Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
Paper
•
2501.18585
•
Published
•
61
Research Papers/Reviews/Literature
Daily Research papers and review including older relevant content.
-
-
RWKV-7 "Goose" with Expressive Dynamic State Evolution
Paper • 2503.14456 • Published • 153 -
DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning
Paper • 2503.15265 • Published • 47 -
Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
Paper • 2503.15558 • Published • 51 -
One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation
Paper • 2503.13358 • Published • 96 -
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
Paper • 2504.00999 • Published • 95 -
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
Paper • 2504.01990 • Published • 302 -
The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink
Paper • 2204.05149 • Published • 10 -
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Paper • 2504.13837 • Published • 134 -
Learning to Reason under Off-Policy Guidance
Paper • 2504.14945 • Published • 86 -
Kuwain 1.5B: An Arabic SLM via Language Injection
Paper • 2504.15120 • Published • 122 -
TTRL: Test-Time Reinforcement Learning
Paper • 2504.16084 • Published • 120 -
VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models
Paper • 2504.15279 • Published • 75 -
Step1X-Edit: A Practical Framework for General Image Editing
Paper • 2504.17761 • Published • 93 -
Towards Understanding Camera Motions in Any Video
Paper • 2504.15376 • Published • 159 -
BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs
Paper • 2504.18415 • Published • 47 -
MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention
Paper • 2504.16083 • Published • 9 -
LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects
Paper • 2504.19838 • Published • 22 -
Reinforcement Learning for Reasoning in Large Language Models with One Training Example
Paper • 2504.20571 • Published • 97 -
Sadeed: Advancing Arabic Diacritization Through Small Language Model
Paper • 2504.21635 • Published • 59 -
UniversalRAG: Retrieval-Augmented Generation over Multiple Corpora with Diverse Modalities and Granularities
Paper • 2504.20734 • Published • 63 -
A Survey of Interactive Generative Video
Paper • 2504.21853 • Published • 47 -
Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks
Paper • 2505.00234 • Published • 26 -
Improving Editability in Image Generation with Layer-wise Memory
Paper • 2505.01079 • Published • 29 -
Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play
Paper • 2505.02707 • Published • 86 -
Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning
Paper • 2505.03318 • Published • 94 -
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Paper • 2505.03335 • Published • 184 -
Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models
Paper • 2505.04921 • Published • 185 -
Chain-of-Model Learning for Language Model
Paper • 2505.11820 • Published • 122 -
Web-Shepherd: Advancing PRMs for Reinforcing Web Agents
Paper • 2505.15277 • Published • 103 -
Scaling Law for Quantization-Aware Training
Paper • 2505.14302 • Published • 76 -
NovelSeek: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification
Paper • 2505.16938 • Published • 121 -
QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
Paper • 2505.17667 • Published • 89 -
Mutarjim: Advancing Bidirectional Arabic-English Translation with a Small Language Model
Paper • 2505.17894 • Published • 220 -
The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
Paper • 2505.22617 • Published • 129 -
SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
Paper • 2505.20411 • Published • 88 -
Table-R1: Inference-Time Scaling for Table Reasoning
Paper • 2505.23621 • Published • 94 -
Large Language Models for Data Synthesis
Paper • 2505.14752 • Published • 50 -
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Paper • 2506.01939 • Published • 177 -
Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning
Paper • 2506.07044 • Published • 112 -
Reinforcement Pre-Training
Paper • 2506.08007 • Published • 256 -
Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
Paper • 2506.06395 • Published • 130 -
BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing
Paper • 2506.17450 • Published • 63 -
GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
Paper • 2507.01006 • Published • 232 -
Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs
Paper • 2507.09477 • Published • 80 -
Pixels, Patterns, but No Poetry: To See The World like Humans
Paper • 2507.16863 • Published • 68 -
DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis
Paper • 2507.14988 • Published • 7 -
Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving
Paper • 2507.23726 • Published • 108 -
Story2Board: A Training-Free Approach for Expressive Storyboard Generation
Paper • 2508.09983 • Published • 63 -
Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery
Paper • 2508.08401 • Published • 38 -
DINOv3
Paper • 2508.10104 • Published • 183 -
SSRL: Self-Search Reinforcement Learning
Paper • 2508.10874 • Published • 87 -
DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization
Paper • 2508.14460 • Published • 72 -
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
Paper • 2508.06471 • Published • 156