Chun Deng, Hui Sub Shim, Evan Laufer, Anna Eaton, David Tennenhouse, Tsachy Weissman, Philip Levis
Server main memory is increasingly heterogeneous, incorporating technologies such as zswap, CXL memory expanders, and emerging phase-change memories (PCM). To decide where to place pages, operating systems have to choose between efficient but coarse-grained access bits, out-of-band profiling, or costly runtime instrumentation. This paper proposes memory fit, a hardware abstraction that provides precise and accurate page placement information to an operating system. Memory fit measures how well a page "fits" each type of memory in the system. Memory fit separates the mechanism of measuring affinity between pages and memories from the OS policy of choosing which pages to move when. The paper describes soft trace matching (STM), a computationally and space efficient algorithm to compute memory fit. The key technical insight behind STM is that it can estimate memory fit by comparing accesses to a page with a learned model of "good" traces for a memory. We have implemented memory fit and STM in a BOOMv3 RISC-V processor running Linux 6.6. On extended GUPS, memory fit placements recover 2.2-3.8 times as much of the performance gap to optimal placement as Linux TPP. For Redis with equal DRAM and PCM capacities, placements selected by memory fit recover 80% of the performance gap, versus 19% for TPP, in a placement replay. Memory fit requires only 64 bits of state per 4 KiB page and can be updated on every main-memory access with only a 1.2% overhead of OS kernel notification processing.
Jiacheng Cen, Anyi Li, Ning Lin, Zihe Wang, Ji-Rong Wen, Wenbing Huang
Symmetry governs the organization of physical structures, while symmetry breaking reveals their transformations. In geometric deep learning, symmetry imposes rank constraints on equivariant representations, limiting the expressive capacity of equivariant graph neural networks (GNNs). Here we show that these constraints can instead be exploited: the singular-value spectra of equivariant representations provide a unified fingerprint of structural symmetry. We introduce spectral symmetry fingerprints (SymFP), which enable discrete point-group identification through rank-template matching and continuous symmetry analysis by quantifying spectral energy beyond target rank constraints. SymFP is orientation invariant and architecture agnostic, enabling a parameter-free GNN implementation. Its spectra can be reused across multiple target groups, and the resulting leakage scores satisfy subgroup monotonicity. Across synthetic structures, molecules, coordination complexes and large biological assemblies, SymFP accurately identifies point groups, tracks controlled symmetry breaking and reveals local and degree-resolved symmetry changes that can be obscured by global geometric measures. These results establish the spectral structure of equivariant representations as a general framework for characterizing symmetry across physical systems.
Merging finetuned Large Language Models (LLMs) has become increasingly important for integrating diverse capabilities into a single unified model. However, prevailing model merging methods rely on linear arithmetic in Euclidean space, which often destroys the intrinsic geometric properties of pretrained weights, such as hyperspherical energy. To address this, we propose Orthogonal Model Merging (OrthoMerge), a method that performs merging operations on the Riemannian manifold formed by the orthogonal group to preserve the geometric structure of the model's weights. By mapping task-specific orthogonal matrices learned by Orthogonal Finetuning (OFT) to the Lie algebra, OrthoMerge enables a principled yet efficient integration that takes into account both the direction and intensity of adaptations. In addition to directly leveraging orthogonal matrices obtained by OFT, we further extend this approach to general models finetuned with non-OFT methods (i.e., low-rank finetuning, full finetuning) via an Orthogonal-Residual Decoupling strategy. This technique extracts the orthogonal components of expert models by solving the orthogonal Procrustes problem, which are then merged on the manifold of the orthogonal group, while the remaining linear residuals are processed through standard additive merging. Extensive empirical results demonstrate the effectiveness of OrthoMerge in mitigating catastrophic forgetting and maintaining model performance across diverse tasks.
Two candidate approaches for univariate sumcheck over roots of unity are presented. The first takes the form of a multilinear evaluation protocol, which can be combined with the standard multivariate sumcheck protocol. The other consists of a direct reduction from univariate sumcheck to multilinear evaluation, which can be combined with Gemini (Bootle et al., Eurocrypt 2022). Optionally, natural round reductions from $m$ to $\log(m)$ are supported, while retaining linear prover time.
Neehal Tumma, Philipp Nazari, Rohan Cherukuri, Daniela Rus, T. Konstantin Rusch
Linear recurrences are emerging as practical alternatives to softmax attention in large language models, appearing in both standalone and hybrid architectures. However, despite their rapid emergence, low-precision inference remains much less developed for these models than for softmax attention. During prefill, chunkwise-parallel algorithms cast much of the recurrence as dense matrix multiplications, suggesting a natural path to low-precision execution. Simply quantizing these operations in their native form, however, can be fragile. In this work, we identify functional invariances that preserve the full-precision computation while making the operands more amenable to quantization. Building on this observation, we introduce LinQuant, a framework for low-precision recurrent prefill based on seven such invariances, including rotations, diagonal rescalings, and alternative placements of recurrent decay and write factors. We derive when these transformations remain valid across common recurrence families spanning linear, gated, and delta-rule updates, and show that they provide complementary degrees of freedom for improving low-precision accuracy. Finally, we translate this framework to production by augmenting SSDi8, an existing low-precision prefill pipeline for Mamba-2, with the applicable invariances. LinQuant improves perplexity at matched latency on Mamba-2 1.3B, 2.7B, and 8B and Nemotron-H 8B, demonstrating the practical utility of invariance-based quantization for recurrent models.
Self-Organizing Maps (SOM) are a classical method for unsupervised learning, vector quantization, and topographic mapping of high-dimensional data. However, existing SOM formulations often involve a trade-off between computational efficiency and a clearly defined optimization objective. Objective-based variants such as Soft Topographic Vector Quantization (STVQ) provide a principled formulation, but their neighborhood-coupled computations become expensive as the number of latent nodes increases. In this paper, we propose Self-Organizing Maps with Optimized Latent Positions (SOM-OLP), an objective-based topographic mapping method that introduces a continuous latent position for each data point. Starting from the neighborhood distortion of STVQ, we construct a separable surrogate local cost based on its local quadratic structure and formulate an entropy-regularized objective based on it. This yields a simple block coordinate descent scheme with closed-form updates for assignment probabilities, latent positions, and reference vectors, while guaranteeing monotonic non-increase of the objective and retaining linear per-iteration complexity in the numbers of data points and latent nodes. Experiments on a synthetic saddle manifold, scalability studies on the Digits and MNIST datasets, and 16 benchmark datasets show that SOM-OLP achieves competitive neighborhood preservation and quantization performance, favorable scalability for large numbers of latent nodes and large datasets, and the best average rank among the compared methods on the benchmark datasets.
Valuing player actions in football, a complex multi-agent system, requires accounting for strategic interactions among 22 players, including off-ball movements and defensive positioning. Existing reinforcement-learning-based valuation methods commonly incorporate other players through the observed state while retaining independent-agent value formulations. To our knowledge, we introduce the first Markov perfect equilibrium (MPE)-inspired framework for valuing the actions of all 22 players using real football tracking and event data, formulating each possession as a finite-horizon multi-agent dynamic game. To improve interpretability, the framework uses Expandable Decision-Making States (EDMS) and decomposes each Q-value into a successor-feature basis and a linear reward-weight vector. The value basis is estimated through a two-stage procedure combining linear temporal-difference initialization with nonlinear iterative refinement from observed state-action transitions. Using tracking and event data from 95 J1 League matches, we compare the proposed formulation with an independent reinforcement learning baseline under both Position and Velocity States (PVS) and EDMS representations. With EDMS held fixed, the independent baseline assigns the highest value to forward movement in 99.21% of evaluated off-ball states, whereas the most frequent direction under the proposed formulation accounts for 17.63%. Qualitative analyses illustrate context-dependent off-ball valuations and highlight limitations of the current state representation for defensive positioning. Overall, the framework provides an MPE-inspired approach to interpretable action valuation in football, enabling analysis under alternative tactical reward weights.
Sequential Model-Based Optimization (SMBO) traditionally relies on Bayesian or ensembling surrogates for uncertainty quantification. While historically treated as fully data-driven, SMBO increasingly integrates external domain expertise to accelerate discovery. To overcome the opaque guidance and diminished integration fidelity of standard acquisition re-weighting, Probabilistic Circuits (PCs) have emerged as a generative surrogate alternative, enabling direct knowledge injection via conditional sampling. However, these generative routines lack the formal exploration-exploitation semantics required for rigorous optimization. We introduce the Distributional Conformance Score (DisCo), a novel metric that unifies the flexibility and efficiency of PCs with a formal uncertainty framework. DisCo provides a bounded, $[0, 1]$-normalized measure of model "surprise" that (1) recovers properties comparable to kernel-based uncertainty known from, e.g., Gaussian Processes, while maintaining linear-time inference, and (2) enables accurate assessment of conformance of external knowledge w.r.t. model evidence. We then present DisCoMBO, a framework leveraging these properties for robust, knowledge-aware optimization. We prove that DisCoMBO is a zero-regret algorithm and demonstrate its effectiveness across diverse benchmarks from AutoML, material optimization, and wind park optimization.
Unlocking medieval archives at scale is bottlenecked by the cost of line-level diplomatic transcriptions and manual abbreviation expansion. Focusing on the registers of Pope Honorius III (1216-1227) over 5,000 letters surviving in full only as manuscript images - we show that existing, line-break-free expert transcriptions (edition drafts) suffice to train end-to-end hand-written text recognition (HTR) that jointly transcribes and expands heavily abbreviated Latin. Using forced alignment on 860 unaligned edition entries across 394 pages of Reg. Vat. 9, we automatically bootstrap 13,122 training lines without manual alignment of segmented lines. While the generic CATMuS baseline struggles on this domain (18.9% CER) and a modular space-free HTR + word-segmentation pipeline (cf. Camps et al. 2021) plateaus at 15.6% WER, our from-scratch hybrid Conformer - combining CTC with bidirectional subword attention decoders, iterative self-realignment and n-best LM rescoring - achieves 4.7% CER and 8.7% WER (8.4% WER with ROVER system combination), nearly halving errors on clause-final words (22.7% to 12.2% WER). These figures are measured on the test lines that align with the transcription (86% of all test lines for the best hybrid). Furthermore, we address a tension between paleographic fidelity and editorial normalization: training on targets that preserve scribal name initials reduces the WER against the manuscript text on the 31 affected test lines from 13.3% to 9.2%, at a small cost against the expanded transcription (WER +0.3 points, CER +0.4). Finally, extensive ablations show that none of an auxiliary diplomatic CTC head, a copy mechanism, a permutation decoder or masked-image pretraining improves on direct end-to-end supervision, while strict padding-mask propagation and per-line beam termination make inference batch-invariant.
Stefano Civelli The University of Queensland, Pietro Bernardelle University of Queensland, Nicolò Brunello, Gianluca Demartini The University of Queensland
Large language models (LLMs) encode problem difficulty as an internal signal that can be linearly decoded from their residuals. Given their multilingual capabilities, we investigate whether this meta-cognitive signal is language-agnostic and how it is organized across the model’s layers by training linear probes on the AMC subset of the Easy2Hard benchmark, translated into 21 languages. We found that difficulty-related signals emerge at two distinct stages of the model internals, corresponding to shallow (early-layers) and deep (later-layers) internal representations, that exhibit functionally different behaviors. Probes trained on deep representations achieve high accuracy when evaluated on the same language but exhibit weaker cross-lingual transfer. In contrast, probes trained on shallow representations generalize better across languages, despite achieving lower within-language performance. This closely aligns with existing findings in LLM interpretability, showing that models tend to operate in an abstract conceptual space before producing language-specific outputs. Our results suggest that this two-stage organizational principle extends beyond simple semantic processing to meta-cognitive properties such as problem difficulty, highlighting an internal control signal that is not tied to surface meaning.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · 2026 · 正式发表
Diffusion language models generate text by iteratively denoising all tokens in parallel, but when and where their hidden states encode whether the output will be functionally correct remains unknown.We present the first probing study of DLM internals, training linear classifiers on hidden states to predict functional correctness.Across two models (LLaDA-8B, Dream-7B) and four tasks, we find that DLMs uniquely accumulate correctness signal across denoising steps (AUC gains of 0.08–0.11 on reasoning tasks), absent in single-pass AR decoding. However, step-0 signal reflects prompt difficulty rather than diffusion-specific computation. Signal emergence is task-dependent: structural tasks show flat profiles while reasoning tasks show gradual buildup. The two models exhibit distinct layer dynamics, with LLaDA concentrating signal in upper layers while Dream redistributes toward lower layers. We further show that probe confidence can identify likely failures, enabling selective generation that avoids 36–98% of wasted compute.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop) · 2026 · 正式发表
Neural networks are often treated as monolithic black boxes that process all inputs uniformly through all layers. However, researchers intuitively wonder: do simple images require all 50 layers of ResNet-50, or is the prediction effectively decided much earlier? We investigate when pretrained models make up their minds during a forward pass by training linear probes at each layer of ResNet variants on ImageNet, without modifying the base model. Our findings reveal substantial computational heterogeneity across architectures. We discover pronounced bimodal patterns with distinct populations of early and late deciders: in deeper ResNets, 33--39% of samples stabilize within the first third of the network, while 39--42% are assigned to the final 30% of depth; across all three ResNets, the late fraction ranges from 39% to 54%. The decision layer is highly sensitive to stability criteria, with mean depths increasing from 2.6--4.1 (k=1) to 9.0--10.0 (k=4). Linear probe accuracy exhibits sharp jumps in final residual stages, reaching 73--75% for ResNet-50/101 and 65% for ResNet-18, indicating that semantic consolidation occurs late. These findings expose computational heterogeneity in standard inference and clarify both the promise and the limits of stability-based early exiting.
尚无 AI 解读，展示原文摘要
cs.CV
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表
Diffusion Transformers (DiTs) have achieved state-of-the-art image and video generation performance, but sampling remains expensive due to repeated transformer forward passes over many timesteps. Feature caching offers a training-free way to accelerate inference by reusing or forecasting hidden representations, yet recent forecasting-based methods derive their coefficients from hand-crafted formulas (e.g., Taylor expansion), which ultimately reduce to fixed linear combinations of a few historical features. Such fixed coefficients are suboptimal and fragile under aggressive skipping. In this paper, we first show that existing forecasting-based caching methods can be unified in a common linear form, and then analyze DiT feature trajectories, finding that for most denoising steps the current feature can be reconstructed from past features with projection fidelity above 0.95, indicating that accurate linear prediction is feasible. Motivated by this, we propose L^2P (Learnable Linear Predictor), a simple data-driven caching framework that replaces hand-designed coefficients with learnable per-timestep weights trained on a small set of cached trajectories using a mean-squared error loss, converging in about 20 seconds on a single GPU. Extensive experiments on state-of-the-art DiTs demonstrate that L^2P consistently outperforms existing caching baselines: on FLUX.1-dev, L^2P achieves a 4.55xFLOPs reduction and 4.15xlatency speedup with a PSNR of 31.459, and on Qwen-Image and Qwen-Image-Lightning, it maintains high visual fidelity even under up to 7.18xacceleration, where prior methods suffer from noticeable quality degradation. These results show that learning linear predictors is a practical and effective alternative to designing increasingly complex forecasting formulas for efficient diffusion model inference. The implementation code is available at https://github.com/Aredstone/L2P-Cache.
尚无 AI 解读，展示原文摘要
cs.CV
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表
Hallucination has been a significant impediment to the development and application of current Large Vision-Language Models (LVLMs). To mitigate hallucinations, one intuitive and effective way is to directly increase attention weights to image tokens during inference. Although this effectively reduces the hallucination rate, it often induces repetitive descriptions. To address this, we first conduct an analysis of attention patterns and reveal that real object tokens tend to assign higher attention to the generated text than hallucinated ones. This inspires us to leverage the generated text, which contains instruction-related visual information and contextual knowledge, to alleviate hallucinations while maintaining linguistic coherence. We therefore propose Increase Attention to Generated Text (IAT) and demonstrate that it significantly reduces the hallucination rate while avoiding repetitive descriptions. To prevent naive amplification from impairing the inherent prediction capabilities of LVLMs, we further explore Adaptive IAT (AdaIAT) that employs a layer-wise threshold to control intervention time and fine-grained amplification magnitude tailored to the characteristics of each attention head.Both analysis and experiments demonstrate the effectiveness of AdaIAT. Results of several LVLMs show that AdaIAT effectively alleviates hallucination (reducing hallucination rates C_S and C_I on LLaVA-1.5 by 35.8% and 37.1%, respectively) while preserving linguistic performance and prediction capability, achieving an attractive trade-off.
尚无 AI 解读，展示原文摘要
cs.CV · cs.CL
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表