVILA: Legged Robot Vision-Language-Action Model for Navigation

PHI-S: Distribution Balancing for Agglomerative Models

LLM Pruning and Distillation in Practice

ZoomVLM: A Tuning-Free Framework for Efficient Video Understanding via Adaptive Zooming in Vision-Language Models

LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models

CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation

X-VILA: Cross-Modality Alignment for Large Language Models

Wolf: Accurate Video Captioning with a World Summarization Framework

VILA^2: VLM Augmented VLM with Self-Improvement

Factorized Implicit Global Convolution for Automotive Computational Fluid Dynamics Prediction

UNAST: Unified framework for Neural Architecture Search for Transformers