The Pitfalls of KV Cache Compression
Paper
•
2510.00231
•
Published
•
4
•
2
Librarian Bot (Bot)
librarian-bot
AI & ML interests
I am a friendly librarian bot working to help improve metadata on the 🤗 hub. Run by Hugging Face'ss Machine Learning Librarian (HF username: davanstrien)
Recent Activity
liked
a dataset
29 minutes ago
biglam/doab-metadata-extraction
updated
a dataset
about 7 hours ago
librarian-bots/paper-recommendations-v2
commented on
a paper
about 7 hours ago
The Pitfalls of KV Cache Compression
Organizations
commented
20
papers
about 7 hours ago
Rethinking Reward Models for Multi-Domain Test-Time Scaling
Paper
•
2510.00492
•
Published
•
23
•
2
Eliciting Secret Knowledge from Language Models
Paper
•
2510.01070
•
Published
•
2
•
2
Making, not Taking, the Best of N
Paper
•
2510.00931
•
Published
•
7
•
2
BroRL: Scaling Reinforcement Learning via Broadened Exploration
Paper
•
2510.01180
•
Published
•
10
•
2
EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing
Paper
•
2509.26346
•
Published
•
12
•
3
Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution
Paper
•
2509.25301
•
Published
•
12
•
2
In-Place Feedback: A New Paradigm for Guiding LLMs in Multi-Turn Reasoning
Paper
•
2510.00777
•
Published
•
2
•
1
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
Paper
•
2510.00526
•
Published
•
7
•
2
It Takes Two: Your GRPO Is Secretly DPO
Paper
•
2510.00977
•
Published
•
19
•
2
Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models
Paper
•
2509.25162
•
Published
•
2
SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights
Paper
•
2509.22944
•
Published
•
29
•
3
TGPO: Temporal Grounded Policy Optimization for Signal Temporal Logic Tasks
Paper
•
2510.00225
•
Published
•
1
•
2
Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned
Paper
•
2509.23250
•
Published
•
5
•
2
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search
Paper
•
2509.25454
•
Published
•
106
•
2
Pay-Per-Search Models are Abstention Models
Paper
•
2510.01152
•
Published
•
4
•
2
MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources
Paper
•
2509.25531
•
Published
•
4
•
3
Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls
Paper
•
2510.00184
•
Published
•
13
•
3
Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures
Paper
•
2509.25045
•
Published
•
2
•
2
PIPer: On-Device Environment Setup via Online Reinforcement Learning
Paper
•
2509.25455
•
Published
•
26
•
2