arXiv AI
Jul 21
Constrained Path Reasoning: Measuring When Committed Stages Earn Their Cost
arXiv:2607. 17240v1 Announce Type: new Abstract: When does a committed intermediate stage in an LLM reasoning pipeline earn its cost?
LC-Implicit-QAOA: Active-Workspace-Capped Exact Objective-and-Gradient Evaluation for Training over Bounded QUBO Light Cones
arXiv:2608. 05610v1 Announce Type: cross Abstract: QAOA training repeatedly queries an objective and all shared gradients, making exact evaluation a feasibility bottleneck even when QUBO terms have bounded causal cones.
Related stories
arXiv AI
Jun 8
ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
arXiv:2605. 24011v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models exhibit remarkable action generation for embodied intelligence, but their heavy compute make deployment on edge platforms impractical.
arXiv AI
Jun 11
Small Experiments, Cheaper Decisions: A Case Study in Staged Promotion for Micro-Pretraining
arXiv:2606. 11387v1 Announce Type: cross Abstract: Short pretraining runs can reduce experimental cost, but they can also over-promote configurations that only look strong at tiny budgets.
arXiv Machine Learning
Aug 11
When Does Trace-Driven Evaluation Mislead MoE Expert Caching? Replay Semantics, Workload Contamination, and Operating Regimes
arXiv:2608. 07911v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models have outgrown accelerator memory, and offloading expert weights to host memory is now standard.
arXiv Machine Learning
Jul 21
AQKA: Active Quantum Kernel Acquisition Under a Shot Budget
arXiv:2605. 14672v2 Announce Type: replace Abstract: Estimating an $N \times N$ quantum kernel from circuit fidelities requires $\Theta(N^2 S)$ measurement shots, the dominant bottleneck for deployment on near-term hardware.
arXiv AI
Jul 8
Think Before You Grid-Search: Floor-First Triage for LLM Serving
arXiv:2607. 05876v1 Announce Type: cross Abstract: LLM serving optimization typically benchmarks many configurations and reaches for heavy profilers when latency targets are missed.
arXiv AI
Jun 9
How Much Dense Attention is Necessary? Oracle-Guided Sparse Prefill for Full/GQA Layers in Hybrid Long-Context Models
arXiv:2606. 07703v1 Announce Type: cross Abstract: Long-context prefill remains expensive because full/GQA layers still score the historical sequence, even in hybrid models with local, sparse, linear, or recurrent components.
arXiv Machine Learning
Jul 15
VQCSim: When Does Compile-Once Statevector Simulation Beat Generic Quantum Frameworks?
arXiv:2607. 11985v1 Announce Type: cross Abstract: Hybrid quantum-classical machine learning workflows repeatedly evaluate many small parametrized circuits during training and model exploration.
arXiv Machine Learning
Aug 11
Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving
arXiv:2608. 08910v1 Announce Type: cross Abstract: PTQTP decomposes LLM weight matrices into two ternary (trit) planes with two free per-group scales.
arXiv Machine Learning
Aug 11
When Do Task Vectors Interfere? Mapping the Validity Boundaries of Weight-Space Composition
arXiv:2608. 09490v1 Announce Type: new Abstract: Task arithmetic treats fine-tuning displacements as composable directions in weight space, yet it remains unclear when parameter addition reflects predictable changes in model function.
arXiv AI
5d ago
TEMPO: Makespan-Aware Expert-Parallel Load Balancing Across Memory- and Compute-Bound Regimes
arXiv:2608. 13057v1 Announce Type: cross Abstract: In expert-parallel (EP) MoE serving, every layer synchronizes at the slowest GPU.
arXiv AI
Jun 16
Fine-Tuning a 7B Advisor on Free-Tier GPUs: An Adapter-Handoff Recipe and a Synthetic-Data Reliability Caution
arXiv:2504. 15610v4 Announce Type: replace Abstract: Fine-tuning a 7B language model for specialized advising is attractive in resource-constrained settings, but multi-epoch runs routinely exceed the wall-clock limits of the free-tier GPUs (Kaggle, Colab) such users rely on.