Hacker Newsnew | past | comments | ask | show | jobs | submit | veryluckyxyz's submissionslogin
1.
Generalizing Test-Time Compute-Optimal Scaling as an Optimizable Graph (huggingface.co)
2 points by veryluckyxyz 31 days ago | past
2.
Hidden drivers of HRM's performance on ARC-AGI (arcprize.org)
31 points by veryluckyxyz 59 days ago | past | 2 comments
3.
Set Block Decoding Is a Language Model Inference Accelerator (arxiv.org)
4 points by veryluckyxyz 89 days ago | past
4.
Deep Think with Confidence (jiaweizzhao.github.io)
1 point by veryluckyxyz 3 months ago | past
5.
A Batch Size and Token NUM- BER Agnostic Learning Rate Scheduler (arxiv.org)
2 points by veryluckyxyz 6 months ago | past
6.
Easily Understand Rdma Technology (naddod.com)
1 point by veryluckyxyz 6 months ago | past | 1 comment
7.
Model Merging in Pre-Training of Large Language Models (arxiv.org)
2 points by veryluckyxyz 6 months ago | past
8.
Understanding Perception and Reasoning Through Model Merging (arxiv.org)
2 points by veryluckyxyz 6 months ago | past
9.
Building and better understanding vision-language models (2024) (huggingface.co)
2 points by veryluckyxyz 7 months ago | past
10.
HF smolagents computer-agent demo (huggingface.co)
1 point by veryluckyxyz 7 months ago | past
11.
Do Reasoning Models Show Better Verbalized Calibration? (arxiv.org)
2 points by veryluckyxyz 7 months ago | past
12.
Robustly identifying concepts introduced during chat fine-tuning with crosscoder (arxiv.org)
6 points by veryluckyxyz 7 months ago | past
13.
Retrieval with Learned Similarities (arxiv.org)
3 points by veryluckyxyz 8 months ago | past
14.
The Curse of Depth in Large Language Models (arxiv.org)
1 point by veryluckyxyz 8 months ago | past
15.
Looking Back at Speculative Decoding (research.google)
36 points by veryluckyxyz 9 months ago | past | 5 comments
16.
Long-Context GRPO (unsloth.ai)
60 points by veryluckyxyz 9 months ago | past | 22 comments
17.
HippoRAG: Neurobiologically Inspired Long-Term Memory for LLMs (2024) (arxiv.org)
65 points by veryluckyxyz 10 months ago | past | 4 comments
18.
Learning to Plan and Reason for Evaluation with Thinking-LLM-as-a-Judge (arxiv.org)
1 point by veryluckyxyz 10 months ago | past
19.
Process Reinforcement Through Implicit Rewards (curvy-check-498.notion.site)
1 point by veryluckyxyz 11 months ago | past
20.
Explaining Large Language Models Decisions Using Shapley Values (arxiv.org)
89 points by veryluckyxyz 11 months ago | past | 19 comments
21.
Phi-4 Technical Report (arxiv.org)
2 points by veryluckyxyz 11 months ago | past
22.
Alignment Faking in LLMs [pdf] (anthropic.com)
2 points by veryluckyxyz 11 months ago | past | 1 comment
23.
What Makes Rotary Positional Encodings Useful? (arxiv.org)
1 point by veryluckyxyz on Nov 18, 2024 | past
24.
Rethinking Softmax: Self-Attention with Polynomial Activations (arxiv.org)
2 points by veryluckyxyz on Oct 27, 2024 | past
25.
Post-Training Layer Scaling Prevents Forgetting and Enhances Model Merging (arxiv.org)
1 point by veryluckyxyz on Oct 26, 2024 | past
26.
Random Matrix Theory in Machine Learning Tutorial (random-matrix-learning.github.io)
2 points by veryluckyxyz on Sept 18, 2024 | past
27.
Rerankers: A Lightweight Python Library to Unify Ranking Methods (answer.ai)
1 point by veryluckyxyz on Sept 17, 2024 | past
28.
Double Descent Demystified (arxiv.org)
1 point by veryluckyxyz on Sept 15, 2024 | past
29.
Synthetic Continued Pretraining (arxiv.org)
3 points by veryluckyxyz on Sept 14, 2024 | past
30.
Bright: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval (arxiv.org)
1 point by veryluckyxyz on July 21, 2024 | past

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: