controlled-study

Tag

Cards List
#controlled-study

When Does Explicit View Routing Work? A Controlled Study of Multi-View Graph-Text Alignment

arXiv cs.LG · 2026-07-31 Cached

This paper presents a controlled study of multi-view graph-text alignment, using causal derangement tests on molecular datasets (BBBP, BACE) to determine when explicit view routing genuinely works. Correct routing improves label and property nDCG, but the evidence is limited to explicit externally grounded routing and does not establish free-form routing or consistent three-view specialization.

0 favorites 0 likes
#controlled-study

A Controlled Study of Attention-Only Transformers

arXiv cs.LG · 2026-07-22 Cached

This paper presents a controlled study comparing attention-only transformers (Simple Attention Networks, SANs) against standard transformers matched for parameters, compute, and depth. It finds that removing feed-forward layers largely closes the performance gap when the freed capacity is reallocated to attention depth, with the remaining deficit attributed to parametric recall.

0 favorites 0 likes
#controlled-study

Moving Alphabet: A Controlled Study of Training Data for Text-to-Video Generation

Hugging Face Daily Papers · 2026-07-21 Cached

This paper introduces Moving Alphabet, a procedural testbed for controlled experiments on how data distribution and caption quality affect text-to-video models, revealing key insights for data curation.

0 favorites 0 likes
#controlled-study

Echo-Memory: A Controlled Study of Memory in Action World Models

Hugging Face Daily Papers · 2026-06-08 Cached

Echo-Memory presents a controlled study of memory mechanisms in action-conditioned world models, revealing that memory structure and capacity significantly impact open-domain return performance beyond replay fidelity. The study introduces a matched evaluation protocol and finds that raw context and state-space recurrence are strong mechanisms.

0 favorites 0 likes
#controlled-study

When Does Complexity Conditioning Help a Frozen Sentence Embedding? A Controlled Study of Per-Sentence and Pair-Level Difficulty Adaptation

arXiv cs.CL · 2026-06-03 Cached

This paper presents a controlled, multi-seed study testing whether adapting frozen sentence embeddings to input difficulty improves performance. It finds that per-sentence complexity conditioning fails, while a pair-level residual gated by a cross-encoder difficulty signal yields consistent gains on semantic similarity tasks.

0 favorites 0 likes
← Back to home

Submit Feedback