cs.LG · 2026-09-02 · No. 103
Machine Learning, 2026-09-02.
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
The Structure of Quantization Damage in LLMs: Why the Next Bit Should Be Spent Globally
Jundong Hu, Shekar Ramachandran
cs.LG · cs.CL
Post-training quantization (PTQ) is widely used to reduce the cost of serving large language models (LLMs), but its accuracy cost is uneven and is often tuned per model. We study where quantization damage occurs and how to allocate a small additional precision budget. Using causal mixed-precision intervention as ground truth (raise each layer to 8-bit in turn and measure the accuracy it recovers) across 9 open-weight models in 4 architecture...
-
02
Gradient-Update Mismatch: Rethinking Conflict-Free Training of Physics-Informed Neural Networks
Jing Xiao, Xinhai Chen, Qinglin Wang, Menghan Jia, Zhiquan Lai, Dongsheng Li, Jie Liu, Tiejun Li
cs.LG
Training Physics-Informed Neural Networks (PINNs) requires jointly optimizing physics residual and initial/boundary condition loss terms, which often induce conflicting gradients. Gradient surgery methods mitigate this issue by constructing directions from loss-specific gradients to reduce conflict before optimizer transformation. However, even when the constructed direction is conflict-free, this property may not be preserved after optimizer...
-
03
Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories
Nabira Rashid, Manolis Kellis
cs.LG · cs.AI · cs.IR
We evaluate embedding retrieval where surface form and meaning are pulled apart on purpose: retrieving items that share underlying structure but not wording, in two unrelated domains under one protocol, competition mathematics (MathNet-Retrieve; 500 queries, 117,088-item corpus) and embodied-agent trajectories (ALFWorld-derived; 118 queries, 336 trajectories). In mathematics the failure is complete: strict Hit@1 at the heaviest disguise tier...
-
04
A Mathematical Theory of Reusable Neural Bases for Network Compression
Binshuai Wang
cs.LG · cs.AI
As large AI models become increasingly prevalent across a wide range of applications, memory cost has become a critical bottleneck in both training and inference. To mitigate this issue, we introduce the Linear Reusable Neural Bases Architecture (LRNBA), a novel framework aimed at improving parameter efficiency and reducing memory cost. Inspired by recurrent neural network (RNN) designs, the core idea of our approach is to represent each...
-
05
NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games
Tomáš Holeček, Viliam Lisý
cs.LG
Model-based reinforcement learning (MBRL) has achieved remarkable results in single-agent domains, yet its extension to competitive imperfect information games (IIGs) remains underexplored. In multi-agent settings, opponent-induced non-stationarity complicates the learning process, and decentralized model learning faces severe identifiability barriers, which we argue make centralized model learning a mathematical necessity. Building on this...
-
06
Quantum Sparse Autoencoders for Q-Matrix Estimation in Cognitive Diagnosis
Arif Hassan Zidan, Yi Pan, Bowen Guo, Xiang Li, Yu Bao, Yingfeng Wang, Tianming Liu, Wei Zhang
cs.LG
Q-matrices play a central role in cognitive diagnosis within educational data mining (EDM), specifying which latent skills each assessment item requires. Data-driven Q-matrix estimation remains challenging when assessments involve many correlated skills and when real response patterns depart from idealized generative assumptions. We introduce a novel quantum sparse autoencoder (QSAE) for Q-matrix estimation, which, to the best of our...
-
07
LatentPress: Context Compression Beyond Text and Vision
Zhengze Zhou, Hejian Sang
cs.LG · cs.AI
Compressed context is usually carried as human-readable text or as rendered images that must be decoded, even when its consumer is a language model. We introduce LatentPress, which writes conversational histories and long documents into a third representation: continuous memory tokens that a frozen decoder reads directly through its input-embedding interface, with no text reconstruction at inference. A small reader-matched writer compresses...
-
08
Optimizing Byzantine Node Placement in Decentralized Federated Learning
Edoardo Gabrielli, Gabriele Tolomei
cs.LG · cs.AI
Security evaluations of decentralized federated learning (DFL) typically focus on how Byzantine participants behave, while largely overlooking which participants are compromised. Yet, because aggregation is distributed over a communication graph, the placement of Byzantine nodes determines how malicious influence propagates through the network. We therefore treat Byzantine placement as an explicit adversarial decision and formulate the...
-
09
Rethinking Learnability in Offline Data-driven Optimization
Chao Qian, Chen-Guang Wang, Rong-Xi Tan, Ke Xue
cs.LG · cs.AI · cs.NE
Black-Box Optimization (BBO) has found broad applications, but evolutionary algorithms and Bayesian optimization face efficiency challenges as real-world BBO problems grow increasingly complex. Data-driven optimization improves the efficiency of BBO algorithms by learning from data. Offline data-driven optimization seeks high-quality solutions using only a fixed set of previous evaluations, attracting substantial attention because it requires...
-
10
Diffusion as a Training Curriculum for Timestep-Free Iterative Reasoning
Mariia Drozdova, Aidan Sirbu, Pietro Miotti, Robert Obryk, Mayalen Etcheverry, Eyvind Niklasson, Blake Richards
cs.LG
Diffusion models and recursive reasoners are both iterative, but they carry information across iterations differently. We add a persistent hidden state to a diffusion denoiser and remove its timestep conditioning, leaving a single shared update that can be run to arbitrary depth. The result is an anytime solver: accuracy keeps improving with inference depth far beyond the rollout lengths and backpropagation window used in training, reaching...
-
11
Edge-Girth as a Structural Edge Feature for Graph Neural Networks
Lilian Marey, Charlotte Laclau
cs.LG
Graph neural networks (GNN) based on message passing are provably no more powerful than the one-dimensional Weisfeiler--Leman colour-refinement test (1-WL): two graphs it cannot tell apart receive identical representations, however deep or wide the network. A common remedy augments node or edge features with precomputed structural descriptors, most often counts of a fixed small subgraph such as triangles or longer cycles, but such counts...
-
12
Efficiently Estimating Optimal Hyperparameter Scaling Laws through Power-Law Entropy Search
Zhiliang Chen, Sebastian Ament, David Eriksson, Maximilian Balandat, Eytan Bakshy, Jihao Andreas Lin
cs.LG · cs.AI
Optimal hyperparameter scaling laws describe how the best hyperparameters for large language model (LLM) training change with model and data scale, enabling practitioners to predict optimal configurations at production scales without expensive large-scale tuning. However, estimating these scaling laws conventionally requires exhaustive grid searches over thousands of training runs, consuming enormous computational resources. We introduce...
-
13
Learning Sparse Decision Trees via Transformer Variational Auto-Encoders
Giacomo Fidone, Alessio Cascione, Riccardo Guidotti
cs.LG · cs.AI
Decision trees are among the most widely used models in machine learning, largely due to their transparent decision logic, making them well-suited for high-stakes decision-making contexts. However, most existing learning algorithms focus on predictive performance, overlooking the joint optimization of other desirable properties, such as structural sparsity. In this work we propose TREVIS, an approach for learning decision trees with respect...
-
14
TRIAGE: Three-level Routing and Intelligent Agent Guidance for Efficient Execution
Ruocan Wei
cs.LG
Large Language Model (LLM) agents based on the ReAct paradigm have demonstrated remarkable capabilities in tool use and task execution. However, ReAct suffers from a fundamental efficiency problem: every query triggers a complete reasoning loop from scratch, and similar queries repeat identical steps without leveraging historical experience. We propose TRIAGE,a three-level routing framework that reduces token consumption by reusing historical...
-
15
CATeye: Coupled Attribute-Topology Invariance Learning for Voucher Abuse Detection
Tian Tian, Shuaicheng Niu, Hao Kuang, Yuanhang Hu, Dong Li, Zhiqi Shen
cs.LG
Voucher abuse poses a major challenge in e-commerce, where malicious users exploit promotional vouchers for profit. Unfortunately, fraud patterns evolve rapidly over time and across regions, causing distribution shifts that degrade existing detection models unless retrained frequently. To tackle this, we propose the Coupled Attribute-Topology Invariance Learning framework (CATeye). The key challenge arises from coupled attribute-topology...
-
16
Provably Safe Sim-to-Real Transfer
Tingting Ni, Maryam Kamgarpour
cs.LG · cs.AI
To mitigate the sample complexity of real-world reinforcement learning (RL), a common practice is to first train a policy in a simulator, where samples are cheap, and then deploy the learned policy in the real world with the hope that it generalizes effectively. Such direct sim-to-real transfer is not guaranteed to succeed: simulator-trained policies can be suboptimal in the real world due to sim-to-real mismatch. Correcting this mismatch...
-
17
Predicting Subsurface Abnormalities Growth using Physics-Informed Neural Networks
Mehrdad Shafiei Dizaji, Hoda Azari
cs.LG
The research explores the pioneering integration of Physics-Informed Neural Networks (PINNs) into the domain of Ground-Penetrating Radar (GPR) data prediction. This research presents a detailed development framework for a specialized PINN model, proficient at interpreting and forecasting GPR data, much like how medical imaging models predict tumor behavior. By harnessing the synergy between deep learning algorithms and the physical laws...
-
18
Contribution-Aware Bandwidth Allocation for Multimodal Split Learning
Iason Ofeidis, Leandros Tassiulas
cs.LG · cs.DC · cs.NI
Multimodal models are increasingly the default option for perception at the network edge, yet they are trained almost entirely in the datacenter, because a client holding several sensor streams cannot host an encoder per modality. Split Learning makes such training feasible by keeping only the first layers on the device, at the cost of an uplink that must carry smashed activations for every modality at every step. Existing compression schemes...
-
19
SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers
Shaowen Wang, Ge Zhang, Kairong Luo, Yuhao Wu, Shaofan Liu, Jiaheng Liu, Wenhao Huang, Shen Yan, Jian Li
cs.LG
Looped Transformers increase effective depth by iterating a shared block of layers, but most evaluations compare at fixed model size, conflating architectural advantage with extra FLOPs. We study looping on Mixture-of-Experts Transformers while closely matching per-token FLOPs, total non-embedding parameters, and KV cache. Through a series of ablations, we arrive at a recipe we call SMELT (Sparse MoE Transformer, middle layers Loop Twice),...
-
20
Bandits in Prod: Hyperparameter Optimization at Inference Time
Louis Abraham, Tuan-Anh Nguyen, Nicolas Devatine
cs.LG · cs.AI
Many production systems can assess a configuration only by using it on live requests and observing noisy feedback. Modern agentic systems are a prominent example, with inference-time choices such as model selection, retrieval depth, prompting strategy, and decoding temperature, yet often with no representative validation data. We formalize this setting as Online Hyperparameter Optimization (OHPO) and cast it as an infinitely many-armed bandit...
-
21
One-Layer Transformer Provably Learns Multiclass One-Nearest Neighbor in Context
Skanda Athreya, Yutong Wang
cs.LG · stat.ML
We extend recent work establishing an equivalence between one-layer transformers and nearest-neighbor classifiers in the binary setting to the multiclass case. By leveraging the simplex encoding, we show that one-layer transformers with an argmax classification head behave identically to a one-nearest-neighbor classifier in the multiclass setting. This closes a gap left by prior work, whose multiclass result relied on a non-standard...
-
22
The Constitutional Coverage Trilemma in AI Governance
Natalija Mitic, Soona Sedahmed A. O., Mamadou Selly Ly, Moustapha Cisse
cs.LG · cs.AI
Frontier AI systems function as \emph{constitutional institutions}: each deployed model encodes an implicit ranking among safety, helpfulness, honesty, autonomy, and equity. We ask whether the supply of frontier constitutional types covers human demand. Combining a paraphrase-controlled audit of the as-shipped default constitutions of $23$ frontier LLM archetypes with a pairwise-tradeoff study of $1{,}649$ US participants on the same...
-
23
Position: Privacy Is a Claim, Not a Property of Synthetic Data
Jiachen Zhao, Antonia Januszewicz, Taeho Jung
cs.LG · cs.CR
Synthetic data has become a common component of machine learning research. While widely adopted, its use in privacy-sensitive contexts has quietly shifted from a claim of residual inference risk under stated assumptions to an appearance-based property inferred from data generation itself. In this position paper, we argue that this shift reflects an implicit change in community standards for what counts as sufficient privacy evidence, rather...
-
24
Solving In-Table Prediction Problems by Deep Neural Networks with Performance Evaluation Using Synthetic Data
Xiao Zhao, Daniela Oelke
cs.LG
Tabular deep learning (TDL) leverages neural networks (NN) to extract patterns from tabular data. Traditional TDL methods follow a supervised learning paradigm, where a target feature is explicitly given. In this work, however, we explore a different approach by employing deep NNs to learn relationships among individual columns within a given table. We investigate whether NNs can predict the values of arbitrarily selected columns in a given...
-
25
Explore More, Drift Less: Outcome-Only Reinforcement Learning Can Suffice for Long-Horizon Interactive Agents
Liming Pu, Xiaoxia Li, Yifu Liu, Teng Cao, Bin Yang
cs.LG · cs.AI
Reinforcement learning is a natural way to post-train LLM agents for long-horizon interactive tasks judged only by end-of-task verification, yet a shared belief holds that outcome-only RL soon hits a ceiling on small open models. Recent work therefore compensates around the training with denser rewards, SFT priors, skill libraries, curated memory, or multi-agent orchestration. We argue the ceiling is an artifact of two failures of common...
-
26
Post-Training Science for Supervised Fine-Tuning
Charles O'Neill, Mudith Jayasekara, Harry Partridge
cs.LG · cs.CL
Every supervised fine-tuning run forces the same chain of decisions, such as learning rate, batch size, LoRA or full fine-tuning, how many epochs, which optimiser, and what data to feed the model. Each of these is typically rediscovered from scratch for every new model and dataset. Here we measure them under one instrument: a sweep that varies one lever at a time, and spans dense and mixture-of-experts models in two families (Qwen3 and...
-
27
Multi-Head Self Attention is a Parameter Identification Mechanism
W. Ross Morrow
cs.LG · stat.ML
We prove that a multi-head scaled dot product attention can be viewed as a parameter identification strategy. The ratio of unidentified parameters to the total number of parameters scales like the reciprocal of the number of heads ($1/2 \to 1/(2H)$), meaning models with more heads are structurally more identified. A subtle side effect of the mathematics observation that attention can never be fully identified. Similarly we also show that some...
-
28
REFACTOR-VLA: Unsupervised Library Learning of Typed Motor Programs
Riyaaz Shaik, Chandru Venkataraman
cs.LG · cs.AI · cs.RO
Most vision-language-action (VLA) models -- OpenVLA, $π_0$, RT-2, RDT-1B -- are monolithic: they emit raw motor commands or short action chunks without organizing behavior into reusable abstractions, so they degrade on long-horizon tasks and resist interpretation. Existing skill-discovery methods sidestep the core question of when two action sequences are behaviorally equivalent, either clustering contrastive embeddings or delegating the...
-
29
Recent Developments in Transformer Inference Deployment on FPGA Platforms: A Survey
Arjan Blankestijn, Uraz Odyurt, Amirreza Yousefzadeh
cs.LG · cs.AR
With the rapid and continuous growth in the incorporation of machine learning models based on the Transformer architecture, capable deployment is in high demand. In this context, capable deployment refers to operational performance aspects, e.g., throughput and latency, as well as efficiency aspects, e.g., energy consumption. When it comes to the task of inference using such models, purpose-built hardware accelerators provide a lucrative...
-
30
Births are difficult to predict even with rich survey and full-population register data
Elizaveta Sivak, Emily M. Cantrell, Thomas Emery, Javier Garcia-Bernardo, Flavio Hafner, Kasia Karpinska, Malte...
cs.LG
Major life events have proven difficult to predict. Does this reflect limits of theory, data, and algorithms, or the large role of chance? We examine one outcome - having a child within three years - through a near-ideal setting for prediction: a data challenge where 147 researchers predicted births for Dutch residents aged 18-45, using survey data and full-population registers. Methods ranged from logistic regression to a large language...
-
31
Pre-carved Niches: The Formation Dynamics of Modular Task Partitions in Early LLM Training
Guangqi Li, Yongxin Li
cs.LG
Large language models exhibit a modular internal organization that mirrors well-studied functional networks of the human brain, but how this organization forms during training is unknown: prior work has characterized finished models, not the formation process. We track formation step by step: we train a Pythia-410M model from scratch (two trajectories, bf16 and fp32) and run attribution patching at every step, alongside probes for gradient...
-
32
CopyShield: A Cross-Level Benchmark of Copyright Defenses in LLMs
Maryam Alshehyari, Dushyant Singh Chauhan, Samuele Poppi, Martin Takac, Salem Lahlou, Nils Lukas
cs.LG
Large language models can reproduce memorized text verbatim, yet copyright defenses are usually evaluated under incompatible protocols. We introduce CopyShield, a controlled benchmark comparing three representative defenses at distinct intervention levels: contrastive decoding (output), Direct Preference Optimization (behavioral), and activation intervention (representation). We evaluate CopyShield on two model families, LLaMA-3.1-8B and...
-
33
Superposed Latent Autoencoder
Quanling Zhao, Jiaying Yang, Tianqi Zhang, Ziyang Hao, Fatemeh Asgarinejad, Flavio Ponzina, Tajana Rosing
cs.LG · cs.AI
Autoencoders typically meet tight latent-memory budgets by making each latent representation smaller, sacrificing representational capacity. We ask a different question: can multiple wider latents be stored together instead? We introduce the Superposed Latent Autoencoder (SLAE), which preserves high-capacity latent representations while sharing storage through learned superposition. SLAE transforms latents into storage-friendly codes, binds...
-
34
Scaled Idempotence in Transformer Attention: Paired OV Geometry and Shared-Value Algebras
Jiming Feng, Junliang Li
cs.LG
We identify a recurrent algebraic regularity in Transformer attention: a sparse subset of effective OV operators $T=OV^\top$ nearly closes under composition, $T^2\approxαT$. Across six pretrained endpoints spanning 2.8B--235B parameters, 3.98--8.00% of heads reach squared closure alignment $\mathcal{P}\geq0.9$, while no matched within-layer O/V mismatch does. An exact principal-coordinate factorization, $T=Q_OKQ_V^\top$ and...
-
35
When Does Online Adaptation Pay on the Edge? A Leakage-Free Evaluation of Warmup, Learning-Rate Selection, and Resource Trade-offs for Time-Series Forecasting
Takumi Fujimoto, Hiroaki Nishi
cs.LG
Online adaptation can help edge time-series forecasting under distribution drift, but its measured benefit is sensitive to evaluation choices. We study six public multivariate streams, including building-sensor and smart-meter data, under a leakage-free streaming protocol. We identify two additional sources of comparison bias. First, the warmup budget of the static baseline has a two-sided effect: insufficient warmup undertrains the baseline,...
-
36
Replicating TRACE: A Practitioner's Guide to Its Threshold and Particle Budget
Alex Chadyuk, Alicia Zhang, Roy Kucukates
cs.LG
TRACE (Math & Lienhart, arXiv:2602.01135) reads causal graphs over event types out of a pretrained autoregressive sequence model by thresholding a per-position conditional-mutual-information estimate at a fixed tau. We independently replicate its headline synthetic result: with tau selected on a validation split, mean per-sequence F1 against exact interventional truth reaches 0.90-0.91 at vocabulary size 1000 (paper: 0.91) and 0.86-0.91 from...
-
37
Neural Symbollic Regression Using Deep Learning and Sparse Modelling
Ravi Kumar U, Sumitra S
cs.LG · cs.NE · cs.SC
Symbolic Regression (SR) seeks to find succinct mathematical expressions that represent the fundamental relationships within data, providing interpretability and scientific understanding that exceeds that of black-box models. Nevertheless, traditional methods like Genetic Programming face challenges with scalability and are highly sensitive to noise, while sparse regression techniques such as SINDy rely significantly on predetermined feature...
-
38
Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation
Zhixuan Liu, Zhichen Dong, Yuyu Fan, Xiangtian Li, Chao Yang
cs.LG
Beyond intended capabilities, model distillation can transfer hidden traits from a teacher. A teacher biased by a system prompt can generate semantically clean training data, such as numeric sequences, that still causes a downstream student to inherit the hidden preference, a phenomenon known as subliminal learning. Prior work has identified several parts of this process. How the signal builds up during training and produces behavioral...
-
39
Modelpedia: A Catalog of Model Findings for the Meta-Science of AI
Franciszek Bernat, Dawid Płudowski, Michał Jan Włodarczyk, Luca Longo, Jianlong Zhou, Andreas Holzinger, Riccardo...
cs.LG
Scientific knowledge about AI models is produced faster than the community can organize it. Every few months a new foundation model reshapes the field and hundreds of papers, blogs, and technical reports document how each behaves or fails. Yet, these findings remain scattered and effectively unretrievable. To address this gap we present Modelpedia, an automated, LLM-assisted framework that extracts findings about models from published papers,...
-
40
Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration
Daehwan Kim, Haejun Chung, Ikbeom Jang
cs.LG · cs.CV
Post-hoc calibration corrects reported confidence, yet a multiclass calibrator can also change the associated top-1 prediction. Accuracy captures only the net effect of these changes on correctness, not how often predictions change; the Top-1 Prediction Change Rate (TPCR) instead measures this frequency. We propose Calibrator-Output Repair for Top-1 Decision Preservation (CORD), the first post-fit adapter to impose exact prediction...
-
41
SAGE: Subpopulation-Aware Generative Enhancement for Mitigating Spurious Correlations
Yiming Luo, Rongqiang Zhao, Jie Liu
cs.LG · cs.CV
Spurious correlations pose a significant challenge to the robustness of modern machine learning. The inherent imbalance in dataset distributions often leads traditional Empirical Risk Minimization (ERM) models to rely on majority spurious attributes for classification, resulting in poor performance on minority groups. This problem becomes particularly challenging when the spurious attributes are unavailable. Existing group-label-free methods...
-
42
From Truncation to Commitment: Persistent Context in Uniform Discrete Diffusion
Satoshi Hayakawa
cs.LG · cs.AI · math.PR · stat.ML
Uniform-state discrete diffusion models update all tokens in parallel while keeping every position revisable. Even when the commonly used top-$p$ rule leaves only one candidate at a position, that choice affects only the current reverse step and can be revised at the next sampling step. We ask what changes when selected hypotheses instead become persistent context for later predictions. We therefore propose committed reveal sampling (CRS), a...
-
43
The Multiple Timescales of Gradient Descent on the Edge of Stability: A Perturbative Derivation of the Central Flow
Raphaël Berthier
cs.LG · math.OC · stat.ML
The central flow of Cohen et al. (2025) is an empirically accurate continuous-time model of gradient descent at the edge of stability in deep learning, However, its derivation is heuristic. We propose a perturbative regime in which the central flow is the limit of gradient descent: we assume that the loss decomposes as $f = g + \varepsilon h$; in the limit $\varepsilon \to 0$, the dynamics of gradient descent with learning rate $η$ converge...
-
44
When Metropolis and Hastings Meet Bradley and Terry: Exact MCMC From Preference Voting
Ariel Smogorghevski, Nir Rosenfeld, Yaniv Romano
cs.LG · stat.CO · stat.ML
Sampling from distributions conditioned on desired semantic properties is an emerging challenge in modern generative modeling. Metropolis-Hastings (MH) provides a principled route to conditional sampling, but requires access to exact pointwise target-density evaluations, which are not available in generative settings. Meanwhile, pairwise comparisons by humans or model "judge" are highly accessible and have proved valuable across diverse...
-
45
Poisson-Gamma Dynamical Systems with Time-varying Transition Dynamics
Jiahao Wang, Yijun Wang, Nan Fang, Sikun Yang
cs.LG
Bayesian methodologies for handling count-valued time series have gained prominence due to their ability to infer interpretable latent structures and to estimate uncertainties. Among these Bayesian models, Poisson-Gamma Dynamical Systems (PGDSs) are proven to be effective in capturing the evolving dynamics underlying observed count sequences. However, the state-of-the-art PGDS still falls short in capturing the transition dynamics that are...
-
46
iPINN for Broadband CARS Phase Retrieval: A Framework for Function Approximation and Inverse Modeling Problems in Nonlinear Spectroscopy
Ravi Teja Vulchi, Carl Messerschmidt, Mohammadsadegh Vafaeinezhad, Rajendhar Junjuri, Tobias Meyer-Zedler, Juergen...
cs.LG · physics.data-an
Phase retrieval in broadband coherent anti-Stokes Raman spectroscopy (BCARS) is an ill-posed inverse problem. The Raman-like signal is encoded in the imaginary part of the resonant susceptibility, which mixes coherently with a non-resonant background (NRB) that varies across acquisitions. We introduce an inverse physics-informed neural network (iPINN) that predicts Lorentzian peak parameters from raw BCARS spectra and reconstructs the...
-
47
MemoryWalker: Stop Training Agents on Contexts They Never Saw
Zinco J, Xunjie Zhu, Shen Huang, Zhenyi Wang, Pengjun Xie, Jieping Ye
cs.LG · cs.CL
Production agent harnesses such as Claude Code and Qwen-Agent compress context during rollout, but training under compression creates a conditioning problem: every eviction branches the effective history, so the learning object is a tree rather than a sequence. Existing linearizations either retain the rightmost path, causing time-travel leakage, or replay a depth-first traversal, causing train-inference mismatch. We introduce two exact,...
-
48
Conditional Flow Matching for ML-Based Inverse Design Problems
Juliana Felder, Milad Habibi, Soheyl Massoudi, Mark Fuge
cs.LG
Engineering inverse design is often limited by the high computational cost of iterative solvers for optimization problems constrained by partial differential equations (PDEs) and by their sensitivity to initialization. Deep generative models can produce candidate designs without rerunning the simulator at inference time. Generative adversarial networks (GANs) sample in one forward pass, whereas diffusion models require iterative reverse-time...
-
49
HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution
Wen Jiang, Mingmin Chu, Yimeng Tian, Qianxin Zhang, Haofei Yang, Rui Yang, Yang Liu, Tao Lv, Fangming Li
cs.LG · cs.AI
Self-evolving agents advance toward autonomy by optimizing their harness---prompts, skills, tools, and execution logic---based on environmental feedback. This paradigm, however, is hampered by three challenges: \textit{credit assignment failure}, where terminal success/failure feedback makes it ambiguous which step caused the error; \textit{shortcut learning}, where agents memorize task-specific patterns rather than acquire generalizable...
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.