Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.16318 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
When Structure Doesn't Help: LLMs Do Not Read Text-Attributed Graphs as Effectively as We Expected
by: Xu, Haotian, et al.
Published: (2025)
by: Xu, Haotian, et al.
Published: (2025)
When More Data Doesn't Help: Limits of Adaptation in Multitask Learning
by: Hanneke, Steve, et al.
Published: (2026)
by: Hanneke, Steve, et al.
Published: (2026)
Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't
by: Dang, Quy-Anh, et al.
Published: (2025)
by: Dang, Quy-Anh, et al.
Published: (2025)
Explorations of the Softmax Space: Knowing When the Neural Network Doesn't Know
by: Sikar, Daniel, et al.
Published: (2025)
by: Sikar, Daniel, et al.
Published: (2025)
Active Learning Works! Until It Doesn't: Measuring the Effectiveness of Activity-Based Learning Exercises on Information Anxiety
by: Halpern, Rebecca
Published: (2016)
by: Halpern, Rebecca
Published: (2016)
REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
by: Wang, Ziqiao, et al.
Published: (2025)
by: Wang, Ziqiao, et al.
Published: (2025)
Infinite Width Models That Work: Why Feature Learning Doesn't Matter as Much as You Think
by: Sernau, Luke
Published: (2024)
by: Sernau, Luke
Published: (2024)
A Particle-Flow Algorithm for Free-Support Wasserstein Barycenters
by: You, Kisung
Published: (2025)
by: You, Kisung
Published: (2025)
Scale-Calibrated Median-of-Means for Robust Distributed Principal Component Analysis
by: You, Kisung
Published: (2026)
by: You, Kisung
Published: (2026)
Constant Metric Scaling in Riemannian Computation
by: You, Kisung
Published: (2026)
by: You, Kisung
Published: (2026)
Recurrent Off-Policy Deep Reinforcement Learning Doesn't Have to be Slow
by: Clark, Tyler, et al.
Published: (2025)
by: Clark, Tyler, et al.
Published: (2025)
Library Learning Doesn't: The Curious Case of the Single-Use "Library"
by: Berlot-Attwell, Ian, et al.
Published: (2024)
by: Berlot-Attwell, Ian, et al.
Published: (2024)
Intrinsic effective sample size for manifold-valued Markov chain Monte Carlo via kernel discrepancy
by: You, Kisung
Published: (2026)
by: You, Kisung
Published: (2026)
Why Prompt Optimization Works, and Why It Sometimes Doesn't: A Causal-Inspired Edit-Level Analysis
by: Gong, Shuzhi, et al.
Published: (2026)
by: Gong, Shuzhi, et al.
Published: (2026)
A Critical Look at Targeted Instruction Selection: Disentangling What Matters (and What Doesn't)
by: Nayak, Nihal V., et al.
Published: (2026)
by: Nayak, Nihal V., et al.
Published: (2026)
PCA, SVD, and Centering of Data
by: Kim, Donggun, et al.
Published: (2023)
by: Kim, Donggun, et al.
Published: (2023)
Quotient-Based Posterior Analysis for Euclidean Latent Space Models
by: You, Kisung, et al.
Published: (2026)
by: You, Kisung, et al.
Published: (2026)
Is Cosine-Similarity of Embeddings Really About Similarity?
by: Steck, Harald, et al.
Published: (2024)
by: Steck, Harald, et al.
Published: (2024)
The Hidden Pitfalls of the Cosine Similarity Loss
by: Draganov, Andrew, et al.
Published: (2024)
by: Draganov, Andrew, et al.
Published: (2024)
One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs
by: He, Di, et al.
Published: (2026)
by: He, Di, et al.
Published: (2026)
Variance-Adjusted Cosine Distance as Similarity Metric
by: Sahoo, Satyajeet, et al.
Published: (2025)
by: Sahoo, Satyajeet, et al.
Published: (2025)
Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences
by: Falahati, Ali, et al.
Published: (2026)
by: Falahati, Ali, et al.
Published: (2026)
Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
by: Cooper, A. Feder, et al.
Published: (2024)
by: Cooper, A. Feder, et al.
Published: (2024)
Chapter When It Doesn't Go to Plan
by: Kim, Seoyeon | https://orcid.org/0000-0002-2018-9520, et al.
Published: (2026)
by: Kim, Seoyeon | https://orcid.org/0000-0002-2018-9520, et al.
Published: (2026)
Network Distance Based on Laplacian Flows on Graphs
by: Bao, Dianbin, et al.
Published: (2018)
by: Bao, Dianbin, et al.
Published: (2018)
In Defense of Cosine Similarity: Normalization Eliminates the Gauge Freedom
by: Bouhsine, Taha
Published: (2026)
by: Bouhsine, Taha
Published: (2026)
Learning over von Mises-Fisher Distributions via a Wasserstein-like Geometry
by: You, Kisung, et al.
Published: (2025)
by: You, Kisung, et al.
Published: (2025)
The Usual Doesn't Work: Why We Need Problem-Based Learning
by: Spence, Larry
Published: (2004)
by: Spence, Larry
Published: (2004)
MedCalc-Bench Doesn't Measure What You Think: A Benchmark Audit and the Case for Open-Book Evaluation
by: Krohn-Grimberghe, Artus
Published: (2026)
by: Krohn-Grimberghe, Artus
Published: (2026)
Scalable Geometric Learning with Correlation-Based Functional Brain Networks
by: You, Kisung, et al.
Published: (2025)
by: You, Kisung, et al.
Published: (2025)
Gamma Mixture Modeling for Cosine Similarity in Small Language Models
by: Player, Kevin
Published: (2025)
by: Player, Kevin
Published: (2025)
Revisiting Intermediate-Layer Matching in Knowledge Distillation: Layer-Selection Strategy Doesn't Matter (Much)
by: Yu, Zony, et al.
Published: (2025)
by: Yu, Zony, et al.
Published: (2025)
When the Conversation Doesn't Go Your Way
Published: (2024)
Published: (2024)
Outlier Detection Using Vector Cosine Similarity by Adding a Dimension
by: Shen, Zhongyang
Published: (2025)
by: Shen, Zhongyang
Published: (2025)
Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism
by: Zhang, Haoxiang, et al.
Published: (2026)
by: Zhang, Haoxiang, et al.
Published: (2026)
Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax Dies
by: Liu, Ming
Published: (2026)
by: Liu, Ming
Published: (2026)
CosineGate: Semantic Dynamic Routing via Cosine Incompatibility in Residual Networks
by: Thota, Yogeswar Reddy
Published: (2025)
by: Thota, Yogeswar Reddy
Published: (2025)
SAVGO: Learning State-Action Value Geometry with Cosine Similarity for Continuous Control
by: Orfanoudakis, Stavros, et al.
Published: (2026)
by: Orfanoudakis, Stavros, et al.
Published: (2026)
Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity
by: Hinostroza, Cristian, et al.
Published: (2026)
by: Hinostroza, Cristian, et al.
Published: (2026)
Surpassing Cosine Similarity for Multidimensional Comparisons: Dimension Insensitive Euclidean Metric
by: Tessari, Federico, et al.
Published: (2024)
by: Tessari, Federico, et al.
Published: (2024)