Reviewed by the event organisers
Permanent, citable homes for conference papers.
Open-access proceedings for conferences, workshops and symposia. Organisers deposit their accepted papers; every paper and every volume receives a DOI.
7 resultsSearch & filters ↓
We audit 2,400 checklist responses submitted over three years and compare them against the papers they accompany. Checks for compute reporting and variance were answered affirmatively in 78% of cases but supported by the paper in only 41%, suggesting that checklists work best when responses must point to a location in the text.
Fatima Zahra El Idrissi, Ravi Menon
Model checkpoints are cited by URL and then disappear. We propose a metadata profile for model checkpoints that supports DOIs, content hashes and links to training data and code, and evaluate it by retro-fitting 120 published checkpoints.
We study reports from 300 openly reviewed machine-learning papers. Open reports are longer, more specific and more often cite evidence than comparable anonymous reports from closed venues, and reviewers who sign their reports are no more lenient. We discuss limits of the comparison.
Four-bit quantisation of small language models often hurts instruction following. We distil from a full-precision teacher while letting the student's layers use different bit widths chosen by a sensitivity analysis. The resulting 1.1B-parameter model fits in 700 MB and retains 96% of teacher accuracy on our instruction-following suite.
Long conversations on a phone are limited by the size of the key-value cache. We compare eviction, quantisation and merging strategies under hard memory budgets and find that a hybrid of merging and 8-bit storage keeps perplexity within 3% at one quarter of the memory.
Agents that retry failed tool calls recover from transient errors but can also compound mistakes and waste resources. We analyse 18,000 recorded agent runs and show that retries help for network and rate-limit errors but hurt for malformed arguments. We propose a retry budget that depends on the error class and show that it improves success by 6 points at equal cost.
Tool-using agents are typically granted broad credentials, so a single injected instruction can cause large harm. We describe a capability-token scheme in which every tool call carries a narrowly scoped, short-lived token issued by a policy layer outside the model. A prototype blocks all 41 attack scripts in our test suite with under 4 ms of added latency.
