StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training
Paper • 2609.26774 • Published • 56
Aylin Öztürk
aylin-oo
·
AI & ML interests
Retrieval-augmented generation, dense retrieval, open-domain question answering, RAG pipelines
Recent Activity
liked a dataset 2 days ago
llmware/rag_instruct_benchmark_tester liked a dataset 2 days ago
glaiveai/RAG-v1 upvoted a paper 2 days ago
StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer TrainingOrganizations
None yet
upvoted 2
papers 2 days ago
upvoted 6
papers 5 days ago
Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion
Paper • 2609.24220 • Published • 68
OmniEdu: Open Foundation Models for Learning and Teaching
Paper • 2609.23088 • Published • 234
Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations
Paper • 2609.22255 • Published • 22
The Functionalizer: Lossless Functional Decomposition for Subword Tokenization
Paper • 2609.15991 • Published • 17
Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents
Paper • 2609.23986 • Published • 28
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
Paper • 2609.24972 • Published • 217
upvoted 10
papers 7 days ago
StudentSim: Training LLM-based Student Simulators
Paper • 2609.01591 • Published • 476
When2Think: Learning When and How Much to Reason
Paper • 2609.19671 • Published • 54
JEPA-Anything: Learning Predictive Models across Different Worlds
Paper • 2609.20800 • Published • 75
FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations
Paper • 2609.20817 • Published • 40
VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control
Paper • 2609.19554 • Published • 42
UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation
Paper • 2609.12397 • Published • 46
WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing
Paper • 2609.20423 • Published • 48
PACT: Can Enterprise AI Assistants Be Trusted Under Pressure?
Paper • 2609.18605 • Published • 41
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
Paper • 2609.19969 • Published • 190
An Empirical Study of Harness Design for Coding Agents
Paper • 2609.20804 • Published • 91
upvoted 2
papers 8 days ago