lusxvr/nanoVLM-222M
Image-Text-to-Text
•
0.2B
•
Updated
•
267
•
96
Library
-
-
Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
Paper • 2503.09516 • Published • 36 -
AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
Paper • 2505.24863 • Published • 97 -
QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
Paper • 2505.17667 • Published • 88 -
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Paper • 2505.24864 • Published • 138 -
AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning
Paper • 2505.24298 • Published • 28 -
GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning
Paper • 2505.20355 • Published • 35 -
Interleaved Reasoning for Large Language Models via Reinforcement Learning
Paper • 2505.19640 • Published • 14 -
FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow
Paper • 2505.17399 • Published • 14 -
Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
Paper • 2505.19914 • Published • 43 -
One RL to See Them All: Visual Triple Unified Reinforcement Learning
Paper • 2505.18129 • Published • 59 -
Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models
Paper • 2505.14810 • Published • 62 -
Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning
Paper • 2505.16410 • Published • 57 -
JULI: Jailbreak Large Language Models by Self-Introspection
Paper • 2505.11790 • Published -
Optimizing Anytime Reasoning via Budget Relative Policy Optimization
Paper • 2505.13438 • Published • 36 -
Reward Reasoning Model
Paper • 2505.14674 • Published • 37 -
RM-R1: Reward Modeling as Reasoning
Paper • 2505.02387 • Published • 78 -
CPGD: Toward Stable Rule-based Reinforcement Learning for Language Models
Paper • 2505.12504 • Published • 24 -
Neuro-Symbolic Query Compiler
Paper • 2505.11932 • Published • 18 -
Ψ-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models
Paper • 2506.01320 • Published • 16 -
Aligning Latent Spaces with Flow Priors
Paper • 2506.05240 • Published • 27 -
Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
Paper • 2506.00070 • Published • 29 -
A Controllable Examination for Long-Context Language Models
Paper • 2506.02921 • Published • 33 -
MotionSight: Boosting Fine-Grained Motion Understanding in Multimodal LLMs
Paper • 2506.01674 • Published • 28 -
CodeContests+: High-Quality Test Case Generation for Competitive Programming
Paper • 2506.05817 • Published • 9 -
FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion
Paper • 2506.01111 • Published • 30 -
Reinforcement Pre-Training
Paper • 2506.08007 • Published • 262 -
GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior
Paper • 2506.08012 • Published • 7 -
Dreamland: Controllable World Creation with Simulator and Generative Models
Paper • 2506.08006 • Published • 7 -
Saffron-1: Towards an Inference Scaling Paradigm for LLM Safety Assurance
Paper • 2506.06444 • Published • 73 -
BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation
Paper • 2506.07530 • Published • 20 -
Solving Inequality Proofs with Large Language Models
Paper • 2506.07927 • Published • 20 -
Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better
Paper • 2506.09040 • Published • 34 -
Through the Valley: Path to Effective Long CoT Training for Small Language Models
Paper • 2506.07712 • Published • 18 -
Multimodal DeepResearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Framework
Paper • 2506.02454 • Published • 7 -
Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation
Paper • 2506.04614 • Published • 18 -
Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning
Paper • 2506.06205 • Published • 30 -
Magistral
Paper • 2506.10910 • Published • 64 -
Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Team
Paper • 2506.14234 • Published • 41 -
Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers
Paper • 2506.14702 • Published • 3 -
AR-RAG: Autoregressive Retrieval Augmentation for Image Generation
Paper • 2506.06962 • Published • 28 -
DoTA-RAG: Dynamic of Thought Aggregation RAG
Paper • 2506.12571 • Published • 50 -
syftr: Pareto-Optimal Generative AI
Paper • 2505.20266 • Published -
Scaling Test-time Compute for LLM Agents
Paper • 2506.12928 • Published • 63 -
LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning
Paper • 2506.10082 • Published • 8 -
General-Reasoner: Advancing LLM Reasoning Across All Domains
Paper • 2505.14652 • Published • 23 -
Optimizing Length Compression in Large Reasoning Models
Paper • 2506.14755 • Published • 10 -
UniFork: Exploring Modality Alignment for Unified Multimodal Understanding and Generation
Paper • 2506.17202 • Published • 10 -
ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs
Paper • 2506.18896 • Published • 29 -
Vision-Guided Chunking Is All You Need: Enhancing RAG with Multimodal Document Understanding
Paper • 2506.16035 • Published • 88 -
Robust Reward Modeling via Causal Rubrics
Paper • 2506.16507 • Published • 9 -
LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion
Paper • 2507.02813 • Published • 60 -
FreeMorph: Tuning-Free Generalized Image Morphing with Diffusion Model
Paper • 2507.01953 • Published • 19 -
Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective
Paper • 2506.17930 • Published • 19 -
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
Paper • 2506.24119 • Published • 50 -
katanemo/Arch-Router-1.5B
Text Generation • 2B • Updated • 3.29k • • 215 -
Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky
Paper • 2507.03336 • Published • 5 -
SingLoRA: Low Rank Adaptation Using a Single Matrix
Paper • 2507.05566 • Published • 112 -
CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization
Paper • 2507.06181 • Published • 43 -
AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs
Paper • 2507.05687 • Published • 27 -
Coding Triangle: How Does Large Language Model Understand Code?
Paper • 2507.06138 • Published • 21 -
High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning
Paper • 2507.05920 • Published • 11 -
RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs
Paper • 2507.03253 • Published • 18 -
Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs
Paper • 2507.07996 • Published • 34 -
Lumos-1: On Autoregressive Video Generation from a Unified Model Perspective
Paper • 2507.08801 • Published • 30 -
A Survey of Context Engineering for Large Language Models
Paper • 2507.13334 • Published • 257 -
WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization
Paper • 2507.15061 • Published • 59 -
AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning
Paper • 2507.12841 • Published • 41 -
Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning
Paper • 2507.16784 • Published • 120 -
MUR: Momentum Uncertainty guided Reasoning for Large Language Models
Paper • 2507.14958 • Published • 46 -
Does More Inference-Time Compute Really Help Robustness?
Paper • 2507.15974 • Published • 7 -
RefCritic: Training Long Chain-of-Thought Critic Models with Refinement Feedback
Paper • 2507.15024 • Published • 14 -
ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting
Paper • 2507.15454 • Published • 7 -
Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models
Paper • 2507.14241 • Published • 17 -
TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation
Paper • 2507.18537 • Published • 17 -
Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos
Paper • 2507.15597 • Published • 33 -
A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning
Paper • 2507.14295 • Published • 13 -
SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction
Paper • 2507.15852 • Published • 38 -
FLEXITOKENS: Flexible Tokenization for Evolving Language Models
Paper • 2507.12720 • Published • 9 -
RiemannLoRA: A Unified Riemannian Framework for Ambiguity-Free LoRA Optimization
Paper • 2507.12142 • Published • 36 -
Replacing thinking with tool usage enables reasoning in small language models
Paper • 2507.05065 • Published • 15 -
Lizard: An Efficient Linearization Framework for Large Language Models
Paper • 2507.09025 • Published • 18 -
MemOS: A Memory OS for AI System
Paper • 2507.03724 • Published • 153 -
Agentic Reinforced Policy Optimization
Paper • 2507.19849 • Published • 156 -
Deep Researcher with Test-Time Diffusion
Paper • 2507.16075 • Published • 64 -
SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment
Paper • 2507.20984 • Published • 56 -
MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents
Paper • 2507.19478 • Published • 30 -
Geometric-Mean Policy Optimization
Paper • 2507.20673 • Published • 31 -
UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities
Paper • 2507.19766 • Published • 14 -
VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning
Paper • 2507.22607 • Published • 46 -
Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models
Paper • 2508.00819 • Published • 62 -
Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Following
Paper • 2508.02150 • Published • 36 -
Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training
Paper • 2508.00414 • Published • 91 -
On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective
Paper • 2507.23632 • Published • 6 -
Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving
Paper • 2507.23726 • Published • 113 -
SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension
Paper • 2508.01959 • Published • 56 -
Tool-integrated Reinforcement Learning for Repo Deep Search
Paper • 2508.03012 • Published • 20 -
InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization
Paper • 2508.05731 • Published • 25 -
MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh
Paper • 2508.01242 • Published • 10 -
Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning
Paper • 2508.08221 • Published • 48 -
Reinforcement Learning in Vision: A Survey
Paper • 2508.08189 • Published • 29 -
Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents
Paper • 2508.05954 • Published • 6 -
Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments
Paper • 2508.08791 • Published • 16 -
Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning
Paper • 2508.03501 • Published • 56 -
Complex Logical Instruction Generation
Paper • 2508.09125 • Published • 39 -
Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery
Paper • 2508.08401 • Published • 42 -
Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
Paper • 2508.09192 • Published • 30 -
Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping
Paper • 2508.12466 • Published • 8 -
Has GPT-5 Achieved Spatial Intelligence? An Empirical Study
Paper • 2508.13142 • Published • 34 -
VertexRegen: Mesh Generation with Continuous Level of Detail
Paper • 2508.09062 • Published • 37 -
XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization
Paper • 2508.10395 • Published • 42 -
STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer
Paper • 2508.10893 • Published • 31 -
FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction
Paper • 2508.11987 • Published • 69 -
MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents
Paper • 2508.13186 • Published • 18 -
Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models
Paper • 2508.10751 • Published • 28 -
UI-Venus Technical Report: Building High-performance UI Agents with RFT
Paper • 2508.10833 • Published • 43 -
Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models
Paper • 2508.09968 • Published • 15 -
CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search
Paper • 2508.02091 • Published • 13 -
LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries
Paper • 2508.15760 • Published • 46 -
Deep Think with Confidence
Paper • 2508.15260 • Published • 87 -
DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization
Paper • 2508.14460 • Published • 82 -
Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs
Paper • 2508.14896 • Published • 22 -
PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs
Paper • 2508.17188 • Published • 17 -
Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning
Paper • 2508.16949 • Published • 22 -
Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation
Paper • 2508.18032 • Published • 41 -
Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling
Paper • 2508.16745 • Published • 28 -
UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning
Paper • 2508.18756 • Published • 36 -
Do What? Teaching Vision-Language-Action Models to Reject the Impossible
Paper • 2508.16292 • Published • 9 -
MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting
Paper • 2508.17811 • Published • 6 -
FastMesh:Efficient Artistic Mesh Generation via Component Decoupling
Paper • 2508.19188 • Published • 16 -
Spacer: Towards Engineered Scientific Inspiration
Paper • 2508.17661 • Published • 32 -
ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models
Paper • 2508.18773 • Published • 15 -
VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space
Paper • 2508.19247 • Published • 41 -
TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling
Paper • 2508.17445 • Published • 80 -
Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Paper • 2508.20751 • Published • 89 -
Provable Benefits of In-Tool Learning for Large Language Models
Paper • 2508.20755 • Published • 11 -
Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models
Paper • 2508.21365 • Published • 28 -
Efficient Code Embeddings from Code Generation Models
Paper • 2508.21290 • Published • 18 -
CLIPSym: Delving into Symmetry Detection with CLIP
Paper • 2508.14197 • Published • 8 -
Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR
Paper • 2509.02522 • Published • 25 -
SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
Paper • 2509.02479 • Published • 83 -
Universal Deep Research: Bring Your Own Model and Strategy
Paper • 2509.00244 • Published • 13 -
LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations
Paper • 2509.03405 • Published • 23 -
Open Data Synthesis For Deep Research
Paper • 2509.00375 • Published • 68 -
Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?
Paper • 2509.04292 • Published • 57 -
Towards a Unified View of Large Language Model Post-Training
Paper • 2509.04419 • Published • 73 -
How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench
Paper • 2508.20931 • Published • 15 -
Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers
Paper • 2509.03059 • Published • 24 -
NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings
Paper • 2509.04011 • Published • 28 -
Symbolic Graphics Programming with Large Language Models
Paper • 2509.05208 • Published • 45 -
Bootstrapping Task Spaces for Self-Improvement
Paper • 2509.04575 • Published • 5 -
Behavioral Fingerprinting of Large Language Models
Paper • 2509.04504 • Published • 5 -
Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers
Paper • 2509.06493 • Published • 11 -
Reinforcement Learning Foundations for Deep Research Systems: A Survey
Paper • 2509.06733 • Published • 31 -
Reconstruction Alignment Improves Unified Multimodal Models
Paper • 2509.07295 • Published • 40 -
Visual Representation Alignment for Multimodal Large Language Models
Paper • 2509.07979 • Published • 83 -
Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
Paper • 2509.06949 • Published • 56 -
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
Paper • 2509.07980 • Published • 98 -
Towards General Agentic Intelligence via Environment Scaling
Paper • 2509.13311 • Published • 70 -
WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning
Paper • 2509.13305 • Published • 89 -
SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation
Paper • 2509.10708 • Published • 17 -
HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering
Paper • 2509.09713 • Published • 24 -
FlowRL: Matching Reward Distributions for LLM Reasoning
Paper • 2509.15207 • Published • 110 -
Single-stream Policy Optimization
Paper • 2509.13232 • Published • 33 -
World Modeling with Probabilistic Structure Integration
Paper • 2509.09737 • Published • 13 -
Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning
Paper • 2509.13755 • Published • 19 -
C2-Evo: Co-Evolving Multimodal Data and Model for Self-Improving Reasoning
Paper • 2507.16518 • Published • 2 -
WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance
Paper • 2509.15130 • Published • 30 -
Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation
Paper • 2509.15194 • Published • 33 -
THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning
Paper • 2509.13761 • Published • 16 -
A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning
Paper • 2509.15937 • Published • 20 -
BaseReward: A Strong Baseline for Multimodal Reward Model
Paper • 2509.16127 • Published • 21 -
MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks
Paper • 2509.14638 • Published • 11 -
Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents
Paper • 2509.15233 • Published • 2 -
MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
Paper • 2509.16197 • Published • 54 -
Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification
Paper • 2509.15591 • Published • 45 -
BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent
Paper • 2509.15566 • Published • 14 -
Mano Report
Paper • 2509.17336 • Published • 10 -
Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback
Paper • 2501.10799 • Published • 15 -
Table as Thought: Exploring Structured Thoughts in LLM Reasoning
Paper • 2501.02152 • Published -
Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning
Paper • 2412.09078 • Published -
TinyThinker: Distilling Reasoning through Coarse-to-Fine Knowledge Internalization with Self-Reflection
Paper • 2412.08024 • Published • 1 -
LLM2: Let Large Language Models Harness System 2 Reasoning
Paper • 2412.20372 • Published -
Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective
Paper • 2501.11110 • Published • 4 -
Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning
Paper • 2412.15797 • Published • 18 -
RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement
Paper • 2412.12881 • Published • 2 -
OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models
Paper • 2509.17627 • Published • 65 -
Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation
Paper • 2509.18824 • Published • 22 -
Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode Theory
Paper • 2509.14662 • Published • 13 -
VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models
Paper • 2509.19803 • Published • 117 -
Tree Search for LLM Agent Reinforcement Learning
Paper • 2509.21240 • Published • 88 -
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention
Paper • 2509.24006 • Published • 115 -
Fine-tuning Done Right in Model Editing
Paper • 2509.22072 • Published • 28 -
No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping
Paper • 2509.21880 • Published • 51 -
LucidFlux: Caption-Free Universal Image Restoration via a Large-Scale Diffusion Transformer
Paper • 2509.22414 • Published • 21 -
Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning
Paper • 2509.22601 • Published • 29 -
EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning
Paper • 2509.22576 • Published • 132 -
Variational Reasoning for Language Models
Paper • 2509.22637 • Published • 68 -
AutoIntent: AutoML for Text Classification
Paper • 2509.21138 • Published • 33 -
TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning
Paper • 2509.25760 • Published • 53 -
Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
Paper • 2509.26628 • Published • 14 -
Sequential Diffusion Language Models
Paper • 2509.24007 • Published • 42 -
ReviewScore: Misinformed Peer Review Detection with Large Language Models
Paper • 2509.21679 • Published • 63 -
ReviewRL: Towards Automated Scientific Review with RL
Paper • 2508.10308 • Published -
ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks
Paper • 2508.15804 • Published • 15 -
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search
Paper • 2509.25454 • Published • 136 -
Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
Paper • 2509.25849 • Published • 47 -
BroRL: Scaling Reinforcement Learning via Broadened Exploration
Paper • 2510.01180 • Published • 17 -
GEM: A Gym for Agentic LLMs
Paper • 2510.01051 • Published • 87 -
Interactive Training: Feedback-Driven Neural Network Optimization
Paper • 2510.02297 • Published • 42 -
More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models
Paper • 2509.25848 • Published • 78 -
CLUE: Non-parametric Verification from Experience via Hidden-State Clustering
Paper • 2510.01591 • Published • 26 -
LongCodeZip: Compress Long Context for Code Language Models
Paper • 2510.00446 • Published • 107 -
Efficient Multi-modal Large Language Models via Progressive Consistency Distillation
Paper • 2510.00515 • Published • 39 -
Reactive Transformer (RxT) -- Stateful Real-Time Processing for Event-Driven Reactive Language Models
Paper • 2510.03561 • Published • 23 -
Large Language Models as Optimizers
Paper • 2309.03409 • Published • 77 -
Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Paper • 2309.08532 • Published • 53 -
PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback
Paper • 2307.14936 • Published • 41 -
Factuality Matters: When Image Generation and Editing Meet Structured Visuals
Paper • 2510.05091 • Published • 18 -
Reinforce-Ada: An Adaptive Sampling Framework for Reinforce-Style LLM Training
Paper • 2510.04996 • Published • 15 -
Paper2Video: Automatic Video Generation from Scientific Papers
Paper • 2510.05096 • Published • 109 -
SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
Paper • 2510.05069 • Published • 12 -
MITS: Enhanced Tree Search Reasoning for LLMs via Pointwise Mutual Information
Paper • 2510.03632 • Published • 41 -
Large Reasoning Models Learn Better Alignment from Flawed Thinking
Paper • 2510.00938 • Published • 57 -
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 459 -
Multi-Agent Tool-Integrated Policy Optimization
Paper • 2510.04678 • Published • 30 -
Agent Learning via Early Experience
Paper • 2510.08558 • Published • 255 -
Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models
Paper • 2510.05034 • Published • 46 -
Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
Paper • 2510.03222 • Published • 45 -
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
Paper • 2510.11696 • Published • 168 -
PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs
Paper • 2510.09507 • Published • 10 -
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
Paper • 2510.04618 • Published • 110 -
Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models
Paper • 2510.08492 • Published • 7 -
Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
Paper • 2510.09577 • Published • 6 -
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
Paper • 2510.08697 • Published • 33 -
Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs
Paper • 2510.09201 • Published • 47 -
Diffusion Transformers with Representation Autoencoders
Paper • 2510.11690 • Published • 160 -
UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning
Paper • 2510.13515 • Published • 11 -
Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training
Paper • 2510.12586 • Published • 107 -
Understanding DeepResearch via Reports
Paper • 2510.07861 • Published • 6 -
RAG-Anything: All-in-One RAG Framework
Paper • 2510.12323 • Published • 42 -
The Art of Scaling Reinforcement Learning Compute for LLMs
Paper • 2510.13786 • Published • 30 -
Glyph: Scaling Context Windows via Visual-Text Compression
Paper • 2510.17800 • Published • 63 -
LoongRL:Reinforcement Learning for Advanced Reasoning over Long Contexts
Paper • 2510.19363 • Published • 58 -
Unified Reinforcement and Imitation Learning for Vision-Language Models
Paper • 2510.19307 • Published • 26 -
Attention Is All You Need for KV Cache in Diffusion LLMs
Paper • 2510.14973 • Published • 37 -
Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn LLM Agents
Paper • 2510.14967 • Published • 32 -
Video Reasoning without Training
Paper • 2510.17045 • Published • 7 -
AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders
Paper • 2510.19779 • Published • 58 -
Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall
Paper • 2510.19304 • Published • 22 -
Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values
Paper • 2510.20187 • Published • 18 -
ReCode: Unify Plan and Action for Universal Granularity Control
Paper • 2510.23564 • Published • 113 -
Reasoning with Sampling: Your Base Model is Smarter Than You Think
Paper • 2510.14901 • Published • 43 -
Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning
Paper • 2510.23473 • Published • 78