arXiv subjects

Nitzan Hodos

Publications and source records attributed to Nitzan Hodos.

6 recordsLinked to original sources

arXiv2026

AnchorKV: Anchor-Residual KV Cache Compression

The key-value (KV) cache is the primary memory bottleneck in long-context LLM inference. Existing approaches attack it from opposite ends: eviction methods permanently discard tokens, degrading performance whenever a discarded token later proves essential, while quantization methods retain all tokens at low precision but offer limited compression. We propose AnchorKV, a compression scheme that shrinks the cache by $20\times$ without discarding a single token. AnchorKV represents the cache using a small set of anchors stored exactly, expresses every other token through its most similar anchor, and refines only those whose approximation most affects the model's output. AnchorKV consistently preserves accuracy across models and datasets, retaining 99% of the full-cache score at the 70B scale, while keeping the entire context at a fraction of its cost.

cs.LG↗

arXiv2026

MACRO: Training-free Multi-plane Attention for Closeup Render Optimization

Close-up rendering, zooming into a scene well beyond any training camera, is important for virtual production and interactive 3D content, yet remains an open challenge. 3D Gaussian splatting (3DGS) enables high-fidelity, real-time novel view synthesis, but its rendering quality degrades at close range. Recent diffusion-based methods that enhance the rendering by conditioning on reference images from the training set produce significant artifacts in this setting. We analyze this failure and identify its root cause: the scale gap between the close-up and reference views. We show that the features in reference-conditioned enhancement models are not scale-invariant, causing cross-view attention to retrieve incorrect correspondences when the same content appears at different scales, and that this mismatch cannot be corrected in latent space because the VAE encoder is not scale-equivariant. Building on this analysis we introduce MACRO, Multi-plane Attention for Closeup Render Optimization, a training-free method for high-quality close-up novel view synthesis from 3DGS. MACRO resolves the scale gap by leveraging the scene's known 3D structure: it decomposes the close-up into depth planes, crops and resizes references in image space to match the scale of each plane before encoding, and applies a depth-aware attention mask so each token attends only to scale-matched references. The method requires no architectural changes or additional training. We further contribute two new close-up novel view synthesis benchmarks, the first standardized evaluation protocol for this setting, and demonstrate state-of-the-art results on both, outperforming existing 3DGS and diffusion-based methods on both reconstruction and perceptual metrics. Project page: https://nitzanhod.github.io/MACRO

cs.CV↗

arXiv2025

QKV Projections Require a Fraction of Their Memory

The Multi-Head Attention mechanism is central to LLM operation, and multiple works target its compute and memory efficiency during training. While most works focus on approximating the scaled dot product, the memory consumption of the linear projections that compute the $Q$, $K$, and $V$ tensors from the input $x$ is often overlooked. To address this, we propose Point-Approximate Matrix Multiplication (PAMM), a novel tensor compression technique that compresses the activations of the $Q,K,V$ projections in attention layers by a factor of up to $\times 512$, effectively erasing their memory footprint, while achieving similar or better final perplexity. PAMM is fully composable with efficient attention techniques such as FlashAttention, making it a practical and complementary method for memory-efficient LLM training.

cs.LG↗

arXiv2025

CompAct: Compressed Activations for Memory-Efficient LLM Training

We introduce CompAct, a technique that reduces peak memory utilization on GPU by 25-30% for pretraining and 50% for fine-tuning of LLMs. Peak device memory is a major limiting factor in training LLMs, with various recent works aiming to reduce model memory. However most works don't target the largest component of allocated memory during training: the model's compute graph, which is stored for the backward pass. By storing low-rank, compressed activations to be used in the backward pass we greatly reduce the required memory, unlike previous methods which only reduce optimizer overheads or the number of trained parameters. Our compression uses random projection matrices, thus avoiding additional memory overheads. Comparisons with previous techniques for either pretraining or fine-tuning show that CompAct substantially improves existing compute-performance tradeoffs. We expect CompAct's savings to scale even higher for larger models.

cs.LG↗

arXiv2024

DNCs Require More Planning Steps

Many recent works use machine learning models to solve various complex algorithmic problems. However, these models attempt to reach a solution without considering the problem's required computational complexity, which can be detrimental to their ability to solve it correctly. In this work we investigate the effect of computational time and memory on generalization of implicit algorithmic solvers. To do so, we focus on the Differentiable Neural Computer (DNC), a general problem solver that also lets us reason directly about its usage of time and memory. In this work, we argue that the number of planning steps the model is allowed to take, which we call "planning budget", is a constraint that can cause the model to generalize poorly and hurt its ability to fully utilize its external memory. We evaluate our method on Graph Shortest Path, Convex Hull, Graph MinCut and Associative Recall, and show how the planning budget can drastically change the behavior of the learned algorithm, in terms of learned time complexity, training time, stability and generalization to inputs larger than those seen during training.

cs.LG↗

arXiv2022

Coin Flipping Neural Networks

We show that neural networks with access to randomness can outperform deterministic networks by using amplification. We call such networks Coin-Flipping Neural Networks, or CFNNs. We show that a CFNN can approximate the indicator of a $d$-dimensional ball to arbitrary accuracy with only 2 layers and $\mathcal{O}(1)$ neurons, where a 2-layer deterministic network was shown to require $Ω(e^d)$ neurons, an exponential improvement (arXiv:1610.09887). We prove a highly non-trivial result, that for almost any classification problem, there exists a trivially simple network that solves it given a sufficiently powerful generator for the network's weights. Combining these results we conjecture that for most classification problems, there is a CFNN which solves them with higher accuracy or fewer neurons than any deterministic network. Finally, we verify our proofs experimentally using novel CFNN architectures on CIFAR10 and CIFAR100, reaching an improvement of 9.25\% from the baseline.

cs.LG↗