PatternGSL introduces a learnable specification language for sewing patterns that lets vision-language models reconstruct explicit, simulation-ready 3D garments from single images, backed by a new 300K paired dataset.
Journal of Machine Learning Research , volume=
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
representative citing papers
Zero-shot time series foundation models largely fail to beat econometric benchmarks for realized volatility forecasting, with only TTM achieving a narrow, calibration-driven edge.
Coverage-aware pruning using per-corpus utility profiles on WikiText2 and C4 improves zero-shot accuracy and reduces perplexity degradation in two MoE models at 25-75% retention compared to baselines, without downstream data.
E-PMQ improves 4-bit quantization accuracy on merged models by 8-42 points across CLIP and GLUE tasks through expert-guided calibration and merged-weight anchoring.
Orth-Dion uses QR factorization on the right factor instead of column normalization to eliminate the geometric mismatch in low-rank approximations of spectral optimizers like Muon, achieving O(sqrt(L_r/T)) rate under non-Euclidean smoothness.
ART automatically generates multi-step reasoning programs with tool integration for LLMs, yielding substantial gains over few-shot and auto-CoT prompting on BigBench and MMLU while matching hand-crafted CoT on most tasks.
GSRQ applies a gain-shape variant of K-means inside residual quantization to improve directional fidelity, raising LongBench accuracy from 11.34 to 33.54 at 1-bit on LLaMA-3-8B.
Few-step deterministic maps on continuous text latents fail because they cannot resolve discrete branch choices before sharp categorical readouts, with failure governed by decoder sharpness rather than transport accuracy.
QREAM rewrites documents to question-focused style using iterative ICL and distilled FT models, boosting RAG performance by up to 8% relative improvement.
LLM-based POS tagging outperforms traditional taggers on medieval Occitan, Catalan, and French, with fine-tuning and cross-lingual transfer providing the largest gains for under-resourced varieties.
citing papers explorer
-
PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments
PatternGSL introduces a learnable specification language for sewing patterns that lets vision-language models reconstruct explicit, simulation-ready 3D garments from single images, backed by a new 300K paired dataset.
-
Forecasting Realized Volatility with Time Series Foundation Models: A Comparison with Econometric Benchmarks
Zero-shot time series foundation models largely fail to beat econometric benchmarks for realized volatility forecasting, with only TTM achieving a narrow, calibration-driven edge.
-
Generic Expert Coverage for Pruning SparseMixture-of-Experts Language Models
Coverage-aware pruning using per-corpus utility profiles on WikiText2 and C4 improves zero-shot accuracy and reduces perplexity degradation in two MoE models at 25-75% retention compared to baselines, without downstream data.
-
E-PMQ: Expert-Guided Post-Merge Quantization with Merged-Weight Anchoring
E-PMQ improves 4-bit quantization accuracy on merged models by 8-42 points across CLIP and GLUE tasks through expert-guided calibration and merged-weight anchoring.
-
Orth-Dion: Eliminating Geometric Mismatch in Distributed Low-Rank Spectral Optimization
Orth-Dion uses QR factorization on the right factor instead of column normalization to eliminate the geometric mismatch in low-rank approximations of spectral optimizers like Muon, achieving O(sqrt(L_r/T)) rate under non-Euclidean smoothness.
-
ART: Automatic multi-step reasoning and tool-use for large language models
ART automatically generates multi-step reasoning programs with tool integration for LLMs, yielding substantial gains over few-shot and auto-CoT prompting on BigBench and MMLU while matching hand-crafted CoT on most tasks.
-
GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache
GSRQ applies a gain-shape variant of K-means inside residual quantization to improve directional fidelity, raising LongBench accuracy from 11.34 to 33.54 at 1-bit on LLaMA-3-8B.
-
Why Do Few-Step Text Latents Fail When Image Latents Work? Non-Commitment at Sharp Categorical Readouts
Few-step deterministic maps on continuous text latents fail because they cannot resolve discrete branch choices before sharp categorical readouts, with failure governed by decoder sharpness rather than transport accuracy.
-
Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation
QREAM rewrites documents to question-focused style using iterative ICL and distilled FT models, boosting RAG performance by up to 8% relative improvement.
-
From Traditional Taggers to LLMs: A Comparative Study of POS Tagging for Medieval Romance Languages
LLM-based POS tagging outperforms traditional taggers on medieval Occitan, Catalan, and French, with fine-tuning and cross-lingual transfer providing the largest gains for under-resourced varieties.
- FishBack: Pullback Fisher Geometry for Optimal Activation Steering in Transformers
- Lessons from the Trenches on Reproducible Evaluation of Language Models