跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-10 06:03 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-09 06:15 — 2026-11-10 06:15（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-10 06:03最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

18,172 已收录论文15,506 AI 相关4,527 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 3,609 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-10 06:02（北京时间）
新论文 · v1arXiv:2611.08789

TopoSHAP: Shapley for Explainable and Efficient Topological Deep Learning

Mathilde Papillon, Nina Miolane

原文摘要

Topological deep learning (TDL) extends learning on graphs, such as molecules or social networks, to higher-order structures, such as rings in a molecule or groups in a social network. Explaining which of these structures drive a model's predictions, and which architectural components matter most for its performance, remains challenging. We introduce TopoSHAP, an efficient and general explanation framework that addresses both questions across topological domains and model architectures. TopoSHAP-cell assigns Shapley values to topological data cells and extracts compact explanations. These explanations match or outperform graph-based counterparts on GraphXAI benchmark data while running up to 112$\times$ faster. They also reveal advantageous topological feature design, leading to measured improvements in explanation recovery and predictive accuracy. On the architecture side, TopoSHAP-neighbor explains how neighborhoods contribute to model performance, and turns these evaluations into a backward-elimination search that identifies smaller, competitive architectures early in training. This is up to $11.3\times$ cheaper than traditional TDL training sweeps.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08788

Not All Latents Are Equal: Importance-Weighted Latent Graph Generation

Biraaj Rout, Jay Revolinsky, Han Liu, Harry Shomer

原文摘要

Graph generation has shown tremendous effectiveness in modeling complex scientific tasks ranging from molecule generation to optimized circuit design. Most recent advancements have developed models that learn to denoise noisy graphs using either discrete diffusion or flow matching. However, discrete graph diffusion scales quadratically with the number of nodes, making it difficult to use such models on larger graphs. On the other hand, latent graph generation instead seeks to denoise noisy graph latents, which scale better to more nodes due to their lower dimension. However, in practice, latent graph generation models lag behind their discrete counterparts in performance. We study this problem, finding that it is caused by the unequal distribution of that different latent dimensions have on graph reconstruction. the impact. We observe that the vast majority of impact is contained in only a smaller number of latent dimensions. Since equal emphasis is placed on reconstructing the entire latent in the loss function, existing models are optimized to reconstruct information irrelevant to the downstream task. To tackle this problem, we propose Latent Importance Reweighting ({\bf LIR)} which weights each latent dimensions via it's importance to final graph reconstruction. Importance is calculated as the relative influence of a single latent unit on graph reconstruction, which is represented via the Jacobian of the decoder relative to the latent. Our method is model-agnostic and requires no additional model parameters or hyperparameters. Experiments show that LIR can boost performance and lead to faster training convergence when applied to two different autoencoders on various benchmark datasets. Code: https://github.com/biraaj/GraphGenLatentReweight

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08787

Training Stability under Adaptive Curricula

Johan Obando-Ceron, Walter Mayor, Michael Dennis, Aaron Courville, Pablo Samuel Castro

原文摘要

Unsupervised Environment Design (UED) approaches train reinforcement learning (RL) agents on diverse curricula that may evolve with their capabilities. While prior work has largely focused on how these curricula are constructed, we study whether their students remain trainable under the resulting distributions. Across multiple UED mechanisms, environment complexities, and extended training horizons, we identify recurring learner-side pathologies, including parameter growth, degraded value--outcome ordering, and loss of representational diversity, that accompany stagnation and performance degradation. These findings connect limitations in UED to optimization failures previously identified in conventional deep RL, while showing how adaptive curricula couple the learner's optimization state to its future training distribution. Controlled interventions show that mitigating selected pathologies improves learning. Stabilizing the learner improves long-horizon performance and zero-shot generalization without changing the curriculum rule or increasing environment interaction. Our results establish learner trainability as a complementary design principle for UED. Effective curricula require students that remain capable of learning from the distributions they produce.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08784

Blind Noise Equalization for Large Data Matrices under General Variance Profiles

Boris Landa, Francesco Strino, Fabio Parisi, Ruiqi Li, Yuval Kluger

原文摘要

Low-rank approximation is a basic tool for inference from large and noisy data matrices. However, when noise variances differ across entries, a setting known as heteroskedasticity, the noise can distort the observed spectrum, producing spurious components and obscuring weak signals. To address these challenges, we develop BRINE (Blind Resolvent-based Iterative Noise Equalizer), a data-driven procedure that iteratively rescales rows and columns to equalize the average noise variance across both dimensions. Under suitable conditions, this procedure restores the Marchenko-Pastur law for the noise spectrum and can amplify signal components without prior knowledge of the signal or noise structure. A key idea underlying our approach is to equalize the diagonal entries of the data resolvent as a proxy for equalizing the unknown noise variances. At the population level, we identify a potential function that characterizes this equalization and motivates an iterative minimization procedure. We prove convergence of the iterations to the true equalizer for arbitrary positive variance profiles, with a geometric rate under mild conditions. The updates can be estimated directly from noisy data, and we establish probabilistic error bounds for the scaling factors. Simulations and experiments across diverse biological data modalities and preprocessing pipelines illustrate the effectiveness of our approach.

stat.ML · cs.LG · eess.SP · math.ST · stat.ME

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.00422

A Spectral Renormalization-Group View of Learning

Charles H. Martin

原文摘要

We study how the layers in deep neural networks (NNs) converge, using Wilsonian Renormalization-Group (RG) ideas to organize the spectral picture. During training, these layers often develop heavy-tailed power-law (PL) spectra, and the strongest checkpoints often appear near the PL exponent $α\approx 2$. This pattern raises a simple question: why should this value mark a well-trained layer? The answer is both statistical and physical. Our statistical hypothesis is that $α=2$ marks the boundary between stable if not optimal learning and overfitting via non-self-averaging. The physical answer is that the same value makes the spectral energy gain scale evenly across logarithmic spectral scales, which is the proposed Wilsonian marginal condition. We then apply the ERG trace-log condition, the proposed SETOL theory, which we justify by taking volume-preserving, scale-invariant transformations to remove arbitrary layer scale along the proposed RG flow. The resulting spectral RG flow connects the HTSR and SETOL theories to optimizers such as Muon, and motivates a new optimizer extension, WW-PGD. Together, these results point toward a spectral Renormalization-Group view of learning, in which NNs may approach shared spectral structure in the settings studied here.

cs.LG · cond-mat.dis-nn · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2607.00642

Coachable Agents for Interactive Gameplay

Roberto Capobianco, Harm van Seijen, Nolan D. Bard, Neil Burch, Fatima Davelouis, Josh Davidson, Alisa Devlic, Yunshu Du 等 41 位作者

原文摘要

Reinforcement learning has proven to be a valuable tool in the creation of advanced AI and robotic systems, contributing to everything from game playing (Silver et al., 2016; 2017; Wurman et al., 2022) to robotics (Levine et al., 2016; Andrychowicz et al., 2020; Luo et al., 2025; Dürr et al., 2026) to foundation models (Ouyang et al., 2022; Noukhovitch et al., 2024; Sun et al., 2024; Guo et al., 2025). Through trial and error, these AI systems typically learn a single, near-optimal behavior to solve their tasks. However, there are many use cases in which one would like to assert some level of control, after training is completed, over how the task is solved. We refer to these modifications of a core task as styles. We combine universal value function approximators (UVFAs) with carefully selected training scenarios, learning algorithms, and data augmentation to create a framework for coaching agents that exhibit styles in complex domains. We demonstrate the framework's application in the AAA video games Horizon Forbidden West and Gran Turismo, and in an open-source humanoid test domain. Despite the different nature of the domains--car racing, stylized game combat, and humanoid walking--each agent shows strong coherence to the style requests while still satisfying the main task in its domain. Importantly, the techniques outlined in this paper allow an end user to choose the final behavior at run time, giving them flexible control over the final executed performance.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08779

Jacobian-Causal Memory Control for Persistent Memory in Language Model Systems

Marvin Danig

原文摘要

Persistent-memory systems choose not only which records are retrieved but which prior information can alter current inference. We propose Jacobian-causal memory control (JCMC), which represents each authorized memory intervention by a predicted influence signature in a shared behavioral measurement space, selects interventions against a target effect and side-effect budget, and compares predicted with observed effects before retaining or rolling back the intervention. Under explicit smoothness and bounded-estimation assumptions, we prove a quadratic local-approximation bound, characterize the target effects reachable by a set of signatures, bound selection regret under signature error, and bound non-additive interactions between simultaneous memories. The paper reports no benchmark measurements; it defines a paired counterfactual estimator and an evaluation protocol comparing JCMC with relevance, graph, and policy-filtered retrieval baselines. The central claim is narrowed or falsified if those simpler baselines match effect targeting, side-effect control, and rollback utility under equal model, memory, policy, and cost budgets.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02236

Iterative Gumbel Planning for Continuous Control

Shaohuai Liu, Weirui Ye, Yilun Du, Le Xie

原文摘要

Search-based planning remains a powerful policy improvement paradigm in reinforcement learning, driving milestone successes in discrete domains. However, extending this paradigm to continuous control exposes a structural mismatch: search evaluates a finite set of action candidates, whereas continuous RL typically relies on Gaussian policies. We show that winner-action distillation into a continuous Gaussian induces a \textit{projection error} and a stepwise variance-expanding gradient tendency when the selected action is sufficiently far from the current mean. Empirically, this tendency is associated with elevated terminal variance and a return gap on the evaluated tasks. To address this, we propose \textbf{Iterative Gumbel Planning (IGP)}. By adopting a per-dimension factorized categorical policy, IGP naturally aligns the policy support with the search candidates, eliminating the projection error and reducing the residual approximation to a bounded discretization error. To bypass the combinatorial explosion of high-dimensional discrete action spaces, IGP pairs Gumbel Top-$K$ candidate sampling with an MPPI-style multi-round iterative search to refine the policy at each state. Empirically, IGP achieves state-of-the-art aggregate performance and sample efficiency on DMControl and HumanoidBench. Furthermore, it produces more stable action sequences with lower temporal variance, demonstrating its practical potential for real-world robotic deployment.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.23276

Exposing the Illusion of Erasure in Knowledge Editing for LLMs

Advik Raj Basani, Anshuman Chhabra

原文摘要

Knowledge Editing (KE) has emerged as a frontier for updating specific facts in LLMs without costly retraining, but its reliability and underlying mechanisms remain poorly understood. In this work, we examine KE from an adversarial elicitation perspective, revealing that edited knowledge is often not fully erased and continues to surface, with consistent failures observed across diverse model architectures. To explain this behavior, we conduct a mechanistic analysis of popular KE methods. We show that low-rank updates do not overwrite existing knowledge but instead redistribute it within the model's representation space. Furthermore, we find that these methods act as targeted suppression mechanisms that reduce the likelihood of expressing original facts, rather than removing them from the model. Analysis of the loss landscape reveals that edited knowledge lies in narrow, anisotropic regions that are highly sensitive to perturbations, making them highly vulnerable to indirect prompting and adversarial attacks. By exposing these profound architectural vulnerabilities, our work proves that KE algorithms are inherently bypassable and motivates a fundamental reevaluation of how we deploy post-hoc updates in several LLM applications.

cs.LG · cs.AI · cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08775

On Lipschitz Explosion in Deep Neural Networks with Normalization: Consequences for Optimization and Adversarial Robustness

Ashkan Soleymani, Reyhaneh Hosseinpourkhoshkbari, Hadi Daneshmand, Patrick Jaillet

原文摘要

Can a network look stable at every layer and still be exponentially unstable as a whole? The Lipschitz constant of a neural network is a basic stability quantity appearing in optimization guarantees, generalization bounds, and robustness certificates. Deep networks naturally admit two such notions, input Lipschitzness, measuring sensitivity to data perturbations, and parameter Lipschitzness, measuring sensitivity to weight perturbations. We prove that, for deep networks with normalization layers, with batch normalization as the canonical example, both Lipschitz constants can grow exponentially with depth and hence with parameter dimension, even under strong per-layer norm control such as $\|W_\ell\|_2\le 1$, and already for linear activations. Thus, a mechanism widely used to stabilize training can create severe worst-case instabilities that are invisible locally, i.e., from layerwise norm bounds alone. Parameter-Lipschitz explosion turns Lipschitz-dependent nonsmooth optimization guarantees into exponential-in-dimension bounds for deep normalized networks, while input-Lipschitz explosion makes worst-case Lipschitz-based generalization and robustness certificates vacuous. The latter also yields a concrete rank-separation mechanism for adversarial vulnerability. The theory predicts that perturbations introducing new singular directions should be amplified much more strongly than perturbations at the same noise level that remain within the input's original singular subspace. Experiments on MNIST, Fashion-MNIST, and CIFAR-10 support this prediction, showing that rank-creating perturbations cause substantially sharper drops in accuracy, confidence, and margins than same-subspace perturbations.

cs.LG · cs.AI · math.OC · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.04085

Follow the Features: SAE Feature-Guided Data-Efficient Instruction-Tuning of Large Language Models

Ryan Swift, Konstantinos Psounis

原文摘要

Selecting small, effective instruction-tuning datasets requires identifying which aspects of the original data to retain. We introduce Follow the Features (FtF), a data-selection method that uses sparse autoencoder (SAE) features to characterize training data and guide subset construction. FtF ranks features using dataset-level activation statistics, scores samples by their expression of highly ranked features, and incorporates feature resampling to encourage diversity. The LLM-SAE pair used for selection is independent of the model being fine-tuned, enabling reuse across target models. We evaluate FtF on two model-dataset settings at a training budget of 100 samples with a fixed sequence length of 256 tokens. FtF achieves performance competitive with GRAPE and S2L, with relative rankings varying across settings. On Qwen 3 8B trained on Alpaca, FtF exceeds full-dataset training by 1.59 percentage points in the harmonic mean of an AlpacaEval-based win rate and Open LLM Leaderboard performance, although full-dataset training retains a higher Leaderboard score. These results support SAE feature statistics as a useful signal for data-efficient instruction tuning.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.04081

RAPID: Increasing Efficiency of Internal Distillation via Randomized Methods

Ryan Swift, Konstantinos Psounis

原文摘要

Knowledge distillation is a technique used to transfer the expertise of large teacher models into small, efficient student models. Recent advances have integrated the distillation of internal activations, more directly training students to learn similar representations as the teacher. One of the core challenges of internal distillation is the dimensional incompatibility between the student and teacher internal representations. Existing methods add learnable matrices to project the larger teacher activations into the smaller representation space of the student. This is a notable point of inefficiency, as learning additional parameters for the projectors increases training costs, only for them to be discarded immediately after training. We introduce RAPID (RAndomized Projection for Internal Distillation) a novel distillation methodology which eliminates the wasteful projection learning by leveraging randomized methods. RAPID utilizes an efficient transform construction based on the Johnson-Lindenstrauss lemma to compress the teacher representations into the student embedding space with strong theoretical guarantees of structural preservation. RAPID also employs a combination of exponential moving average (EMA) and homoscedastic uncertainty weighting in a novel multi-objective function designed for internal distillation. Our experiments in post-training for reasoning demonstrate that RAPID increases training efficiency by as much as 21.1% while maintaining performance comparable to existing methods.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08767

MEDALLION: Manifold Embedding Distillation and Attributions for Low-dimensional Latent InterpretatiON

Vicky Jung, Claire M. He, Irene Chang, Genevera I. Allen

原文摘要

Dimensionality reduction is widely used to visualize high-dimensional data and guide scientific discovery, yet interpreting which original features contribute to low-dimensional representations remains challenging, particularly for black-box methods such as t-SNE and UMAP. We introduce \textbf{MEDALLION} (Manifold Embedding Distillation and Attributions for Low-dimensional Latent InterpretatiON), a novel framework for interpreting low-dimensional embeddings through knowledge distillation and neural feature attribution. MEDALLION distills any given embedding with a neural encoder which we explain via a broad range of existing neural feature attribution methods. Through experiments on MNIST and applications in single-cell transcriptomics, we show MEDALLION provides informative feature attributions that cast additional insights into the underlying embedding and compare its performance with existing interpretability approaches.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.23047

DIFFLET: A Fast Inference Engine for Diffusion Transformer Models on AWS Trainium

Bin Ma, Min Yu, Vijay Kodamalla, Johnny Liu, Da Li, Dong Li

原文摘要

On AWS Trainium2, every component of a diffusion model runs as a program compiled ahead of time for fixed shapes, while pipelines differ across models, prompt lengths across requests, and caching decisions across denoising steps. We present Difflet, a serving engine in which five model pipelines share one compilation backend, joint attention is split across cores by attention head, and a host controller decides at each denoising step whether to run the denoiser or reuse its earlier output. A small probe program computes the caching signal on the device and returns one number per step, and a resident model process keeps every program loaded across requests. Across five image and video model families, fused attention accelerates denoiser steps by 1.2-4.3x over the same framework using PyTorch/XLA attention, and at 32.8k visual tokens it is the only attention that compiles. On four of the five models, resident serving is 1.5-3.4x faster than standalone runs that reload weights from a warm file cache for each generation.

cs.DC · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.10854

KDFP: A first-principles approach to knowledge distillation in large language models

Ryan Swift, Konstantinos Psounis

原文摘要

Knowledge distillation is an established technique for improving the capabilities of small, efficient student models by training them with the representations of larger, more capable teacher models. Much of the recent work in the distillation of large language models (LLMs) has focused on distilling abilities learned during post-training, such as instruction following, chain-of-thought reasoning, and tool usage. This has left a large research gap in general knowledge distillation for LLMs, which is essential for developing efficient and private systems suitable for deployment on edge devices. We take a first-principles approach, evaluating previous lessons from prior works and conducting new explorations to develop a distillation methodology suitable for modern LLMs. We present KDFP, a novel methodology for white-box general knowledge distillation in LLMs. We demonstrate that KDFP outperforms existing methods by 1.6% $-$ 4.9% across 9 benchmarks while increasing training efficiency by up to 99.1% through ephemeral parameter reduction.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2509.00031

End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost

Qitao Tan, Xiaoying Song, Ningxi Cheng, Guoming Li, Jun Liu, Lingzi Hong, Caiwen Ding, Jundong Li 等 14 位作者

原文摘要

Quantization reduces the deployment cost of large language models (LLMs). However, post-training quantization (PTQ) cannot fine-tune model parameters and often degrades accuracy in low-bit settings, while quantization-aware training (QAT) requires backpropagation and incurs high memory overhead. We propose ZeroQAT, a zeroth-order QAT framework supporting both weight and activation quantization. By using forward-only gradient estimation, ZeroQAT removes backpropagation and substantially reduces memory and computation while retaining end-to-end optimization benefits. We further introduce a lightweight variant of ZeroQAT for quantized fine-tuning, which freezes and pre-quantizes most parameters to further cut memory usage. Experiments show that ZeroQAT consistently outperforms representative PTQ and QAT baselines while requiring significantly less memory. For example, ZeroQAT enables fine-tuning of a 13B model at extremely low bit-widths (e.g., 2-4 bits) on a single 8GB GPU, and even allows fine-tuning a 6.7B model on a OnePlus 12 smartphone, demonstrating its practicality for end-to-end QAT on resource-limited edge devices.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.09993

Beyond Bayesian Nash: Learning Minimax-Regret Equilibria for Adversarial Team Games under Asymmetric Information

Naman Aggarwal, Jonathan P. How

原文摘要

Adversarial team games (ATGs) with asymmetric information, such as adversarial path-finding, goal search, and reachability games on graphs, require strategies that are robust to hidden opponent types, such as a hidden goal flag, and to deception. Under asymmetric information, deception is seen as strategic shifts in the type distribution such that the omniscient opponent can collude with Nature and condition its play on the observed type. Existing risk-neutral solution concepts, such as Bayesian Nash equilibrium (BNE), are sensitive to distribution shifts, while distributionally robust approaches provide guarantees only within a prescribed ambiguity set. To address these limitations, we introduce Probabilistically Robust Minimax-Regret Equilibrium (PR-MRE), a novel equilibrium concept that combines the distribution-free robustness of minimax-regret reasoning with probabilistic information from a nominal type distribution. PR-MRE minimizes worst-case regret over a high-confidence subset of the type space, providing protection against strategic redistribution of probability mass while avoiding the conservatism of fully distribution-free approaches. We show that, for finite normal-form Bayesian games, approximate PR-MRE computation can be formulated as a robust bilinear program and derive a tractable semidefinite relaxation. We then adapt this relaxation into a novel meta-solver within a robust double-oracle framework, PRMRE-PSRO, enabling population-based learning of approximate PR-MRE strategies via deep reinforcement learning best responses. Experiments on graph-structured adversarial team games demonstrate that PR-MRE discovers strategies with substantially improved worst-case performance across hidden types compared to risk-neutral Bayesian Nash equilibrium solutions, resulting in more robust behavior under strategic distribution shifts.

cs.GT · cs.AI · cs.LG · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.20079

Probability-Conserving Flow Guidance

Parsa Esmati, Junha Hyung, Amirhossein Dadashzadeh, Jaegul Choo, Majid Mirmehdi

原文摘要

Diffusion and flow-based generative models dominate visual synthesis, with guidance aligning samples to user input and improving perceptual quality. However, Classifier-Free Guidance (CFG) and extrapolation-based methods are heuristic linear combinations of velocities/scores that ignore the generative manifold geometry, breaking probability conservation and driving samples off the learned manifold under strong guidance. We analyse guidance through the continuity equation and show its effect decomposes into a divergence term and a score-parallel term defined invariantly across parameterizations. We prove the divergence term blows up structurally as sampling approaches the data manifold, motivating a time-dependent schedule alongside score-parallel attenuation. The resulting plug-and-play rule, Adaptive Manifold Guidance (AdaMaG), targets both terms at no additional inference cost. Finally, we show that several existing saturation and manifold preserving heuristics can be read as acting on one of these two terms. On image generation benchmarks, AdaMaG improves realism, reduces visible artefacts, and induces controlled desaturation under strong guidance.

cs.CV · cs.AI · cs.LG · eess.IV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.13660

What to Preserve, Where to Adapt: A Depth-Wise Analysis of Forgetting in Continual Gynecological Image Segmentation

Amal Saqib, Tausifa Jan Saleem, Numan Saeed, Mohammad Yaqub

原文摘要

The clinical management of gynecological diseases often relies on medical imaging for diagnosis, treatment planning, and follow-up. Segmentation in this setting is challenging because successive tasks may differ in imaging modality, target anatomy, pathology, and annotation structure. Continual learning allows models to adapt to new tasks without simultaneous access to previous datasets. However, when successive tasks differ substantially, learning a new task can degrade performance on earlier ones, a problem known as catastrophic forgetting. Understanding where adaptation disrupts previous knowledge can help guide the design of more targeted continual-learning strategies. We investigate how forgetting changes as different parts of an encoder--decoder network are allowed to adapt. We progressively expand the trainable region of a 3D nnU-Net backbone from the bottleneck toward input- and output-proximal blocks. Under a shared learning rate, adaptation near the bottleneck largely preserves previous-task performance but provides limited current-task learning, whereas broader adaptation improves current-task performance but sharply increases forgetting. This trade-off persists even when the average change in trainable backbone parameters is approximately comparable. Assigning different learning rates to different blocks substantially reduces forgetting when part of the backbone is trainable, although this changes both the size and location of the updates. Forgetting still increases as more blocks are trained and remains severe when the full backbone is updated. These results show that forgetting depends not only on how much the model changes, but also on which parts of the model are allowed to change.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2604.11748

LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling

Yuxin Chen, Chumeng Liang, Hangke Sui, Ruihan Guo, Chaoran Cheng, Jiaxuan You, Ge Liu

原文摘要

Continuous diffusion has served as a foundation for high-fidelity, controllable, and few-step generation across continuous data modalities such as images, videos, and molecular structures. However, in language modeling, prior continuous diffusion language models (DLMs) lag behind discrete counterparts. Existing categorical and simplex-based approaches operate over extremely large and sparse language spaces, while prior embedding-space approaches avoid this sparsity but lack a well-selected design space. In this work, we close this gap with LangFlow by connecting embedding-space DLMs to Flow Matching, alongside three key innovations: (1) we derive a novel ODE-based NLL bound for principled evaluation of continuous flow-based language models; (2) we propose an information-uniform principle for setting the noise schedule, which motivates a learnable noise scheduler based on a Gumbel distribution; and (3) we revise prior training protocols by incorporating self-conditioning, which improves both likelihood and sample quality for embedding-space DLMs and behaves differently from its use in discrete diffusion. Putting everything together, LangFlow is competitive with top discrete DLMs on generative quality, reaching a generative perplexity of 92.3 on LM1B and 36.5 on OpenWebText. It also outperforms discrete counterparts on reasoning tasks like Sudoku. As the first continuous DLM shown to rival discrete diffusion in generative quality, LangFlow provides clear evidence that continuous diffusion is a promising paradigm for language modeling. Code: https://github.com/nealchen2003/LangFlow.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2511.20798

Physics Steering: Causal Control of Cross-Domain Concepts in a Physics Foundation Model

Rio Alexa Fear, Payel Mukhopadhyay, Michael McCabe, Alberto Bietti, Miles Cranmer

原文摘要

Foundation models trained on text and images have been shown to develop abstract internal features that align with human concepts and that can be directly manipulated via activation steering to alter model behaviour. Whether scientific foundation models learn similarly abstract and domain-general representations has remained an open question. Inspired by recent work identifying single directions in activation space that control complex behaviours in large language models, we show that Walrus, a large physics foundation model, learns linearly steerable representations of physical phenomena. By computing the difference between activations representing contrasting physical regimes, we identify single directions in activation space that correspond to vorticity, diffusion, and even temporal progression. We find that injecting these concept directions back into the model during inference enables fine-grained causal control: vortices can be induced or removed, diffusion enhanced or suppressed, and simulations sped up or slowed down. Moreover, directions derived from one physical system also steer the behaviour of other physical systems, suggesting that they are domain-general. These results provide early evidence that scientific foundation models can learn general representations of physical principles, and further support for the Linear Representation Hypothesis.

cs.LG · cs.AI · physics.comp-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08753

Random Symbolic Boosting: A Geometric Approach to Symbolic Regression

José R. Ortegaa, José Manuel Muñoz Contreras, Leonardo Trujillo

原文摘要

Symbolic models offer interpretability, but their construction through generational evolution can be computationally expensive. This article presents Random Symbolic Boosting (RSB), a method that constructs explicit additive symbolic models via boosting over populations of randomly generated syntax trees, eliminating the need for generational evolution. The idea combines two observations: high-dimensional spaces can be spanned by enough linearly independent vectors, and the semantics of syntax trees can be directly manipulated as such vectors. It is shown that, for Ordinary Least Squares, the boosting process guarantees a monotonic reduction of the training error for both regression and classification. Furthermore, an adaptive geometric early stopping mechanism is introduced. It is based on the angle between the prediction and target vectors, is independent of the problems scale, and requires no adjustments across tasks. Evaluated on a standard benchmark for symbolic regression, the method is located at the Pareto-optimal point between predictive accuracy and training time, ranking first on the real-world datasets. Additionally, it was tested on a large tabular classification benchmark with 200 problems, achieving competitive results.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2505.15417

Robust Multimodal Learning via Entropy-Gated Contrastive Fusion

Leon Chlon, Maggie Chlon, MarcAntonio M. Awada

原文摘要

Real-world multimodal systems routinely face missing-input scenarios, and in reality, robots lose audio in a factory or a clinical record omits lab tests at inference time. Standard fusion layers either preserve robustness or calibration but never both. We introduce Adaptive Entropy-Gated Contrastive Fusion (AECF), a single light-weight layer that (i) adapts its entropy coefficient per instance, (ii) enforces monotone calibration across all modality subsets, and (iii) drives a curriculum mask directly from training-time entropy. On AV-MNIST and MS-COCO, AECF improves masked-input mAP by +18 pp at a 50% drop rate while reducing ECE by up to 200%, yet adds 1% run-time. All back-bones remain frozen, making AECF an easy drop-in layer for robust, calibrated multimodal inference.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.11639

Inter-Layer Hessian Analysis of Neural Networks with DAG Architectures

Maxim Bolshim, Alexander Kugaevskikh

原文摘要

Automatic differentiation computes loss Hessians, while interpreting inter-layer interactions requires an explicit choice of graph-indexed blocks. This paper presents an analytical formalism that decomposes the full Hessian into blocks indexed by the DAG of an architecture. The standard decomposition $H = H^{GN} + H^T$ separates the Gauss-Newton component (positive semidefinite for a convex output loss) from the tensor component (residual curvature). If every node map is locally affine in its parent activations, the tensor component of the input Hessian vanishes on each smooth cell ($H^{T}_{v,w}=0$, $H^f_{v,w}=H^{GN}_{v,w}$); ReLU activations alone do not suffice. The full parametric Hessian contains residual terms that do not reduce to the GGN. Building on this decomposition, we use diagnostic metrics (inter-layer resonance $\mathcal{R}$, geometric coupling $\mathcal{C}$, stable rank $\mathcal{D}$, GN-Gap) with stochastic HVP-based estimates whose cost depends on graph evaluation and the number of probes. The theoretical analysis gives conditional bounds on curvature decay and residual-chain transport; empirical examples span fully connected MLPs (Exp. 1-5) and convolutional architectures (ResNet-18, ${\sim}11$M parameters, Exp. 6). When the architecture reduces to a single node, all definitions collapse to the standard Hessian $\nabla^2_θ\mathcal{L}(θ)\in\mathbb{R}^{p\times p}$. Archival correction. The original general novelty claims are no longer maintained: general DAG-Hessian calculus has prior precedents. This is a corrected archival version.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08737

On Differentially Private Mechanisms for Linear Regression

Bardiya Aryanfard, Monika Henzinger, Farhood Rostamkhani

原文摘要

We study the classic least-squares linear regression problem under differential privacy (DP) in the batch and the continual observation setting. In the latter setting, the mechanism receives a stream of $n$ data points $(x_i,y_i)$ ($x_i\in\mathbb{R}^d$ and $y_i\in\mathbb{R}$) and must output an estimate of the optimal parameters at each time step $i$. Although differentially private linear regression has been extensively studied in the batch setting, the problem remains underexplored for the continual setting, with prior work being restricted to constrained linear regression and update time polynomial in $n$. In this work, we introduce ContinualAdaSSP, the first mechanism for unconstrained linear regression under continual differential privacy. Our mechanism's suboptimality gap is proportional to $\sqrt{d}\operatorname{polylog}(n)$. It requires $O(d^2\log{n})$ space and $O(d^2\log{n}+d^ω)$ update time, where $d$ is the dimension of the input space. We also study fundamental limits of differentially private linear regression by showing the first lower bounds for the box-constrained least-squares linear regression problem. Our lower bounds are proportional to $\min(n,\frac{\sqrt{d}}{\log^{1.5}d})$ for $(1,O(\frac{1}{n}))$-DP, and $\min(n,\frac{d}ε)$ for $ε$-DP, and are derived using a reduction from a fingerprinting code problem from [Peter et al., 2024], providing new insights into the inherent hardness of this canonical task. Our experimental evaluation on real-world datasets shows that the accuracy of our continual observation mechanism clearly outperforms any other known differentially private mechanism for this problem such as rerunning the batch algorithm at each time step.

cs.LG · cs.CR · cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2505.24030

From Images to Signals: Are Large Vision Models Useful for Time Series Analysis?

Ziming Zhao, ChengAo Shen, Hanghang Tong, Dongjin Song, Zhigang Deng, Qingsong Wen, Jingchao Ni

原文摘要

Transformer-based models have gained increasing attention in time series research, driving interest in Large Language Models (LLMs) and foundation models for time series analysis. As the field moves toward multi-modality, Large Vision Models (LVMs) are emerging as a promising direction. In the past, the effectiveness of Transformer and LLMs in time series has been debated. When it comes to LVMs, a similar question arises: are LVMs truely useful for time series analysis? To address it, we design and conduct the first principled study involving 4 LVMs, 8 imaging methods, 18 datasets and 26 baselines across both high-level (classification) and low-level (forecasting) tasks, with extensive ablation analysis. Our findings indicate LVMs are indeed useful for time series classification but face challenges in forecasting. Although effective, the contemporary best LVM forecasters are limited to specific types of LVMs and imaging methods, exhibit a bias toward forecasting periods, and have limited ability to utilize long look-back windows. We hope our findings could serve as a cornerstone for future research on LVM- and multimodal-based solutions to different time series tasks.

cs.LG · cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.17778

Self-Distillation is Optimal Among Spectral Shrinkage Estimators

Radu Lecoiu, Debarghya Mukherjee, Pragya Sur

原文摘要

Self-distillation has emerged as a promising technique for improving model performance in modern machine learning systems. We develop the statistical foundations of self-distillation in high-dimensional linear regression by introducing and analyzing a broad class of estimators, namely spectral shrinkage estimators. We consider both spiked and general covariance matrices. For the former, we establish that when the covariance has $s$ distinct spikes, $s$-step self-distillation achieves optimal prediction among spectral shrinkage estimators, outperforming well-known estimators in statistics and machine learning. Moreover, we show that $s$ steps are necessary for optimality: any $(s-k)$-step distilled estimator is strictly suboptimal for $1 \leq k \leq s$. For general covariance matrices, we show that self-distillation approaches the optimal limiting prediction risk among continuous spectral shrinkage estimators as the number of distillation steps increases. We further develop a generalized cross-validation procedure for selecting the distillation parameters from data and establish an asymptotic oracle guarantee for the resulting estimator. We also study a federated approach where multiple data centers share spectral shrinkage estimators and a common server seeks to aggregate them to achieve optimal performance. In this case, we find that the best local rule again takes the form of self-distillation, though it differs from the optimal rule when data are hosted centrally on a single server. Together, our results explain why self-distillation improves predictive performance and provide a broader statistical framework that connects it to classical shrinkage-based methods.

math.ST · cs.LG · stat.ME · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08714

Patching the Blind Spots: Reversible LLM Rule Overlay for Frozen Fraud Detectors

Bo Qu, Zhurong Wang, Frank Zahradnik, Ming Ouyang

原文摘要

In industrial tabular fraud classification, gradient-boosted trees remain state-of-the-art, but even a well-trained model has blind spots, and retraining the deployed model is not always safe. We propose a framework that patches such a model without modifying it: LLMs propose rules anchored on features the model underweights by SHAP, and the resulting noisy pool is screened for empirical support and calibrated into an additive, reversible log-lift overlay that runs at the production cut-off. Single-LLM benefit is high-variance and inverts between datasets, so we pool three diverse backbones by equal-weight logit averaging, trading peak gain for a bounded worst case. On a real-world e-commerce fraud detector trained on selection-biased data, continued training regresses even when carefully tuned, whereas the overlay gains on average +2.26% recall at equal precision ($Δ$R@P) and +1.60% precision at equal recall ($Δ$P@R) over production cut-offs spanning 30-57% precision and 23-63% recall. On a public benchmark of seven designed bias-shift variants it raises $Δ$P@R on every variant and keeps $Δ$R@P near neutral. Each amendment is a readable predicate naming the fraud pattern it covers.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.26097

Dynamic Tokenization via Reinforcement Patching: End-to-end Training and Zero-shot Transfer

Yulun Wu, Sravan Kumar Ankireddy, Samuel Sharpe, Nikita Seleznev, Dehao Yuan, Hyeji Kim, Nam H. Nguyen

原文摘要

Efficiently aggregating spatial or temporal horizons to acquire compact representations has become a unifying principle in modern deep learning models, yet learning data-adaptive representations for long-horizon sequence data, especially continuous sequences like time series, remains an open challenge. While fixed-size patching has improved scalability and performance, discovering variable-sized, data-driven patches end-to-end often forces models to rely on soft discretization, specific backbones, or heuristic rules. In this work, we propose Reinforcement Patching (ReinPatch), a novel framework that jointly optimizes a sequence patching policy and its downstream sequence backbone model with reinforcement learning. By formulating patch boundary placement as a discrete decision process optimized via Group Relative Policy Gradient (GRPG), ReinPatch bypasses the need for continuous relaxations and performs dynamic patching policy optimization in a natural manner. Moreover, our method allows strict enforcement of a desired compression rate, freeing the downstream backbone to scale efficiently, and natively supports multi-level hierarchical modeling. We evaluate ReinPatch on time-series forecasting datasets, where it demonstrates compelling performance compared to state-of-the-art data-driven patching strategies. Furthermore, our detached design allows the patching module to be extracted as a standalone foundation patcher, providing the community with visual and empirical insights into the segmentation behaviors preferred by a purely performance-driven neural patching strategy.

cs.LG · cs.AI · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08712

An Educated Guess: Deriving Statistically Aligned Gradient Estimates for Zeroth-Order Optimisation

Justus Huebotter, Serge Thill, Marcel van Gerven, Nasir Ahmad

原文摘要

As novel hardware architectures are explored for the purposes of machine learning, including neuromorphic chips, asynchronous systems, and ASICs, effective learning algorithms are highly desirable. While backpropagation is the standard for differentiation on standard hardware, its requirement for global synchrony and exact differentiability limits the exploration of exotic algorithms on non-traditional substrates and devices. Zeroth-order (ZO) optimisation methods, such as SPSA and weight perturbation, offer a compelling alternative by estimating gradients through inference-only passes; however, these methods have historically suffered due to the `curse of dimensionality', where random perturbations become increasingly misaligned with the true gradient in high-dimensional spaces. In this work, we move beyond blind random noise by deriving zeroth-order search directions from activation geometry available during the forward pass. This leads to a family of Spectral Zeroth-Order methods, SZO-$κ$, whose directions solve local response-based gradient-guessing objectives under explicit stochastic assumptions. These methods explore feature-supported directions that are more likely to produce informative loss responses. Using multilayer and convolutional networks, we analyse gradient alignment, bias-variance structure, and training stability of these methods relative to standard perturbation baselines and backpropagation.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗