{"total":19,"rows":[{"id":"2510.10618","title":"Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization","created":"2025-10-12","cited_by_count":9,"area":null},{"id":"2510.15304","title":"Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation","created":"2025-10-17","cited_by_count":6,"area":null},{"id":"2608.10837","title":"TACTICL: Task-Aware Compression of Tabular ICL Models","created":"2026-08-11","cited_by_count":4,"area":null},{"id":"2510.05064","title":"Boomerang Distillation Enables Zero-Shot Model Size Interpolation","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2602.08858","title":"FlattenGPT: Depth Compression for Transformer with Layer Flattening","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2605.15491","title":"Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2603.08083","title":"High-Fidelity Pruning for Large Language Models","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2506.00932","title":"Addressing the Collaboration Dilemma in Low-Data Federated Learning via Transient Sparsity","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2506.05641","title":"Projectable Models: One-Shot Generation of Small Specialized Transformers from Large Ones","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2509.06836","title":"COMPACT: Common-token Optimized Model Pruning Across Channels and Tokens","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2602.06127","title":"Compressing LLMs with MoP: Mixture of Pruners","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2605.25344","title":"A Hamiltonian-Inspired Local-Operator Ansatz for Slimming Large Language Models","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2608.12953","title":"Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.02083","title":"XMerge: Cross-Axis Selection and Reconstructive Layer Merging for LLM Depth Compression","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.09883","title":"Forward-Free LLM Depth Pruning via Weight Redundancy","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.36842","title":"Does the VGGT Family Need All Its Layers?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.06026","title":"Differentiable Bit-Widths: Co-optimizing Pruning and Quantization via SVD for Ultra-Efficient LLM Compression","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.14413","title":"Coarse-Graining Recursive Expert Computation: Continuation-Relative Interfaces and Failure Modes","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.15159","title":"Beyond Adjacent Layers: Graph-Guided Layer Fusion for Compressing Large Language Models","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}