Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2609.40287v1 Announce Type: new Abstract: Physics-constrained generative models aim to generate physical fields that match a target distribution and satisfy prescribed constraints. However, enf...
arXiv:2609.40312v1 Announce Type: new Abstract: Lossy compression is widely used in Federated Learning (FL) but is generally treated as an error source, while conventional poisoning defenses inspect...
arXiv:2605.21603v1 Announce Type: cross Abstract: Intra-device parallelism addresses resource under-utilization in ML inference and training by overlapping the execution of operators with different r...
arXiv:2609.38239v1 Announce Type: cross Abstract: A Technical Report: Operating a large language model (LLM) as a service requires more than inference infrastructure: the provider must also defend ag...
arXiv:2609.40159v1 Announce Type: cross Abstract: Sparse triangular solve (SpTRSV) is a fundamental kernel in numerous scientific and engineering applications. However, the data dependencies inherent...
arXiv:2605.06814v2 Announce Type: replace Abstract: Graph neural networks (GNNs) increasingly rely on sophisticated architectures and training procedures to achieve desirable properties such as high...
arXiv:2507.09001v4 Announce Type: replace-cross Abstract: Machine learning (ML) models for electronic structure typically rely on large datasets generated by computationally expensive Kohn-Sham densi...
arXiv:2610.01589v1 Announce Type: new Abstract: Pretrained 3D encoders are typically developed on globally reconstructed scenes expressed in a consistent world coordinate frame, whereas embodied syst...
arXiv:2610.00895v1 Announce Type: cross Abstract: Foundation models remain vulnerable to spurious correlations and ``Clever Hans'' strategies. Explainable machine learning can find and remove such st...
arXiv:2609.34447v2 Announce Type: replace-cross Abstract: On-policy distillation (OPD) is becoming an important component of large language model (LLM) post-training for transferring the reasoning ca...
The paper introduces Hierarchical Hash Retrieval (HHR), a coarse‑to‑fine framework designed to improve hash‑based retrieval for large language models. HHR combines Geometry‑Aware Key Routing (GKR) to redistribute feature magnitudes and prune low‑logit keys, with Learned Hash Projection (LHP) to align Hamming distance with true query‑key relevance for fine‑grained retrieval. Experiments on diverse LLMs and benchmarks show that HHR outperforms existing methods, boosting LongBench scores by 1.10 points and achieving up to 3.30× decoding speedup at 128K context length for Llama‑3.1‑8B‑Instruct.
MOMAT (Mixture of Multiple Atlases) is a hardware‑enhanced safety framework designed to defend quantized large language models (qLLMs) on edge devices against jailbreak attacks. It uses a collection of semantic atlases—each containing harmful or benign sample clusters and policy templates—to perform domain‑localized Retrieval‑Augmented Generation. A lightweight Mixture of Experts detector evaluates top‑k similarity features retrieved by a Compute‑in‑Memory (CiM) accelerated engine, achieving a 4.69 × 10⁶‑fold speedup and a 2.5 × 10⁵‑fold energy reduction compared to DRAM‑based baselines while matching state‑of‑the‑art defense performance.
The paper introduces TALON, a Task‑Adaptive LoRA‑Teacher framework for Few‑Shot Class‑Incremental Learning. TALON assigns a dedicated LoRA‑Teacher to each incremental task, then distills the frozen teachers into a single LoRA‑Student via Ensemble Knowledge Transfer, using a semantic‑guided weighting scheme to reduce forgetting and overfitting. Experiments on four FSCIL benchmarks show that TALON matches or surpasses state‑of‑the‑art accuracy while using up to 33× fewer deployment parameters and cutting inference time by 41.7%.
The paper introduces RATIO, a framework for improving quantized reasoning models by identifying overthinking tokens and applying token-specific penalties. It uses Quantization-aware Reasoning Behavior Analysis to detect problematic tokens and Token-Specific Penalty Determination to assign penalties without extra training. Experiments show RATIO outperforms existing methods, boosting accuracy by up to 9.8 points and shortening chain-of-thought length by up to 51.3%.
The paper introduces a fault‑tolerant budget conservation framework for distributed multi‑agent delegation, where budgets are represented as exclusive escrow credits that traverse a delegation DAG. It details how each branch converts credit into a reservation tied to lineage, epoch, and idempotency, persists a signed dispatch permit, and ensures that uncertain effects remain charged until settlement or retirement. The authors prove properties such as ownership partition, ledger conservation, and at‑most‑once settlement, and validate the mechanism through TLA+ checks, a JavaScript explorer, and crash‑injected SQLite experiments.
ProtoFlow is a new multivariate time series forecasting framework that combines vector‑quantized autoencoding with prototype‑guided flow matching. It maps sequences into a discrete latent space, constructs a structured prior from the learned VQ codebook, and trains a DiT‑based rectified flow to transport samples from this prior to future latent representations conditioned on past observations. By replacing generic Gaussian noise with a learned prototype prior, ProtoFlow eliminates autoregressive rollout mismatch and achieves faster training convergence while delivering superior forecasting performance on benchmark datasets.
The paper presents a billing‑aware neural text‑to‑speech system for serverless CPUs, focusing on minimizing CPU‑seconds and GB‑seconds rather than just throughput or latency. By using request‑sized concurrent inference and a reclaimable instance lifecycle, the system limits per‑request CPU parallelism and releases idle memory while keeping the server process alive. On the Kokoro‑82M benchmark, it achieves 2.71 audio‑seconds per CPU‑second versus 0.89 with ONNX Runtime, cuts cost per audio‑hour from $0.0631 to $0.0153, and reduces idle billed memory from 8.7 GB to 1.33 GB, with faster restoration times.
The paper demonstrates that using a single activation function across all nodes in artificial neural networks imposes hard limits on evolutionary search, particularly for sparse evolved substrates. By evolving per-node activation functions from an 18-function palette, the authors show that oscillatory functions can solve parity problems at all tested scales, while monotonic functions fail beyond the simplest case. The study reveals that the choice of activation functions, beyond topology and weights, critically influences what evolutionary search can achieve, and that heterogeneous assignments discovered via indirect encoding are unlikely to be selected manually.
The paper investigates four ways to grow a classifier—adding a tree level, a hidden unit, a leaf split, and a statistically significant split—under a fixed protocol for tree‑structured and constructive models. It shows that the most natural method of deepening a soft decision tree by duplicating a leaf’s class distribution leaves the gradient of new gates identically zero, preventing learning, and proposes a small random perturbation as a fix. The other three growth decisions each provide a distinct benefit: fitting a new hidden unit to residual error yields a smaller network, splitting the leaf with the largest expected error adds sparsity, and requiring statistical significance before splitting adds no value and reduces accuracy.
DriftOPD is a teacher‑free, rollout‑free framework that performs sequence‑level on‑policy distillation of continuous Vision‑Language‑Action (VLA) action experts. It decomposes the sequence‑level reverse‑KL divergence into a chunk‑level reverse‑KL term and a future‑potential term, optimizing them with a one‑step drifting objective and a Q‑function critic learned from offline demonstrations. Experiments on multiple VLA architectures in simulation and real‑world manipulation show that DriftOPD outperforms existing one‑step distillation baselines while matching the task success of multi‑step teacher policies.