CART: Context-Anchored Recurrent Transformer -- A Parameter-Efficient Architecture with Learned Stability

• URL: http://arxiv.org/abs/2606.01495v2
• Date: Wed, 03 Jun 2026 00:14:38 GMT
• Title: CART: Context-Anchored Recurrent Transformer -- A Parameter-Efficient Architecture with Learned Stability
• Abstract summary: CART (Context-Anchored Recurrent Transformer) is a parameter-efficient language model that reuses a single shared core block R times across depth.<n>We evaluate CART on single consumer GPUs in two stages: a 64-configuration screen at 3,000 steps, then 36 configurations (P=6, R in 6,8,10, three seeds) trained for 30,500 steps (1B tokens)<n>Two patterns hold across widths d in 256,512,768,1024: prelude depth P dominates loop count R, and the Stage-1 ranking of R reverses at full training (R=6 becomes best at
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present CART (Context-Anchored Recurrent Transformer), a parameter-efficient language model that reuses a single shared core block R times across depth. Unlike prior looped transformers that recompute key-value tensors at every iteration, CART computes K and V once from a multi-layer prelude and has the recurrent core cross-attend to those frozen tensors via multi-head latent attention. A learned Linear Time-Invariant (LTI) gate keeps the recurrence stable: its spectral radius settles in a narrow band (rho in [0.79, 0.83]) across all 36 fully-trained configurations. We evaluate CART on single consumer GPUs in two stages: a 64-configuration screen at 3,000 steps, then 36 configurations (P=6, R in {6,8,10}, three seeds) trained for 30,500 steps (~1B tokens). Two patterns hold across widths d in {256,512,768,1024}: prelude depth P dominates loop count R, and the Stage-1 ranking of R reverses at full training (R=6 becomes best at d>=512). At the binding d=1024 parameter-parity test, CART does not beat a parameter-matched dense baseline, losing by 1-2% at stored-parameter parity and by ~10% at effective-parameter parity. Diagnostic ablations split the effective-parameter gap into ~5% from weight sharing and a residual ~5% from the heterogeneous prelude/anchor/core/coda framing; the recurrent-core machinery (hyper-connections, LTI gate, loop-index embedding) is individually vestigial. Variable-R inference degrades on both sides of the trained R, a negative result for test-time depth scaling under this recipe.

Related papers

• A Multi-Dimensional, Per-Pass Empirical Study of the LLVM Optimization Pipeline [5.6148382426295305]
  We present a systematic, empirical study of the LLVM -O3 optimization pipeline.<n>We measure execution time, compile time, binary size, hardware counters, and RAPL energy across 84,750 measurements.<n>These findings enable more informed pass pruning, cost-model calibration, and autotuning.
  arXiv  Detail & Related papers  (2026-06-30T07:10:48Z)
• CLEAR-MoE: Shared-Basis Expert Extraction from Frozen Vision Transformers via Calibration-Driven Layer Selection [0.0]
  CLEAR-MoE is a post-training pipeline that converts a frozen pretrained Vision Transformer (ViT) into a sparse Mixture-of-Experts (MoE) model without updating backbone weights.<n>On a GTX 960, routing and scatter-gather overhead make the CLEAR-MoE FFN 1.3-1.7x slower than the dense routers.
  arXiv  Detail & Related papers  (2026-06-26T18:12:03Z)
• Closed-Form Spectral Regularization for Multi-Task Model Merging [96.82449201305234]
  Model merging combines several independently fine-tuned experts into a single multi-task model without any training data.<n>State-of-the-art merging methods formulate merging as a layer-wise interference problem.<n>We propose SWUDI, a closed-form method that combines a soft exponential filter, which matches the gradient-flow trajectory of iterative descent.
  arXiv  Detail & Related papers  (2026-06-05T14:00:47Z)
• Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders [123.58723804218151]
  Vision foundation models are bottlenecked by the quadratic cost of self-attention.<n>We present C-GSPN based on 2D spatial propagation propagation.
  arXiv  Detail & Related papers  (2026-05-30T14:29:43Z)
• Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior [107.2098567818173]
  Latent Recurrent Transformer (LRT) is a lightweight augmentation of autoregressive transformers.<n>LRT reuses a high-level source-layer hidden state from the previous token as recurrent memory for the next token.
  arXiv  Detail & Related papers  (2026-05-26T10:10:26Z)
• RD-ViT: Recurrent-Depth Vision Transformer for Semantic Segmentation with Reduced Data Dependence Extending the Recurrent-Depth Transformer Architecture to Dense Prediction [2.8222472653971917]
  Vision Transformers (ViTs) achieve state-of-the-art segmentation accuracy but require large training datasets.<n>We present RD-ViT, a Recurrent-Depth Vision Transformer that adapts the Recurrent-Depth Transformer architecture to dense prediction tasks.<n> RD-ViT replaces the deep stack of unique transformer blocks with a single shared block looped T times, augmented with LTI-stable state injection for guaranteed convergence.
  arXiv  Detail & Related papers  (2026-05-05T17:21:18Z)
• Scaling DoRA: High-Rank Adaptation via Factored Norms and Fused Kernels [83.99688944263843]
  Weight-De Low-Rank Adaptation (DoRA) extends LoRA by decoupling weight magnitude from direction.<n>At d_in = 8192 and rank r = 384, a single module's norm requires about 512 MB of transient working memory in bf16.<n>A factored norm decomposes the squared norm into base, cross, and Gram terms computable through O(d_out r + r2) intermediates, eliminating the dense product.
  arXiv  Detail & Related papers  (2026-03-23T17:57:24Z)
• MLPMoE: Zero-Shot Architectural Metamorphosis of Dense LLM MLPs into Static Mixture-of-Experts [0.0]
  Large Language Models (LLMs) are predominantly deployed as dense transformers, where every parameter in every feed-forward block is activated for every token.<n>Recent upcycling methods such as MoEfication, CMoE, ToMoE, and MoORE reveal that much of the useful computation lives in sparse, semi-modular substructures inside dense feed-forward networks.<n>This paper introducesMoE (MLP-Experts), a training-free transformation that restructures the dense in transformer blocks into a static, high-cardinality mixture of experts.
  arXiv  Detail & Related papers  (2025-11-26T06:14:26Z)
• Temporal Zoom Networks: Distance Regression and Continuous Depth for Efficient Action Localization [6.908972852063454]
  Temporal action localization requires both precise boundary detection and computational efficiency.<n>We address this through two complementary innovations: Boundary Distance Regression (BDR) and Adaptive Temporal Refinement (ATR)<n>On THUMOS14, our method achieves 56.5% mAP@0.7 with 151G FLOPs, using 36% fewer FLOPs than ActionFormer++ (55.7% mAP@0.7 at 235G)
  arXiv  Detail & Related papers  (2025-11-06T00:41:54Z)
• DeepPrune: Parallel Scaling without Inter-trace Redundancy [53.62015294143274]
  Over 80% of parallel reasoning traces yield identical final answers, representing substantial wasted computation.<n>We propose DeepPrune, a novel framework that enables efficient parallel scaling through dynamic pruning.<n>Our work establishes a new standard for efficient parallel reasoning, making high-performance reasoning more efficient.
  arXiv  Detail & Related papers  (2025-10-09T17:24:54Z)
• Tensor Decomposition Networks for Fast Machine Learning Interatomic Potential Computations [48.46721044282335]
  tensor decomposition networks (TDNs) achieve competitive performance with dramatic speedup in computations.<n>We evaluate TDNs on PubChemQCR, a newly curated molecular relaxation dataset containing 105 million DFT-calculated snapshots.<n>Results show that TDNs achieve competitive performance with dramatic speedup in computations.
  arXiv  Detail & Related papers  (2025-07-01T18:46:27Z)
• Speedy MASt3R [68.47052557089631]
  MASt3R redefines image matching as a 3D task by leveraging DUSt3R and introducing a fast reciprocal matching scheme.<n>Fast MASt3R achieves a 54% reduction in inference time (198 ms to 91 ms per image pair) without sacrificing accuracy.<n>This advancement enables real-time 3D understanding, benefiting applications like mixed reality navigation and large-scale 3D scene reconstruction.
  arXiv  Detail & Related papers  (2025-03-13T03:56:22Z)
• Scaling Up 3D Kernels with Bayesian Frequency Re-parameterization for Medical Image Segmentation [25.62587471067468]
  RepUX-Net is a pure CNN architecture with a simple large kernel block design. Inspired by the spatial frequency in the human visual system, we extend to vary the kernel convergence into element-wise setting.
  arXiv  Detail & Related papers  (2023-03-10T08:38:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.