Machine Learning
Research on Machine Learning: explanations, evidence, limitations and connections between papers.
57 results
Match judging evidence to the outcome and its cost
A panel of judges can give more consistent scores after its instructions are clarified, yet show no detectable improvement against expert ratings. A response can also look relevant without answering the request. These cases make “better judging” an incomplete goal until the outcome is named. The studies support choosing evidence for the claim at hand: clarify criteria to study consensus, inspect an answer’s substance to assess request matching, and observe an application in use when its behavior matters. Each choice has a tested scope and a cost; a budget planner depends on how well its pilot represents deployment.
Blitz cuts protein structure sampling to eight steps
Blitz distills AlphaFold 3 and Boltz-2 sampling into eight steps while retaining checked structural accuracy in reported tests.
A run-count method for testing training equivalence
A protocol for testing practical equivalence between training methods models run variation and estimates how many runs are needed.
A learned drafter predicts which masked position comes next
SPOT predicts masked-position order, reducing target passes and improving measured decoding speed on SDAR-8B tests.
Reordering generated programs makes memory savings verifiable
A fixed-wrapper method tests whether reordered neural-network programs realize predicted memory savings and certifies many schedules.
A pilot helps allocate compute when verifiers err
SPLIT allocates samples and verification from a small labeled pilot, staying near hindsight-best choices on unseen tasks.
A local atom model adds long-range forces and electrical response
DPA4C-LR adds long-range electrostatics to distributed atom modeling, with demonstrated scaling and electrical response in tested materials.
Matching training optimizers adds little consistent benefit
Experiments find little consistent downstream benefit from matching AdamW and Muon across language-model training stages.
Cyclone forecasts can locate storms while missing strength
A retrospective cyclone forecast comparison finds stronger location and spatial placement scores alongside persistent peak-wind bias.
Choose low precision models by the constraint the device imposes
A low precision model can score well yet still miss the arithmetic rules of its target device. A proposed cheaper operation may also lack a measured end-to-end hardware benefit. Choose the design that addresses the actual constraint, then read its quality result within the reported test. These studies examine different routes through computation, stored weights, and fixed accelerator rules; their results do not form a common speed ranking.
BitSparse stores sparse feed-forward activations with less memory
BitSparse compresses exact-zero feed-forward activations, reducing measured memory in two language models.
A survival model predicts event curves from censored data
SurvICL predicts survival curves from censored examples and led aggregate comparisons on 63 held-out datasets, with weaker results on larger datasets.
A reporting framework shows how return timing shifts financial NLP labels
An earnings-call audit finds return labels can shift when outcome clocks move to reflect estimated input completion.
A reusable cache keeps tabular predictions accurate after compression
QCOC compresses reusable tabular model memory and has higher mean accuracy than direct compression in tested datasets.
A finer weight grid brings multiplier-free LLM inference closer
A finer four-bit weight grid brings multiplier-free language-model inference close to uniform integer accuracy in most tested settings.
A learned route archive speeds exact vehicle routing
A learned route archive and GPU pricing cut root time in exact vehicle routing while preserving certified bounds.
A learned noise policy steers fast generators without changing them
A reusable noise policy steers tested image, language and protein generators while keeping each generator frozen.
Hyperbolic distance helps agents navigate maze routes
Hyperbolic contrastive learning better reflects maze routes and improves goal reaching across many tested tasks.
A structure score reduces DFT checks under an error budget
A structure-based selector reduced DFT checks across eight molecular model combinations under a shared expected-error budget.
A single calibration protects early-exit prediction sets
A single conformal calibration protects true-label coverage after adaptive early exit, under exchangeability and a frozen model path.
A training flow makes CNNs fit a fixed edge chip’s number rules
ShiftQAT builds MAX7800x scaling rules into CNN training, with comparable reported 8-bit accuracy drops in ImageNet tests.
A method separates data selection from support shifts
A construction-based method separates data selection from support shifts; retrieval evidence favors within-region selection in one data family.
A calibrated reward helps models follow rules and answer well
CaLIF raises added-rule compliance while keeping answer quality near base across five tested model configurations.
Reconstructing replies steadies jailbreak success reports
A reply reconstruction method steadies jailbreak evaluations, while human-labeled tests expose misses on incomplete answers.