Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models
Paper
•
2602.12036
•
Published
•
92
Papers
-
-
Reinforcement Learning for Self-Improving Agent with Skill Library
Paper • 2512.17102 • Published • 36 -
Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation
Paper • 2512.23705 • Published • 45 -
Schoenfeld's Anatomy of Mathematical Reasoning by Language Models
Paper • 2512.19995 • Published • 16 -
Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone
Paper • 2512.22615 • Published • 49 -
TimeBill: Time-Budgeted Inference for Large Language Models
Paper • 2512.21859 • Published • 25 -
Evaluating Parameter Efficient Methods for RLVR
Paper • 2512.23165 • Published • 27 -
Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem
Paper • 2512.24873 • Published • 105 -
Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models
Paper • 2512.24618 • Published • 151 -
SpotEdit: Selective Region Editing in Diffusion Transformers
Paper • 2512.22323 • Published • 39 -
Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards
Paper • 2512.21625 • Published • 4 -
Nested Browser-Use Learning for Agentic Information Seeking
Paper • 2512.23647 • Published • 19 -
GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models
Paper • 2512.15560 • Published • 25 -
Distribution Matching Variational AutoEncoder
Paper • 2512.07778 • Published • 29 -
Self-Improving VLM Judges Without Human Annotations
Paper • 2512.05145 • Published • 20 -
OmniPSD: Layered PSD Generation with Diffusion Transformer
Paper • 2512.09247 • Published • 48 -
Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations
Paper • 2512.21004 • Published • 13 -
CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion
Paper • 2512.19535 • Published • 12 -
Multi-hop Reasoning via Early Knowledge Alignment
Paper • 2512.20144 • Published • 7 -
WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion
Paper • 2512.19678 • Published • 30 -
Step-DeepResearch Technical Report
Paper • 2512.20491 • Published • 86 -
3D-RE-GEN: 3D Reconstruction of Indoor Scenes with a Generative Framework
Paper • 2512.17459 • Published • 12 -
Beyond Memorization: A Multi-Modal Ordinal Regression Benchmark to Expose Popularity Bias in Vision-Language Models
Paper • 2512.21337 • Published • 31 -
KV-Embedding: Training-free Text Embedding via Internal KV Re-routing in Decoder-only LLMs
Paper • 2601.01046 • Published • 14 -
DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer
Paper • 2601.01425 • Published • 52 -
Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes
Paper • 2601.02356 • Published • 14 -
VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation
Paper • 2601.02256 • Published • 33 -
Recursive Language Models
Paper • 2512.24601 • Published • 89 -
NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation
Paper • 2601.02204 • Published • 62 -
K-EXAONE Technical Report
Paper • 2601.01739 • Published • 92 -
mHC: Manifold-Constrained Hyper-Connections
Paper • 2512.24880 • Published • 307 -
OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation
Paper • 2601.15369 • Published • 21 -
Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
Paper • 2601.16163 • Published • 14 -
The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models
Paper • 2601.15165 • Published • 72 -
Learning to Discover at Test Time
Paper • 2601.16175 • Published • 42 -
ActionMesh: Animated 3D Mesh Generation with Temporal 3D Diffusion
Paper • 2601.16148 • Published • 12 -
Behavior Knowledge Merge in Reinforced Agentic Models
Paper • 2601.13572 • Published • 24 -
Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders
Paper • 2601.16208 • Published • 52 -
Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model
Paper • 2601.15892 • Published • 53 -
Agentic-R: Learning to Retrieve for Agentic Search
Paper • 2601.11888 • Published • 19 -
LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning
Paper • 2601.10129 • Published • 12 -
Agentic Reasoning for Large Language Models
Paper • 2601.12538 • Published • 195 -
ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development
Paper • 2601.11077 • Published • 65 -
NAACL: Noise-AwAre Verbal Confidence Calibration for LLMs in RAG Systems
Paper • 2601.11004 • Published • 30 -
Language of Thought Shapes Output Diversity in Large Language Models
Paper • 2601.11227 • Published • 9 -
Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning
Paper • 2601.09667 • Published • 91 -
OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfer
Paper • 2601.14250 • Published • 47 -
LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR
Paper • 2601.14251 • Published • 24 -
PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models
Paper • 2601.11087 • Published • 11 -
Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning
Paper • 2602.11748 • Published • 30 -
Length-Unbiased Sequence Policy Optimization: Revealing and Controlling Response Length Variation in RLVR
Paper • 2602.05261 • Published • 49 -
LatentMem: Customizing Latent Memory for Multi-Agent Systems
Paper • 2602.03036 • Published • 14 -
Reinforced Attention Learning
Paper • 2602.04884 • Published • 28 -
3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation
Paper • 2602.03796 • Published • 57 -
Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations
Paper • 2602.05885 • Published • 28 -
VLS: Steering Pretrained Robot Policies via Vision-Language Models
Paper • 2602.03973 • Published • 22 -
Efficient Autoregressive Video Diffusion with Dummy Head
Paper • 2601.20499 • Published • 8 -
CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs
Paper • 2602.03048 • Published • 33 -
ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought
Paper • 2601.23184 • Published • 36 -
CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
Paper • 2602.01785 • Published • 93 -
Balancing Understanding and Generation in Discrete Diffusion Models
Paper • 2602.01362 • Published • 14 -
Latent Chain-of-Thought as Planning: Decoupling Reasoning from Verbalization
Paper • 2601.21358 • Published • 7 -
daVinci-Agency: Unlocking Long-Horizon Agency Data-Efficiently
Paper • 2602.02619 • Published • 50 -
Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models
Paper • 2601.22060 • Published • 154 -
PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss
Paper • 2602.02493 • Published • 42 -
RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System
Paper • 2602.02488 • Published • 32 -
MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning
Paper • 2601.21468 • Published • 25 -
Innovator-VL: A Multimodal Large Language Model for Scientific Discovery
Paper • 2601.19325 • Published • 79 -
Memory-V2V: Augmenting Video-to-Video Diffusion Models with Memory
Paper • 2601.16296 • Published • 28 -
Self-Distillation Enables Continual Learning
Paper • 2601.19897 • Published • 26 -
Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation
Paper • 2601.20614 • Published • 118 -
Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation
Paper • 2601.21406 • Published • 5 -
Reinforcement Learning via Self-Distillation
Paper • 2601.20802 • Published • 40 -
Visual Personalization Turing Test
Paper • 2601.22680 • Published • 2 -
TTCS: Test-Time Curriculum Synthesis for Self-Evolving
Paper • 2601.22628 • Published • 35 -
EgoActor: Grounding Task Planning into Spatial-aware Egocentric Actions for Humanoid Robots via Visual-Language Models
Paper • 2602.04515 • Published • 38 -
DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation
Paper • 2601.22153 • Published • 69 -
Beyond Imitation: Reinforcement Learning for Active Latent Planning
Paper • 2601.21598 • Published • 9 -
Linear representations in language models can change dramatically over a conversation
Paper • 2601.20834 • Published • 21 -
Post-LayerNorm Is Back: Stable, ExpressivE, and Deep
Paper • 2601.19895 • Published • 23 -
Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability
Paper • 2601.18778 • Published • 40 -
Endless Terminals: Scaling RL Environments for Terminal Agents
Paper • 2601.16443 • Published • 16 -
iFSQ: Improving FSQ for Image Generation with 1 Line of Code
Paper • 2601.17124 • Published • 32