mlsanityData to 7 Oct 2026

T3C: Test-Time Tensor Compression with Consistency Guarantees

arXiv 2601.01299 ↗First posted 3 Jan 2026cs.CL cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We present T3C, a train-once, test-time budget-conditioned compression framework that exposes rank and precision as a controllable deployment knob. T3C combines elastic tensor factorization (maintained up to a maximal rank) with rank-tied mixed-precision quantization and a lightweight controller that maps a latency/energy/size budget token to per-layer rank/bit assignments; the policy snaps to hardware-aligned profiles and is monotone in the budget. A fast, layerwise consistency certificate, computed from spectral proxies and activation statistics, upper-bounds logit drift and regularizes training, yielding a practical reliability signal with negligible overhead. On ImageNet-1k, T3C shifts the vision Pareto frontier: for ResNet-50 at matched accuracy (≤ 0.5% drop), p50 latency is 1.18ms with a 38MB model, outperforming PTQ-8b (1.44ms, 88MB); for ViT-B/16, T3C reaches 2.30ms p50 with 59MB, improving over strong PTQ/QAT baselines. A single T3C checkpoint therefore provides predictable, certificate-backed accuracy-latency-size trade-offs on demand across devices.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 74 of its 96 references that are in the map. First posted on arXiv 3 Jan 2026.

Builds on

74 of 96 references.

References · 74

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  7. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  8. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  9. 2022A ConvNet for the 2020scited by 3,545
  10. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  11. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  12. 2016Pointer Sentinel Mixture Modelscited by 2,992
38 more
  1. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  2. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  3. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  4. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  5. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  6. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,838
  7. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  8. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  9. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,338
  10. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  11. 2023SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shotcited by 1,090
  12. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 881
  13. 2021DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsificationcited by 849
  14. 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 802
  15. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  16. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  17. 2019Learned Step Size Quantizationcited by 604
  18. 2024TinyLlama: An Open-Source Small Language Modelcited by 604
  19. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 600
  20. 2017Learning Sparse Neural Networks through L0 Regularizationcited by 571
  21. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  22. 2019Rigging the Lottery: Making All Tickets Winnerscited by 491
  23. 2016Adaptive Computation Time for Recurrent Neural Networkscited by 479
  24. 2019The State of Sparsity in Deep Neural Networkscited by 471
  25. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 464
  26. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 456
  27. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 439
  28. 2017ThiNet: A Filter Level Pruning Method for Deep Neural Network Compressioncited by 438
  29. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 426
  30. 2020Movement Pruning: Adaptive Sparsity by Fine-Tuningcited by 398
  31. 2019HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precisioncited by 387
  32. 2017SkipNet: Learning Dynamic Routing in Convolutional Networkscited by 328
  33. 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 328
  34. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 322
  35. 2014Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluationcited by 304
  36. 2018Slimmable Neural Networkscited by 301
  37. 2014Speeding up Convolutional Neural Networks with Low Rank Expansionscited by 283
  38. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 254

50 most cited of 74 All 74 (JSON)

Built on by

Not cited yet.