U Berkeley, Kurt Keutzer, Ziyang Wu, Xiuyu Li, Tianjun Zhang, Shishir Patil, Sijun Tan, Llm Decoder, Context Encoder, Joeseph Gonzalez, Ada Popa
2 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.
"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2404.07979.json · badge: /api/ran/2404.07979.svg
Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.
| Repository | Role | Ran |
|---|---|---|
| jeffreysijuntan/lloco | marked official in Papers with Code Papers with Code archive |
2 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| CausalACOutputWithPast | Ran ran on a synthesized input · constructed an object; no result was computed |
jeffreysijuntan/lloco/auto_compressor.py code served (permissive licence) · get_code("8cce01de15fdc4a1") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, CausalACOutputWithPast: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| SummaryConfig | Ran ran on a synthesized input · constructed an object; no result was computed |
jeffreysijuntan/lloco/auto_compressor.py code served (permissive licence) · get_code("4c0a7a2269e32d18") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, SummaryConfig: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| LLoCOAutoCompressorMixin | Not yet run unverified (harvested, no recorded run) |
jeffreysijuntan/lloco/auto_compressor.py code served (permissive licence) · get_code("5f03a86c025b034c") How it ranno invocation recorded. |
Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).
Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| CausalACOutputWithPast brick of this paper's assembly: helper |
1 other paper 1 dated earlier |
2305.14788 (2023-05) Adapting Language Models to Compress Contexts |
|
| SummaryConfig brick of this paper's assembly: helper |
1 other paper 1 dated earlier · 1 only as an assembly brick |
2305.14788 (2023-05) Adapting Language Models to Compress Contexts |
Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Processing long contexts remains a challenge for large language models (LLMs) due to the quadratic computational and memory overhead of the self-attention mechanism and the substantial KV cache sizes during generation. We propose LLoCO, a novel approach to address this problem by learning contexts offline through context compression and in-domain parameter-efficient finetuning with LoRA. Our method enables an LLM to create a concise representation of the original context and efficiently retrieve relevant information to answer questions accurately. Our approach extends the effective context window of a 4k token LLaMA2-7B model to handle up to 128k tokens. We evaluate our approach on several longcontext question-answering datasets, demonstrating that LLoCO significantly outperforms in-context learning while using 30× fewer tokens during inference. LLoCO achieves up to 7.62× speed-up during inference and 11.52× higher throughput during finetuning, substantially reduces the cost of long document question answering. This makes it a promising solution for efficient long context processing. 1 * Equal contribution 1 Our code is publicly available on https://github.com/ jeffreysijuntan/lloco.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2404.07979")
get_code_for_paper("2404.07979")
have("2404.07979")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2404.07979.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2404.07979)
Connect an agent — have() is free.