Read Later Stack - a Sheiphan Collection

Sheiphan 's Collections

Read Later Stack

Read Later Stack

updated Oct 22

Demystifying Reinforcement Learning in Agentic Reasoning

Paper • 2510.11701 • Published Oct 13 • 31

Note Added
Self-Improving LLM Agents at Test-Time

Paper • 2510.07841 • Published Oct 9 • 9
Making Mathematical Reasoning Adaptive

Paper • 2510.04617 • Published Oct 6 • 22
DocReward: A Document Reward Model for Structuring and Stylizing

Paper • 2510.11391 • Published Oct 13 • 27

Note Added Obsidian
Skill-Targeted Adaptive Training

Paper • 2510.10023 • Published Oct 11 • 9
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

Paper • 2510.11696 • Published Oct 13 • 176
DITING: A Multi-Agent Evaluation Framework for Benchmarking Web Novel Translation

Paper • 2510.09116 • Published Oct 10 • 96
FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution

Paper • 2510.12747 • Published Oct 14 • 37
Dr.LLM: Dynamic Layer Routing in LLMs

Paper • 2510.12773 • Published Oct 14 • 31
A Survey of Vibe Coding with Large Language Models

Paper • 2510.12399 • Published Oct 14 • 48
Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks

Paper • 2510.12635 • Published Oct 14 • 15
LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokens

Paper • 2510.11919 • Published Oct 13 • 4
HoneyBee: Data Recipes for Vision-Language Reasoners

Paper • 2510.12225 • Published Oct 14 • 10
Diffusion Transformers with Representation Autoencoders

Paper • 2510.11690 • Published Oct 13 • 165
Don't Just Fine-tune the Agent, Tune the Environment

Paper • 2510.10197 • Published Oct 11 • 28
InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue

Paper • 2510.13747 • Published Oct 15 • 29
Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs

Paper • 2510.13795 • Published Oct 15 • 56
The Art of Scaling Reinforcement Learning Compute for LLMs

Paper • 2510.13786 • Published Oct 15 • 30
When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

Paper • 2510.04849 • Published Oct 6 • 113
Agentic Entropy-Balanced Policy Optimization

Paper • 2510.14545 • Published Oct 16 • 104
From Pixels to Words -- Towards Native Vision-Language Primitives at Scale

Paper • 2510.14979 • Published Oct 16 • 65
TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar

Paper • 2510.14972 • Published Oct 16 • 33
BitNet Distillation

Paper • 2510.13998 • Published Oct 15 • 54
Attention Is All You Need for KV Cache in Diffusion LLMs

Paper • 2510.14973 • Published Oct 16 • 39
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model

Paper • 2510.14528 • Published Oct 16 • 103
Large Language Models Do NOT Really Know What They Don't Know

Paper • 2510.09033 • Published Oct 10 • 16
Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures

Paper • 2510.14616 • Published Oct 16 • 11
LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild

Paper • 2510.14240 • Published Oct 16 • 11
Qwen3Guard Technical Report

Paper • 2510.14276 • Published Oct 16 • 14
MoM: Mixtures of Scenario-Aware Document Memories for Retrieval-Augmented Generation Systems

Paper • 2510.14252 • Published Oct 16 • 2
RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems

Paper • 2510.13910 • Published Oct 15 • 1
DeepAnalyze: Agentic Large Language Models for Autonomous Data Science

Paper • 2510.16872 • Published Oct 19 • 104
Glyph: Scaling Context Windows via Visual-Text Compression

Paper • 2510.17800 • Published Oct 20 • 67
When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling

Paper • 2510.15346 • Published Oct 17 • 33
Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation

Paper • 2510.17354 • Published Oct 20 • 33
Visual Autoregressive Models Beat Diffusion Models on Inference Time Scaling

Paper • 2510.16751 • Published Oct 19 • 20
FineVision: Open Data Is All You Need

Paper • 2510.17269 • Published Oct 20 • 68
Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI

Paper • 2510.16720 • Published Oct 19 • 6
UltraCUA: A Foundation Model for Computer Use Agents with Hybrid Action

Paper • 2510.17790 • Published Oct 20 • 5
AsyncVoice Agent: Real-Time Explanation for LLM Planning and Reasoning

Paper • 2510.16156 • Published Oct 17 • 1
Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering

Paper • 2510.14605 • Published Oct 16 • 4