cs.LG · 2026-09-07 · No. 108
Machine Learning, 2026-09-07.
49 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
49 entries-
01
RegionFed: Federated Learning for Personalized Query Understanding in Heterogeneous Retail Environments
Quoc H. Nguyen, Ali Lafzi, Abhijeet Phatak, Siddharth Pratap Singh, Rohit Upadhyay, Yogananda Domlur Seetharama,...
cs.LG · cs.AI
Retail search systems serve diverse geographic regions with distinct query patterns, vocabularies, and product preferences, creating significant data heterogeneity that challenges both privacy-preserving training and model personalization. Federated learning offers a natural solution for privacy, but standard FL methods produce global models that sacrifice regional performance, while existing personalized FL approaches operate at the...
-
02
Distill Globally, Adapt Locally: Reasoning Distillation and Product-Type Test-Time Training for Scalable Trade-Up Recommendation
Siliang Liu, Mohammad Ghasemi, Sapan Patel, Amin Banitalebi-Dehkordi
cs.LG
Trade-up recommendation identifies higher-quality alternatives that preserve a customer's purchase intent while offering upgraded benefits. Large language models (LLMs) can reason about such distinctions, but applying them directly to hundreds of millions of product pairs is operationally impractical. We introduce a two-level framework that distills LLM reasoning into an efficient non-generative student and adapts its decision boundary to...
-
03
Variational Continuation for Double Pendulum Periodic Orbits
Leo Yao, Ziming Liu, Max Tegmark
cs.LG · math-ph · nlin.CD · physics.class-ph
We present a Hessian-based approach to numerically continue periodic orbits in dynamical systems. A loop (periodic orbit candidate) is parametrized as a Fourier series; a loss function is defined based on the deviation of the loop from the physical differential equations. Unlike previous work relying on hand-derived Jacobians, our method automates the process by leveraging automatic differentiation, a common machine learning technique. The...
-
04
Embedded Graph Flows for Categorical Graph Generation
Ethan Ma, Zihan Wang, Chris Siu Yeung Chow, Xinguo Feng, Qingqing Li, Rui Jiang, Naipeng Dong, Guangdong Bai
cs.LG
Generating categorical graphs requires choosing node and edge types that form a coherent structure without depending on node order. Many graph generators encode categories as fixed one-hot vectors, which can impose an artificial geometry in which categories are equidistant. We propose Embedded Graph Flows (EGF), a generative model that learns continuous embeddings for node and unordered-edge categories and transports Gaussian noise towards...
-
05
Optimal Rates for Agentic Networked Information Aggregation
MohammadHossein Bateni, Zahra Hadizadeh, MohammadTaghi Hajiaghayi, Mahdi JafariRaviz, Shayan Taherijam
cs.LG · cs.GT · econ.TH
Building on the pioneering paper of Kearns, Roth, and Ryu (SODA'26), we study information aggregation in a networked learning model. The model captures a central pattern in agentic AI: each agent sees only part of the data and passes on only its own conclusion. Their model considers a linear regression problem with the mean squared error (MSE) loss. Agents sit in a DAG and each sees only a subset of the features and its parents' predictions,...
-
06
How Does mHC Use Its Residual Streams? Selective Routing and Near-Identity Mixing
Pengxiang Zhao, Xing Li, Xianzhi Yu, Wei Guo, Zhenhua Dong
cs.LG · cs.AI
Hyper-Connections and their manifold-constrained variant mHC widen a residual pathway from one stream to n, yet how trained models use this capacity remains unclear: how broadly blocks read and write, how strongly the residual pathway mixes streams, and whether the streams carry distinct representations. We examine these properties in the four-stream residual pathway of DeepSeek-V4-Flash using effective stream counts, cross-stream residual...
-
07
Learning from VAE Errors to support ECG-based Differential Diagnosis of Myocardial Scar
Shayan Sharifi, Riccardo Treu, Ilaria Gandin, Federico Garoia, Marco Merlo, Giulia Cisotto
cs.LG · stat.ML
Late Gadolinium Enhancement (LGE) on cardiac magnetic resonance is a key marker of myocardial scar, but its limited accessibility motivates routine ECG-based screening. We evaluated whether $β$-variational autoencoder (VAE)-derived ECG representations can discriminate LGE+ from LGE- cardiomyopathic patients in a local cohort of 300 subjects. We compared 32-dimensional features from the foundation ECGx.AI model with those from a shallower...
-
08
How to Speculate about Uncertainty in Agentic Coding? A Draft-Model Gate Method
Konstantin Grotov, Valentin Malykh
cs.LG
LLM agents deployed for software engineering fail expensively: they act confidently wrong, and bad actions are recognized only after costly execution and retry. We present Speculative Uncertainty (SU), a method that recovers a predictive failure signal for a black-box agent from its output tokens alone, with no access to logits, weights, activations, or repeated sampling. Inverting speculative decoding, a small open-weight draft model scores...
-
09
GLASS: Graph-Language Alignment with Spherical Scoring for Transferable Graph-Level Anomaly Detection
Xudong Wang, Chris Ding, Tongxin Li, Jicong Fan
cs.LG
We introduce GLASS, a framework for graph-level anomaly detection (GLAD) that achieves robust cross-domain transferability through graph-language alignment on the unit hypersphere. GLASS builds a unified representation space by aligning a structure-aware graph encoder with an instruction-aware text embedding via a multi-slice soft cosine objective. Our framework serializes local, global, and semantic graph properties into a compact Graph...
-
10
PRICE: A Systematic Study of LLM Adaptation Choices for Bitcoin Price Forecasting
Maryam Fakhari, Mehran Safayani
cs.LG · cs.AI · math.NA
Cryptocurrency markets exhibit extreme volatility and non-stationary dynamics that challenge conventional forecasting methods. Although Large Language Models (LLMs) have shown promise for time series forecasting, the combined effects of adaptation choices remain largely unexplored in financial settings. This study introduces PRICE, a structured approach for adapting LLMs to short-term Bitcoin price forecasting. Built on a 4-bit quantized...
-
11
Hessian-based molecular conformation augmentation for a scalable and efficient strategy of machine learning interatomic potentials
Bumju Kwak, Jeonghee Jo
cs.LG · physics.chem-ph
While machine-learning interatomic potentials (MLIPs) have successfully learned potential energy surfaces (PES) and atomic forces, many practical applications, such as vibrational analysis and transition state search, rely heavily on the PES Hessian. Yet, standard MLIPs tend to be trained on energy and forces alone, leaving Hessian information largely unexploited. Meanwhile, existing methods that explicitly incorporate the Hessian into...
-
12
FedDRAW: Federated Dual Reputation Annealing Weighting for Heterogeneous Multi-Institutional Chest Radiograph Classification
Maryam Moradpour, Anne-Christin Hauschild
cs.LG
Artificial intelligence models are promising for medical diagnosis, but they require large numbers of unbiased data, which in medicine are distributed across hospitals and cannot be centralized to protect patient privacy. Federated Learning (FL) addresses this, since hospitals train one shared diagnostic model while patient data remain local. Training proceeds in communication rounds, in which each hospital trains the shared model locally and...
-
13
Dimension-Adaptive Batched Lipschitz Narrowing Without Knowing the Zooming Dimension
Yasong Feng
cs.LG
The Appropriately Combined Edge-length (ACE) sequence in A-BLiN depends on the zooming dimension $d_z$. This note removes that dependence. The next edge length is selected from the number of cubes that survive the preceding elimination. The resulting Count-Adaptive BLiN algorithm does not use $d_z$ or the zooming constant $C_z$, yet it attains $\widetilde{\mathcal O}_d(T^{(d_z+1)/(d_z+2)})$ regret with $\mathcal O_d(\log\log T)$ batches....
-
14
Phase Transition Frequency as a Training Time Predictor of Test Accuracy in ResNets
Arunan J
cs.LG · cs.AI
The number of discrete class-separability jumps observed during ResNet finetuning is examined empirically as a predictor of final test accuracy. Across 75 experiments spanning four benchmarks (CIFAR-10, CIFAR-100, TinyImageNet, and CIFAR-10-C) and three architectures (ResNet-18, ResNet-50, and ResNet-101), with five to ten seeds per configuration, a strong within-dataset negative correlation is obtained on standard i.i.d. classification...
-
15
Beyond Stationarity in Time Series: Discovering Causal Structures and Latent Regimes via Markov Blankets
Lei Zan, Charles K. Assaad, Emilie Devijver, Eric Gaussier
cs.LG · cs.AI
This paper introduces Regime-aware Constraint-Based and Noise-Based causal discovery with Markov Blankets (RCBNB-MB), a novel causal discovery algorithm for time series that relaxes the common assumption of a single, time-consistent causal structure. Time series are typically observed at discrete time points and often exhibit regime changes that challenge the assumption of a static causal structure, a limitation in many real-world dynamic...
-
16
From 80x to 385x: A Best-Matching-Unit Search at the L2 Roof, Measured Against a Symmetrically Tuned Baseline
Andrew James Amos
cs.LG
Comparisons between GPU implementations are usually asymmetric: one side is tuned by its author, the other is run as found. I report a programme that tuned both a novel SOM algorithm (SparseBin) and the baseline algorithm it was being compared to (cuSPARSE). The best-matching-unit search that dominates self-organizing map training was tuned through four levers - tile size, tile-membership clustering, neuron-axis chunking and vectorised loads...
-
17
MomentQuant: an even more minimalist interval method with linear time complexity for time series classification
Johann Faouzi
cs.LG
Time series data is very common in many real-world applications and in numerous domains, with increasing interest for automated information extraction using machine learning. One of these subfields is time series classification, which consists in assigning a label to each new, unseen time series. Many algorithms have been developed over the past decades, with the trade-off between predictive performance and computational cost being...
-
18
Coarse-Graining Hidden Representations: Unsupervised Neuron Selection via Mapping Entropy
Margherita Mele, Andrea Castagna, Roberto Menichetti, Raffaello Potestio, Alessandro Ingrosso
cs.LG · cond-mat.dis-nn · cond-mat.stat-mech
Overparameterized neural networks carry far more hidden units than a task nominally requires, raising the question of which neurons are essential and whether that distinction is legible in the representation itself, without labels or gradients. We cast neuron selection as the problem of coarse-graining the hidden layer by retaining a subset of its neurons, and score each putative selection by the mapping entropy (ME). This quantity measures...
-
19
Single-Query Black-Box Calibration Auditing via Logit Bias
Roman Plaud, Antoine Saillenfest, Matthieu Labeau, Thomas Bonald, Willem Waegeman
cs.LG
Evaluating the calibration of Large Language Models (LLMs) is critical for their safe deployment as zero-shot classifiers. Yet, commercial API providers increasingly hide the continuous output probabilities required by standard calibration metrics. To bypass this opacity, we demonstrate that any LLM API exposing a logit\_bias parameter can be mathematically manipulated to evaluate exact probability thresholds using strictly one query per...
-
20
A Comparative Study of Counterfactual Explainers for Graph Neural Networks Enabling Multiple Types of Graph Edit
Maria Myrto Villia, Filippos Gouidis, Theodore Patkos, Panos Trahanias
cs.LG
Counterfactual explanations for graph-structured data seek to determine minimal and realistic modifications required in an input graph to alter a model's prediction to a predefined output. Although counterfactual explainers that support modifying the graph by both adding and removing edges have recently emerged, there is still a lack of general and efficient methods, especially when considering the quality of the generated explanations....
-
21
NEAT-POCKET: Pocket-Conditioned Autoregressive 3D Molecular Generation with a Neighborhood-Guided Set Transformer
Roxane Axel Jacob, Daniel Rose, Thierry Langer, Johannes Kirchmair
cs.LG · cs.AI
AI-driven de novo molecular design offers a promising route to accelerate early-stage drug discovery by generating novel ligands directly within target protein binding pockets. We present NEAT-POCKET, a pocket-conditioned extension of the autoregressive NEAT model for 3D molecular generation. NEAT-POCKET generates molecules atom by atom in protein pocket environments while preserving atom permutation invariance and explicitly modeling...
-
22
Deep Microcompression: Structured Pruning and Bit-packed Quantization for Microcontrollers
Opegbemi Matthias Busoye, Tolulope Matthew Busoye, Eghonghon-aye Eigbe
cs.LG
This paper introduces Deep Microcompression (DMC), a hardware-aware pipeline for deep learning inference on bare-metal microcontrollers. DMC integrates structured pruning, quantization-aware training, and fixed-length bit-packing to achieve a 55.8$\times$ weight compression ratio on LeNet-5 (98.77\% accuracy), generating a dependency-free C library with deterministic latency. On the RP2040 (Cortex-M0+), DMC reduces binary size by 3$\times$...
-
23
Confounding-Valid Conformal Inference for Counterfactual KPIs in Wireless Networks
Abdessamed Qchohi, Jessica Moysen Cortes, Matteo Zecchin
cs.LG · cs.NI · eess.SP · stat.ML
Conformal counterfactual inference enables network operators to use logged telemetry to reliably answer 'what-if' questions about network operation. These answers typically take the form of prediction sets that contain, with a user-defined probability, the key performance indicators (KPIs) that would have been observed under alternative control actions. A key challenge is that logged telemetry may omit variables used by the controller,...
-
24
Amortizing Scaling Law Construction Costs
Abhash Kumar Jha, Diana Alexandra Onuţu, Neeratyoy Mallik, Swagatam Haldar, Sam Laing, Niccolò Ajroldi, Shiwei Liu,...
cs.LG · cs.AI
Scaling laws guide the design choices for training large foundation models, but deriving them involves training an exhaustive grid over hyperparameters, token budgets, and parameter counts, which is computationally expensive. Fitting a scaling law, however, only requires the best-loss frontier across compute scales, discarding most of the trained configurations. We propose a framework for efficient scaling law construction that formulates...
-
25
Solution-space heterogeneity shapes federated learning dynamics across partial differential equations
Ping Luo, Jiahuan Wang, Ziqing Wen, Tao Sun, Dongsheng Li
cs.LG · cs.DC
Federated scientific machine learning enables institutions to train neural surrogates without centralizing local physical data, yet studies of partial differential equations (PDEs) lack a transferable definition of non-independent and identically distributed data. Existing protocols partition coordinates, coefficients, boundary conditions, or geometries according to equation-specific rules. Here, we introduce solution-space PDE-Dirichlet, a...
-
26
Beyond Homoscedasticity: Decoupled Uncertainty Optimization for Deep Imbalanced Regression
Juncheng Zhou, Jiaxi Lu, Weijing Zeng, Zhong Li, Hao Qi, Jingsong Cui
cs.LG
Deep Imbalanced Regression (DIR) is pervasive in continuous prediction tasks across diverse modalities, such as age estimation, depth prediction, and protein mutation activity prediction, where label-scarce tail samples often carry higher practical value. However, most existing methods still learn deterministic point mappings under mean squared error or its simple variants, implicitly assuming a uniform uncertainty level across all samples...
-
27
BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference
Janghyeon Kim, Minsoo Kim, Kyuhong Shim, Jungwook Choi
cs.LG · cs.CL
Large Reasoning Models (LRMs) achieve superior problem-solving through extended Chain-of-Thought (CoT) generation, but the resulting key-value (KV) cache grows linearly with sequence length and creates severe memory bottlenecks, often exceeding GPU capacity for long reasoning traces. Existing KV cache compression methods rely on recent queries to estimate future token importance, implicitly assuming these serve as reliable proxies for future...
-
28
Fractal basins trap latent reasoning
Jeffrey Lai, Anthony Bao, John Quinn, William Gilpin
cs.LG
Reasoning allows artificial intelligence models to revisit and correct their mistakes, enabling recent frontier advances in mathematical theorem solving, software engineering, and autonomous task planning. Reasoning models are widely observed to reason for longer on harder tasks, but the general mechanism responsible for these slowdowns is unknown. Here, we show that reasoning models exhibit transient chaos, a physical consequence of the...
-
29
Physics-Aware Random Walk Fingerprints for Scalable Power Grid Graph Classification
Adnan Anwar
cs.LG · eess.SY
Recent benchmarks such as PowerGraph provide large collections of power-grid graphs for cascading-failure classification. Graph neural networks (GNNs) achieve strong predictive performance on this task, but typically require end-to-end training and model-specific tuning, while their latent representations can be difficult to relate to physically meaningful propagation patterns. Random Walk Fingerprints (RWF) offer a scalable and interpretable...
-
30
Fast Gauss Sums via Flash Attention
Nicolaj Rux, Sebastian Neumayer
cs.LG · math.NA
Gaussian kernel sums are the computational core of maximum mean discrepancies (MMDs), kernel gradient flows, Stein variational gradient descent (SVGD), and many other kernel methods. At the same time, softmax attention has received an extraordinary amount of hardware-aware code engineering, culminating in flash attention. We show that Gauss kernel sums with arbitrary, signed weights can be evaluated via flash attention: two small input...
-
31
Adaptation Interfaces for In-Context Tabular Foundation Models in Time-to-Event Prediction
Minh-Khoi Pham, Luca Cotugno, Dan Cernei, Alina Sirbu, Stefano Masi, Giuseppe Prencipe, Alessandro Pingitore,...
cs.LG · cs.AI
Tabular foundation models (TabFMs) achieve strong performance on structured data, particularly for standard classification and regression problems. Yet, extending them to censored time-to-event prediction is challenging because it requires properly handling censoring and event-time dynamics. Building on our prior work, we further link TabFMs with CoxPH and DeepHit and revise the context-resampled training procedure. We evaluate temporal...
-
32
From Deep to Shallow: Unconstrained and Efficient Layer Merging Strategy
Petro Shulzhenko, Gabriele Spadaro, Enzo Tartaglione
cs.LG
Although Deep Neural Networks have become foundational in many areas of Machine Learning, high computational demands limit their application in resource-constrained environments. To address this issue, depth compression methods have been proposed to identify and linearize redundant activation functions, thereby allowing for the merging of layers without intermediate non-linearities. However, these methods face two key challenges: they cannot...
-
33
When Genomic Masking Priors Fail to Transfer: Strong Variant Prediction, Weak Functional Generation
Susu Hu, Preetam Gattogi, Jens Lehmann, Sahar Vahdati, Stefanie Speidel, Julien Vibert
cs.LG
Bidirectional discrete diffusion model appears naturally suited to genomic modeling because it can reconstruct missing sequence from both flanks. We developed GenDA (Genomic Density-optimized Absorbing Diffusion) under the additional hypothesis that entropy-guided span placement would concentrate reconstruction pressure on compositionally complex regions, improving both downstream variant-effect prediction and functional sequence generation....
-
34
KVMem: Virtualizing Million-Token Agent Workspaces on a Consumer GPU
Di Chai, Leye Wang, Zeshen Su, Zhiguo Xia, Zhihang Yu
cs.LG
Modern LLM agents operate in persistent workspaces whose accumulated history can exceed both GPU KV capacity and the model's native context window. Existing systems typically compact older context into summaries or retrieve it later as text, either losing fine-grained execution evidence or repeatedly prefilling content that the model has already processed. We present KVMem, a KV-context virtualization system that preserves overflowed...
-
35
PACE: Propagation-Aware Collaborative Correction for One-Shot Personalized Federated Graph Learning
Ruizhe Huang, Chengran Li, Xiaochuan Shi
cs.LG
Client heterogeneity creates both an opportunity and a risk in personalized federated graph learning. Knowledge held by other subgraphs may complement a receiver's Local model, but an incompatible transfer can override reliable predictions. One-shot communication sharpens this tension because an unsuitable server return cannot be corrected later. We introduce PACE, which treats collaborative knowledge as a compact correction to a complete...
-
36
Communication-Efficient Personalized Federated Learning via Layer-Wise Multi-Threshold Random Sketching
Xu Zhang, Xingyu Hou, Jiacheng Cheng, Kaiyuan Feng, Maoguo Gong
cs.LG
Personalized federated learning (PFL) is a promising paradigm for collaborative learning over distributed devices, where edge nodes collaboratively train personalized models without sharing raw data. Although PFL addresses data heterogeneity by learning client-specific models, it still suffers from substantial uplink and downlink communication costs when exchanging high-dimensional parameters in bandwidth-constrained systems. Recent one-bit...
-
37
Federated Attack Campaign Detection via Contrastive Encoding of Threat Indicators in Gradient Updates
Manuel Röder, Bibin Babu, Frank-Michael Schleif
cs.LG · cs.CR
Detecting orchestrated cyberattack campaigns that span multiple organizations traditionally requires sharing sensitive telemetry and threat intelligence across institutional boundaries and country borders, a barrier that Federated Learning removes by training shared threat detectors directly on local data. We propose FedIoC, a modular framework in which clients fold locally available structured threat indicators into their gradient updates;...
-
38
How Faithful Is Attribution for Sales Forecasting? A Counterfactual Study
Glib Kechyn
cs.LG
Deep models for sales forecasting, such as WaveNet-style dilated convolutional networks, are accurate but opaque: when a single model predicts sales for one of many series, it offers no account of why. We add a post-hoc, architecture-agnostic counterfactual interpretability layer to a multi-series WaveNet forecaster trained on the full Corporacion Favorita grocery dataset (174,685 series over 1,688 days). The method decomposes each forecast...
-
39
Learning-Augmented Algorithms: Guarantees, Construction Mechanisms, and System-Level Implications
Hailiang Zhao, Peng Chen, Xueyan Tang, Jianwei Yin, Shuiguang Deng
cs.LG · cs.DS
Learning-augmented algorithms use fallible predictions while retaining formal performance guarantees. This survey synthesizes prediction interfaces, error measures, consistency--robustness trade-offs, and five representative construction mechanisms across online optimization, caching, learned data structures, graph problems, and mechanism design. An orthogonal theorem-level axis distinguishes achieved upper bounds from matched asymptotic...
-
40
Dynamic Heterogeneous Graph Representation Learning: A Survey
Huan Liu, Pengfei Jiao, Jie Yin, Hongjiang Chen, Zhidong Zhao
cs.LG · cs.AI · cs.SI
Graph representation learning (GRL) serves as a canonical paradigm for modeling complex networks. However, real-world AI systems inherently manifest as evolving heterogeneous entities with complex interactions, posing significant challenges to static or homogeneous modeling. To address these complexities, representation learning for Dynamic Heterogeneous Graphs (DHGs) has emerged as a vital approach for learning low-dimensional...
-
41
Persistent Teacher Anchoring for Tool-Using Agents
Hyun Bin Park, Kyungho Song, Sangmin Lee, Du-Seong Chang
cs.LG · cs.AI · cs.CL
Distillation is common in LLM post-training, where on-policy knowledge distillation (OPKD) uses student-generated trajectories to prepare the student for downstream RL. At each state, the student matches a next-token distribution supplied by the teacher. As the rollout enters states the teacher would not visit, the teacher-student distribution gap can accumulate. In tool use, this gap becomes consequential because student-written calls...
-
42
A Robust Watermark-based Fingerprint Framework for GNNs Ownership Verification
Han Zhang, Yan Wang, Guanfeng Liu, Pengfei Ding, Huaxiong Wang, Kwok-Yan Lam
cs.LG
The high training cost of Graph Neural Networks (GNNs) has raised growing concerns regarding model ownership infringement, such as model stealing and unauthorized misuse. To verify model ownership and prevent significant economic losses, two groups of GNN Ownership Verification (OV) methods have been proposed: watermark-based methods and fingerprint-based methods. However, these methods typically face three limitations: (1) the performance...
-
43
Resilience Beyond Stationary Client Unavailability: Unlocking Efficient and Unbiased Federated Learning
Ming Xiang, Stratis Ioannidis, Edmund Yeh, Carlee Joe-Wong, Lili Su
cs.LG · cs.DC · math.OC
Due to resource constraints or external and internal uncertainties, clients in real-world federated learning systems are often intermittently available edge devices. In highly dynamic environments, the parameter server lacks prior real-time knowledge of clients' availability, making it challenging to adapt traditional federated learning algorithms to be resilient to uncertainties in client availability. If not carefully addressed, complex...
-
44
A Fairness Audit of the Duckworth-Lewis-Stern Method: Format-Specific and Gender-Differential Bias, with an Interpretable Calibration Layer for Cricket Target Revision
Soumyadeep Roy
cs.LG
The Duckworth-Lewis-Stern (DLS) method has been the international standard for revising target scores in rain-interrupted limited-overs cricket since 1999. Despite over two decades of operational use, no large-scale empirical audit of its prediction bias has been published. We conduct such an audit on 8,150 international matches (3,095 ODIs, 5,055 T20Is) from Cricsheet, generating 233,550 synthetic interruption scenarios with temporal splits....
-
45
Training Large Language Models for Small-Molecule Design with Synthetic Task Scaling
Frank Hu, Shriram Chennakesavalu, Zichen Wang, Patricia Suriana, Bodhi Vani, Kirill Shmilovich, Kangway Chuang, Colin Grambow
cs.LG
Designing viable drug candidates requires searching a combinatorially large and rugged chemical space for molecules that satisfy multiple, often competing, objectives. Large language models (LLMs) provide a useful generative prior for this problem because of their representational capacity, reasoning ability, and flexibility when incorporating information from the external environment. While reinforcement learning from verifiable rewards...
-
46
Locating and Steering Refusal Beyond Attention
Preethi Carmel Bosco, Gopalakrishnan Srinivasan
cs.LG
Where inside a language model does refusal live, and does that place change when the architecture does? In a transformer, refusal is governed by a single direction in the residual stream, a finding that safety and interpretability tooling now depend on. State-space models (SSMs) route information through a recurrent update instead of attention, sharing no token-mixing mechanism with a transformer. Does the same safety representation survive...
-
47
Simulation-free Unbalanced Dynamic Optimal Transport with General Growth Penalty
Junda Ying, Yuxuan Wang, Bowen Yang, Peijie Zhou, Lei Zhang
cs.LG · cs.AI · q-bio.QM
Inferring cellular dynamics from unpaired single-cell snapshots requires modeling both state transitions and population growth or death. Unbalanced dynamic optimal transport (UDOT) addresses this by penalizing growth along transport paths, making the choice of growth penalty a key way to encode biological priors on proliferation and apoptosis. However, existing UDOT solvers either rely on computationally expensive NeuralODE simulations or...
-
48
WEECFP-SuRGE: Wide Embedded Extended Connectivity Fingerprint with Substructure Rotary Graph-distance Encoding
Robert Epps
cs.LG
We introduce WEECFP, a parameter-free 1024-dimensional continuous molecular fingerprint that scatters each Morgan substructure across roughly thirty-two signed positions of a single vector, and WEECFP-SuRGE, a transformer architecture whose self-attention applies SuRGE (Substructure Rotary Graph-distance Encoding) -- a RoPE-like rotation parameterized by molecular shortest-path graph distance -- to WEECFP substructure tokens. A 7-model blend...
-
49
Interpretability for Turing Machines
Billy Snikkers, Rumi Salazar, Daniel Murfet, Will Troiani
cs.LG · cs.FL · stat.ML
We show that susceptibilities, an interpretability technique developed for neural networks, can identify the presence of algorithmic structure in Turing machines by probing the local loss landscape of a learning problem for noisy Turing machines introduced by Murfet and Troiani (arXiv:2504.08075). We prove that symmetries and path separation in the algorithm implemented by a Turing machine induce permutation symmetries and low-rank blocks in...
This edition is part of The Daily Abstract — cs.LG archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.