|
|
|
Stories from October 15, 2024 (UTC)
|
| 1. |
Running LLMs with 3.3M Context Tokens on a Single GPU (arxiv.org) |
|
14 points by Van_Chopiszt on Oct 15, 2024 | hide | past | pdf | 1 comment
|
|
| 2. |
Cheating Automatic LLM Benchmarks (arxiv.org) |
|
3 points by jneagu on Oct 15, 2024 | hide | past | pdf | discuss
|
|
| 3. |
Tackling the Abstraction and Reasoning Corpus with Vision Transformers (arxiv.org) |
|
2 points by apsec112 on Oct 15, 2024 | hide | past | pdf | discuss
|
|
| 4. |
Paged KV-Cache Compression with Variable Compression Rates per Attention Head (arxiv.org) |
|
2 points by PaulHoule on Oct 15, 2024 | hide | past | pdf | discuss
|
|
| 5. |
Representation Matters (arxiv.org) |
|
2 points by quxinxin on Oct 15, 2024 | hide | past | pdf | discuss
|
|
| 6. |
Thinking LLMs: General Instruction Following with Thought Generation (arxiv.org) |
|
2 points by mnk47 on Oct 15, 2024 | hide | past | pdf | 1 comment
|
|
| 7. |
Data-Prep-Kit: getting your data ready for LLM application development (arxiv.org) |
|
1 point by PaulHoule on Oct 15, 2024 | hide | past | pdf | discuss
|
|
| 8. |
Quantifying Political Neutrality in LLM-Generated News Summaries (arxiv.org) |
|
1 point by Hard_Space on Oct 15, 2024 | hide | past | pdf | discuss
|
|
| 9. |
Intelligence at the Edge of Chaos [evidence of intelligence in LLMs] (arxiv.org) |
|
1 point by fallingknife on Oct 15, 2024 | hide | past | pdf | discuss
|
|
| 10. |
Lie Algebra Canonicalization: Equivariant Neural Ops Under Arbitrary Lie Groups (arxiv.org) |
|
1 point by lnyan on Oct 15, 2024 | hide | past | pdf | discuss
|
|
|
|
