GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning
Paper
•
2311.12631
•
Published
•
15
Video
-
-
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
Paper • 2401.06066 • Published • 56 -
VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step
Paper • 2504.01956 • Published • 40 -
UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understanding
Paper • 2506.23219 • Published • 7 -
CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization
Paper • 2507.06181 • Published • 43 -
Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky
Paper • 2507.03336 • Published • 5 -
GTA1: GUI Test-time Scaling Agent
Paper • 2507.05791 • Published • 26 -
LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS
Paper • 2507.07136 • Published • 37 -
Lumos-1: On Autoregressive Video Generation from a Unified Model Perspective
Paper • 2507.08801 • Published • 30 -
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
Paper • 2507.10524 • Published • 70 -
SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?
Paper • 2507.12415 • Published • 42 -
OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique
Paper • 2507.09075 • Published • 15 -
REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once
Paper • 2507.10541 • Published • 29 -
Lizard: An Efficient Linearization Framework for Large Language Models
Paper • 2507.09025 • Published • 18 -
AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs
Paper • 2507.08616 • Published • 13 -
EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes
Paper • 2507.11407 • Published • 57 -
The Imitation Game: Turing Machine Imitator is Length Generalizable Reasoner
Paper • 2507.13332 • Published • 48 -
RiemannLoRA: A Unified Riemannian Framework for Ambiguity-Free LoRA Optimization
Paper • 2507.12142 • Published • 36 -
FLEXITOKENS: Flexible Tokenization for Evolving Language Models
Paper • 2507.12720 • Published • 9 -
Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities
Paper • 2507.13158 • Published • 24 -
Upsample What Matters: Region-Adaptive Latent Sampling for Accelerated Diffusion Transformers
Paper • 2507.08422 • Published • 36 -
WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization
Paper • 2507.15061 • Published • 59 -
Robust 3D-Masked Part-level Editing in 3D Gaussian Splatting with Regularized Score Distillation Sampling
Paper • 2507.11061 • Published • 37 -
Gaussian Splatting with Discretized SDF for Relightable Assets
Paper • 2507.15629 • Published • 23 -
Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning
Paper • 2507.16784 • Published • 120 -
Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention
Paper • 2507.17745 • Published • 33 -
Deep Researcher with Test-Time Diffusion
Paper • 2507.16075 • Published • 64 -
ScreenCoder: Advancing Visual-to-Code Generation for Front-End Automation via Modular Multimodal Agents
Paper • 2507.22827 • Published • 98 -
On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective
Paper • 2507.23632 • Published • 6 -
Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models
Paper • 2508.00819 • Published • 62 -
Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training
Paper • 2508.00414 • Published • 91 -
Qwen-Image Technical Report
Paper • 2508.02324 • Published • 257 -
CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward
Paper • 2508.03686 • Published • 36 -
Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
Paper • 2508.01191 • Published • 236 -
Efficient Agents: Building Effective Agents While Reducing Cost
Paper • 2508.02694 • Published • 85 -
Agent Lightning: Train ANY AI Agents with Reinforcement Learning
Paper • 2508.03680 • Published • 70 -
CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search
Paper • 2508.02091 • Published • 13 -
Reinforcement Pre-Training
Paper • 2506.08007 • Published • 262 -
InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization
Paper • 2508.05731 • Published • 25 -
Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization
Paper • 2508.07629 • Published • 41 -
Adapting Vision-Language Models Without Labels: A Comprehensive Survey
Paper • 2508.05547 • Published • 11 -
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
Paper • 2508.06471 • Published • 186 -
BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent
Paper • 2508.06600 • Published • 39 -
Reinforcement Learning in Vision: A Survey
Paper • 2508.08189 • Published • 28 -
Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning
Paper • 2508.08221 • Published • 47 -
Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
Paper • 2508.09736 • Published • 56 -
SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens
Paper • 2508.05305 • Published • 46 -
Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models
Paper • 2508.09968 • Published • 15 -
A Survey on Diffusion Language Models
Paper • 2508.10875 • Published • 34 -
Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs
Paper • 2508.14896 • Published • 22 -
XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization
Paper • 2508.10395 • Published • 42 -
NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
Paper • 2508.14444 • Published • 36 -
Deep Think with Confidence
Paper • 2508.15260 • Published • 87 -
Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization
Paper • 2508.14811 • Published • 40 -
UQ: Assessing Language Models on Unsolved Questions
Paper • 2508.17580 • Published • 15 -
T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation
Paper • 2508.17472 • Published • 26 -
ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models
Paper • 2508.18773 • Published • 15 -
Autoregressive Universal Video Segmentation Model
Paper • 2508.19242 • Published • 28 -
Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies
Paper • 2508.20072 • Published • 30 -
Self-Rewarding Vision-Language Model via Reasoning Decomposition
Paper • 2508.19652 • Published • 84 -
SpotEdit: Evaluating Visually-Guided Image Editing Methods
Paper • 2508.18159 • Published • 3 -
ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks
Paper • 2508.15804 • Published • 15 -
Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Paper • 2508.20751 • Published • 89 -
TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling
Paper • 2508.17445 • Published • 80 -
Mixture of Contexts for Long Video Generation
Paper • 2508.21058 • Published • 34 -
VibeVoice Technical Report
Paper • 2508.19205 • Published • 123 -
CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning
Paper • 2508.20096 • Published • 36 -
InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles
Paper • 2508.16072 • Published • 4 -
EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control
Paper • 2508.21112 • Published • 75 -
UItron: Foundational GUI Agent with Advanced Perception and Planning
Paper • 2508.21767 • Published • 12 -
Efficient Code Embeddings from Code Generation Models
Paper • 2508.21290 • Published • 18 -
TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training
Paper • 2508.17677 • Published • 14 -
CLIPSym: Delving into Symmetry Detection with CLIP
Paper • 2508.14197 • Published • 8 -
UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning
Paper • 2509.02544 • Published • 121 -
Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation
Paper • 2509.00428 • Published • 17 -
Symbolic Graphics Programming with Large Language Models
Paper • 2509.05208 • Published • 45 -
LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence
Paper • 2509.12203 • Published • 19 -
Locality in Image Diffusion Models Emerges from Data Statistics
Paper • 2509.09672 • Published • 12 -
LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios
Paper • 2509.09926 • Published • 13 -
Single-stream Policy Optimization
Paper • 2509.13232 • Published • 33 -
InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis
Paper • 2509.10441 • Published • 30 -
WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents
Paper • 2509.13309 • Published • 66 -
Towards General Agentic Intelligence via Environment Scaling
Paper • 2509.13311 • Published • 69 -
Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation
Paper • 2509.10687 • Published • 6 -
RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation
Paper • 2509.15212 • Published • 21 -
AToken: A Unified Tokenizer for Vision
Paper • 2509.14476 • Published • 36 -
Qwen3-Omni Technical Report
Paper • 2509.17765 • Published • 131 -
MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources
Paper • 2509.21268 • Published • 100 -
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
Paper • 2509.22186 • Published • 121 -
Fine-tuning Done Right in Model Editing
Paper • 2509.22072 • Published • 27 -
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search
Paper • 2509.25454 • Published • 133 -
Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning
Paper • 2509.22601 • Published • 29 -
Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
Paper • 2509.26628 • Published • 13 -
More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models
Paper • 2509.25848 • Published • 77 -
Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
Paper • 2509.25849 • Published • 46 -
VoiceAssistant-Eval: Benchmarking AI Assistants across Listening, Speaking, and Viewing
Paper • 2509.22651 • Published • 22 -
LucidFlux: Caption-Free Universal Image Restoration via a Large-Scale Diffusion Transformer
Paper • 2509.22414 • Published • 21 -
LongCodeZip: Compress Long Context for Code Language Models
Paper • 2510.00446 • Published • 106 -
No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping
Paper • 2509.21880 • Published • 44 -
Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models
Paper • 2510.05034 • Published • 45 -
Reactive Transformer (RxT) -- Stateful Real-Time Processing for Event-Driven Reactive Language Models
Paper • 2510.03561 • Published • 23 -
Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image Pairs
Paper • 2509.25771 • Published • 10 -
Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention
Paper • 2510.04212 • Published • 22 -
Efficient Intent Detection with Dual Sentence Encoders
Paper • 2003.04807 • Published • 2 -
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
Paper • 2510.11696 • Published • 164 -
Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs
Paper • 2510.09201 • Published • 46 -
ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning
Paper • 2510.12693 • Published • 25