MemTrain: Self-Supervised Context Memory Training
Memory is an indispensable capability for long-horizon LLM agents, enabling them to preserve and utilize information accumulated across extended interactions. Existing memory-agent...
Research Papers
Latest AI/ML research from ArXiv and Papers with Code
Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching
Wide-baseline matching (WBM) requires integrating geometric understanding, viewpoint changes, fine-grained perception, and occlusion reasoning, making it a challenging testbed for ...
Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models
Real-time vision demands models that are accurate, efficient, and simple to deploy across diverse hardware. The YOLO family has become widely deployed for this reason, yet most YOL...
SEAOTTER: Sensor Embedded Autoencoding with One-Time Transcode for Efficient Reconstruction
In robotics systems, vast amounts of visual data are easily captured at high resolution using low-cost, low-power hardware. Yet, limited bandwidth and on-device compute resources p...
EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management
Recent progress in Large Language Model (LLM) agents has enabled promising advances in automated data science. However, existing approaches remain fundamentally limited by their st...
KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks
Test-time scaling is a powerful approach to obtain better reasoning in large language models, but it becomes memory-bottlenecked during long-horizon decoding, as the KV-cache grows...
OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs
Multimodal agents in robotics, AR, and autonomous driving must reason about places and layouts from continuous egocentric streams, often using evidence outside the current view. Ex...
Bootstrap Your Generator: Unpaired Visual Editing with Flow Matching
Modern generative models possess a deep understanding of visual content, yet training them for image editing typically requires massive datasets of paired examples. This limits sca...
EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning
Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and s...
Text-to-Image Models Need Less from Text Encoders Than You Think
Text-to-image models rely on text prompts as their primary interface to human intent. Prompts are encoded by a text encoder into embeddings that condition the image generation proc...
Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO
We identify a new dimension for enhancing rollout diversity in Group Relative Policy Optimization (GRPO) for LLMs. While GRPO relies on diverse rollouts, prevailing strategies prim...
Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning
Large language models improve final-answer accuracy through extended chain-of-thought reasoning, but often spend tokens inefficiently and offer little inference-time control. Exist...
NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation
As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck. In closed-loop simulation, the driving pol...
Unlocking Feature Learning in Gated Delta Networks at Scale
Training and scaling Large Language Models demand enormous computational resources, motivating both efficient sub-quadratic architectures and principled hyperparameter tuning metho...
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
The past few decades have witnessed significant advances in the design of machine learning algorithms, from early studies on task-specific shallow models to more general deep Large...
Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking
We introduce Humanoid-GPT, a GPT-style Transformer with causal attention trained on a billion-scale motion corpus for whole-body control. Unlike prior shallow MLP trackers constrai...
Benchmarking Visual State Tracking in Multimodal Video Understanding
Understanding a video requires more than recognizing isolated moments, as humans continuously track entities, states, and events over time. This capacity for visual state tracking ...
AAD-1: Asymmetric Adversarial Distillation for One-Step Autoregressive Video Generation
We present AAD-1, an Asymmetric Adversarial Distillation framework for One-step autoregressive image-to-video generation. State-of-the-art methods adopt adversarial distillation bu...
Steady-Forcing: Balancing Spatial Persistence and Motion Continuity in Long-Horizon Nature Video Diffusion
Autoregressive video diffusion models enable streaming generation but often degrade over long rollouts: static scene layouts drift, while mechanisms that improve spatial stability ...
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
We introduce PaddleOCR-VL-1.6, an upgraded compact document parsing model built upon PaddleOCR-VL-1.5. Although PaddleOCR-VL-1.5 establishes a strong 0.9B baseline, its remaining e...
Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory
Equipping Large Language Models (LLMs) to execute reliable multi-step workflows has become a central challenge in artificial intelligence. Despite recent advances in LLMs' agentic ...
SkillHarness: Harnessing Safe Skills for Computer-Use Agents
Computer-Use Agents (CUAs) are increasingly deployed in dynamic interactive environments, creating a growing need for continual skill learning during interaction. Recent approaches...
BA-T: An Iterative Transformer for Two-View Bundle Adjustment
Feed-forward models for 3D reconstruction have achieved strong performance using deep cross-view attention to exchange information across images. However, these approaches often de...
Neural Networks Provably Learn Spectral Representations for Group Composition
Understanding how structured internal structure emerges during neural network training is central to the study of deep learning. We investigate this phenomenon through the group co...