Machine Learning
Forager: a lightweight testbed for continual learning with partial observability in RL
Steven Tang, Xinze Xiong, Anna Hakhverdyan et al. (+7 more)
In continual reinforcement learning (CRL), good performance requires never-ending learning, acting, and exploration in a big, partially observable world. Most CRL experiments have focused on loss of plasticity—the inability to keep learning—in one-off experiments where some unobservable non-stationarity is added to classic fully observable MDPs. Further, these experiments rarely consider the role of partial observability and the importance of CRL
agents that use
memory or recurrence. One potential reason for this focus on mitigating loss of plasticity without considering partial observability is that many partially-observable CRL environments are prohibitively expensive. In this paper, we introduce Forager, a lightweight partially-observable CRL environment with a constant
memory footprint. We provide a set of experiments and sample tasks demonstrating that Forager is challenging for current CRL
agents and yet also allows for in-depth study of those
agents. We demonstrate that
agents exhibit loss of plasticity, proposed mitigations can help, but that most useful is to leverage state construction. We conclude with a variant of Forager that generates an unending stream of new tasks to learn that clearly highlights the limitations of current CRL
agents.
Read the full abstract ▾
All authors Steven Tang, Xinze Xiong, Anna Hakhverdyan, Andrew Patterson, Jacob Adkins, Jiamin He, Esraa Elelimy, Parham Mohammad Panahi, Martha White, Adam White
Machine Learning
Extreme Weather Bench: A framework and benchmark for evaluation of high-impact weather
Amy McGovern, Taylor Mandelbaum, Daniel Rothenberg et al. (+6 more)
Forecasting the wide variety of high-impact weather events experienced globally is a challenge for both Artificial Intelligence (AI) and Numerical Weather Prediction (NWP) models and it is critical that such models be properly verified before deployment. Although AI weather models are rapidly evolving, much of their evaluation is currently done either with a global-scale evaluation or by hand-picking a small number of case studies or a region. A widely-used open-source
benchmark suite focusing on high-impact weather will help to drive the science forward for all scales of weather models, as it has for other AI fields. Here we introduce Extreme Weather Bench (EWB), a new community-driven
benchmark suite that facilitates model validation and verification on a variety of high-impact hazards that matter to people around the globe. EWB provides a standard set of case studies (spanning across multiple spatial and temporal scales and different parts of the weather spectrum), observational data, impact-based metrics, and open-source code for users to evaluate their models. Verifying that a model works against a standard set of case studies, especially events that are high-impact for the general public, is a key piece of improving the trustworthiness of AI models. EWB will help to drive the science forward for all weather models, enabling true comparisons across models and evaluating models on specific high-impact phenomena through the use of case studies. EWB is a free open-source community-driven system and will continue to evolve to include additional phenomena, test cases and metrics in collaboration with the worldwide weather and forecast verification community.
Read the full abstract ▾
All authors Amy McGovern, Taylor Mandelbaum, Daniel Rothenberg, Nicholas Loveday, Corey Potvin, Montgomery Flora, Linus Magnusson, Eric Gilleland, John Allen
Machine Learning
Machine Learning-Augmented Acceleration of Iterative Ptychographic Reconstruction
Bowen Zheng, Katayun Kamdin, David Shapiro et al. (+10 more)
Iterative ptychographic reconstruction
algorithms are widely used for coherent diffractive imaging but can exhibit slow convergence under realistic experimental conditions. We propose a machine learning-augmented approach that accelerates iterative ptychographic reconstruction by introducing a learned fast-forward operator applied during reconstruction. Following an initial warm-up using standard iterations, the fast-forward operator advances the reconstruction toward a more converged state, after which conventional iterative updates are resumed. This strategy preserves the physical consistency and flexibility of established ptychographic solvers while reducing the number of iterations required for convergence. The model is trained on diverse ptychographic
datasets and evaluated on experimental data acquired in a different year, demonstrating robustness and temporal generalization. Compared with conventional iterative solvers, the machine learning-augmented method achieves comparable reconstruction quality while converging faster in terms of Poisson negative log-likelihood, yielding over a two-fold reduction in wall-clock time. The approach has been integrated into an existing reconstruction pipeline and deployed in production at a synchrotron beamline, demonstrating practicality for real-time experimental operation.
Read the full abstract ▾
All authors Bowen Zheng, Katayun Kamdin, David Shapiro, Alexander Ditter, Dayne Sasaki, Emma Bernard, Roopali Kukreja, Petrus H. Zwart, Slavomír Nemšák, Apurva Mehta, Nicholas Schwarz, Alexander Hexemer, Tanny Chavez
Machine Learning
When Less is Enough: Efficient Inference via Collaborative Reasoning
Yilei Chen, Sharut Gupta, Yannis Paschalidis et al. (+2 more)
In this work, we introduce DUET (Dual-model Efficient Two-stage inference), a collaborative inference framework in which a capable model and a lightweight model work together to solve a task. Relying on a single large model to perform end-to-end
reasoning and prediction often incurs substantial inference cost. In contrast, DUET decomposes inference into two stages: the capable model produces a
reasoning signal, and the lightweight model interprets this signal to generate the final answer, allowing
reasoning-intensive computation to be handled by the capable model while non-
reasoning-intensive components are delegated to the lightweight model without sacrificing task performance. To achieve this objective, we propose a length-penalized joint training objective that encourages the capable model to transmit only the information that is sufficient for the lightweight model to solve the task. As a result, DUET maintains strong
reasoning performance with substantially lower inference cost than end-to-end inference using a large model alone, saving up to 60% of the large model's output
tokens on challenging
reasoning benchmarks, including AIME and GPQA.
Read the full abstract ▾
All authors Yilei Chen, Sharut Gupta, Yannis Paschalidis, Ayush Sekhari, Aldo Pacchiano
Machine Learning
Topological Neural Tangent Kernel
Sanjukta Krishnagopal
Graph neural tangent kernels give a principled infinite-width theory for graph neural networks, but inherit a basic limitation of graph models: they see only pairwise structure. Many relational systems contain higher-order interactions that are more naturally represented by simplicial complexes. We introduce the Topological Neural Tangent Kernel (TopoNTK), an infinite-width kernel for simplicial message passing on edge features. TopoNTK combines lower Hodge interactions, capturing graph-like coupling through shared vertices, with upper Hodge interactions, capturing coupling through filled simplices. This makes the kernel sensitive to
topology invisible to graph kernels, allowing complexes with the same graph but different filled simplices to induce different kernels. Beyond expressivity, the Hodge structure gives the kernel an interpretable learning geometry. Edge signals decompose into gradient-like, harmonic, and local circulation components, and the spectrum of the TopoNTK determines how quickly each component is learned. This yields a topological form of spectral bias: components aligned with large-
eigenvalue modes are learned quickly, while global harmonic modes, retained through the residual channel, often lie at smaller
eigenvalues and are learned more slowly. We prove expressivity, Hodge-
alignment, spectral learning, and stability properties, and validate them on synthetic simplicial tasks and DBLP higher-order link prediction. The results show that
topology is not merely extra structure; it can provide coordinates that make relational learning more faithful, interpretable, and effective.
Read the full abstract ▾
Machine Learning
Diffusion Operator Geometry of Feedforward Representations
Kanishka Reddy
Feedforward neural networks transform data through learned representations whose geometry shapes how classes separate and relate across successive layers. We study that geometry through
diffusion operators. Each feature-cloud snapshot is assigned a Gaussian-kernel Markov operator, giving a smooth description of one-step transport between classes from which spectral, boundary, and local
geometric information can be read. We define the empirical class chain, state the condition under which it is an exact Markov quotient, and derive both the corresponding population transition and a simpler overlap chain based on expected class affinities. For balanced shared-covariance Gaussian class-conditional snapshots these affinities have closed forms controlled by a regularized Mahalanobis separation, which yields explicit expressions for leakage and coarse spectral behaviour. We further show that operator observables vary smoothly under feature perturbations, whereas hard neighborhood graphs are controlled by neighbor-order margins. Experiments on CIFAR-10 and CIFAR-100 ResNet-18 representations find that class transport becomes increasingly persistent with depth while retaining structured relations between classes, and that the
diffusion class chain is more stable than its $k$-nearest-neighbor counterpart under matched perturbations.
Read the full abstract ▾
Machine Learning
Almost for Free: Crafting Adversarial Examples with Convolutional Image Filters
Alexander Warnecke and Konrad Rieck
Adversarial examples in machine learning are typically generated using gradients, obtained either directly through access to the model or approximated via queries to it. In this paper, we propose a much simpler approach to craft
adversarial examples, drawing inspiration from insights of explainable machine learning. In particular, we design
adversarial image filters that are based on classic edge detection
algorithms but optimized to deceive learning models. The resulting untargeted attacks are transferable and require only a single pass over the input. Empirically, we find that 3x3 filters already enable success rates between 30% and 80% on different neural networks. Compared to related approaches using generative models for crafting
adversarial examples, we reduce the number of parameters by five orders of magnitude, resulting in a very efficient attack. When investigating the parameters of the learned filters, we observe interesting properties such as a high transferability between models and structures common to classic image filters. Our results provide further insights into the vulnerability of neural networks and their fragility to malicious noise.
Read the full abstract ▾
Machine Learning
Learning to Race in Minutes: Infoprop Dyna on the Mini Wheelbot
Devdutt Subhasish, Henrik Hose and Sebastian Trimpe
Reinforcement Learning (RL) has the potential to enable
robots with fast, nonlinear, and unstable dynamics to reach the limits of their performance. However, most recent advances rely on carefully designed physics-based simulators and domain randomization to achieve successful sim-to-real transfer within reasonable wall-clock time. In this work, we bypass the need for such simulators and demonstrate that Infoprop Dyna, a state-of-the-art uncertainty-aware model-based reinforcement learning (MBRL) framework, can enable
robots to learn directly from real-world interactions. Using Infoprop Dyna, the Mini Wheelbot, an underactuated unicycle
robot, learns to race around a track within 11 minutes of real-world experience.
Read the full abstract ▾
Machine Learning
Learning Discriminators for Resampling in the Ensemble Gaussian Mixture Filter through a Normalizing Flow Approach
Zain Jabbar and Andrey A. Popov
The ensemble Gaussian mixture filter (EnGMF) is a powerful, convergent particle filter capable of medium-to-high dimensional non-linear filtering. The EnGMF relies on a resampling step that can generate physically unrealistic posterior samples, that would subsequently produce physically meaningless forecasts. This work introduces the discriminator-informed resampling procedure, that augments the posterior resampling step with a discriminator that accepts or rejects candidate particles based on their physical plausibility. In this work these discriminators are learned through a normalizing flow approach. Numerical experiments on both the Ikeda map and the Lorenz '63 system show that discriminator informed resampling procedure consistently reduces error relative to the standard EnGMF in low-ensemble regimes.
Read the full abstract ▾
Machine Learning
Networked Information Aggregation for Binary Classification
MohammadHossein Bateni, Zahra Hadizadeh, MohammadTaghi Hajiaghayi et al. (+2 more)
We study networked binary classification on a directed acyclic graph (DAG) where each
agent observes only a subset of the feature columns of a shared
dataset.
Agents act sequentially along the DAG: each receives prediction columns from its parents (if any), augments its local features with these columns, fits a logistic predictor by minimizing binary cross-
entropy (BCE), and forwards its prediction column to its outgoing neighbors. We ask whether this sequential distributed training procedure achieves information aggregation, meaning that some
agent attains small excess loss compared to the best logistic predictor trained with access to all feature columns. This question was studied for linear regression under squared loss by Kearns, Roth, and Ryu (SODA 2026). Extending their guarantees to classification is nontrivial because their analysis relies on quadratic structure that does not directly transfer to BCE with a logistic link. We analyze the resulting sequential logit-passing protocol and prove: (i) an excess loss upper bound of $O(M/\sqrt{D})$ on depth-$D$ paths under the condition that every $M$ contiguous subsequence of $M$
agents collectively observe all features, and (ii) a close lower bound showing instances with excess loss of at least $\Omega(k/D)$ where $k$ is the dimension of the feature space. Together, these results identify network depth as a fundamental bottleneck for information aggregation in networked logistic regression.
Read the full abstract ▾
All authors MohammadHossein Bateni, Zahra Hadizadeh, MohammadTaghi Hajiaghayi, Mahdi JafariRaviz, Shayan Taherijam
Machine Learning · Cross-listed from cs.NE
Benchmarking local Hebbian learning rules for memory storage and prototype extraction
Anders Lansner, Andreas Knoblauch, Naresh B Ravichandran et al. (+1 more)
Associative
memory or content-addressable
memory is an important component function in computer science and information processing, and at the same time a key concept in cognitive and computational
brain science. Many different neural network architectures and learning rules have been proposed to model the
brain's associative
memory while investigating key component functions like figure-ground
segmentation, perceptual reconstruction and rivalry. A less investigated but equally important capability of associative
memory is prototype extraction where the training set comprises distorted prototype instances and the task is to recall the correct generating prototype given a new distorted instance. In this paper we
benchmark associative
memory function of seven different Hebbian learning rules employed in non-modular and modular recurrent networks with winner-take-all dynamics operating on moderately sparse binary patterns. We measure pattern storage and weight information capacity, prototype extraction capabilities, and sensitivity to correlations in data. The original additive Hebb rule comes out with worst capacity, covariance learning proves to be robust but with moderate capacity, and the
Bayesian-Hebbian learning rules show highest capacity in almost all different conditions tested.
Read the full abstract ▾
All authors Anders Lansner, Andreas Knoblauch, Naresh B Ravichandran, Pawel Herman
Machine Learning · Cross-listed from hep-th
Reconstructing conformal field theoretical compositions with Transformers
Haotian Cao, Garrett Merz, Kyle Cranmer et al. (+1 more)
We study the use of
transformers to reconstruct the compositions of tensor products of two-dimensional rational conformal field theories (RCFTs) based on their low-energy spectra. The task is challenging due to its combinatorial nature. The constituent theories are characterized by their central charges and affine Lie
algebra labels. We achieve 98% accuracy in recovering the constituents of tensor products theories constructed from Wess-Zumino-Witten models. We further demonstrate that our method generalizes to CFTs with larger central charge and unseen classes of RCFTs by adding a small number of out-of-domain examples. Our results show that
transformers are effective at this task and point towards a new tool for bulk reconstruction in AdS/CFT.
Read the full abstract ▾
All authors Haotian Cao, Garrett Merz, Kyle Cranmer, Gary Shiu
Machine Learning
Deep Variational Inference Symbolic Regression
James Butterworth, Gevik Grigorian and Alejandro DiazDelaO
Symbolic regression discovers explicit, interpretable equations without assuming a functional form in advance. A
Bayesian approach strengthens this through probability distributions over candidate expressions, thus quantifying uncertainty in the presence of noisy and limited data. Deep Symbolic Regression (DSR) uses a neural network to generate symbolic expressions, but it is designed to identify a single best-fitting expression rather than infer a posterior distribution over models. We introduce Deep Variational Inference Symbolic Regression (DVISR), a variational
Bayesian extension of DSR. DVISR replaces the original reward with the integrand of the evidence lower bound. It also extends the network architecture to output distributions over constants within expressions, enabling posterior inference over both expression trees and their associated constants. We show that DVISR can recover the true posterior in simple settings, both with and without constant
tokens, and we examine how its performance changes as the size of the expression space increases. These results position DVISR as a step toward scalable
Bayesian symbolic regression with uncertainty over full symbolic models.
Read the full abstract ▾
Machine Learning
A dimensional R2 regression metric
Jaesung Yoo, Stefan Lemke, Jian Zhong Guo et al. (+2 more)
R2 score is the standard metric for evaluating regression tasks, offering a normalized magnitude-agnostic measure of accuracy that captures variance. However, R2 has three key limitations: it is limited to at most two dimensional inputs, it reduces the score to a single scalar that hides rich patterns of prediction accuracy, and it is sensitive to low-variance noise channels which can yield large, uninterpretable negative values. We introduce the Dimensional R2 score (Dim-R2), a simple extension of R2 that accepts data of arbitrary dimensionality, provides a multidimensional view of accuracy, and reduces sensitivity to noise. We demonstrate its advantages on both synthetic sinusoidal data and three multidimensional regression
datasets. Dim-R2 offers an interpretable and flexible metric that highlights patterns in regression accuracy, guiding regression modeling.
Read the full abstract ▾
All authors Jaesung Yoo, Stefan Lemke, Jian Zhong Guo, Kanaka Rajan, Adam Hantman
Machine Learning
GEODE: Angle-Adaptive OOD Detection with Universal Scorer Compatibility
Bruno Abrahao
Outlier Exposure (OE) is among the strongest training-based OOD detectors on standard
benchmarks but exhibits scorer-dependent tradeoffs (e.g., strong on MSP, weak on KNN) and requires curated auxiliary data. We show why OE works: its features sit at the same
geometric locus as real near-OOD data, with the boundary-adjacent quartile driving nearly all of OE's gain. OE is boundary calibration, not OOD coverage. GEODE (GEOmetry-preserving DEtection) replicates this calibration synthetically through an angle-adaptive norm loss in which targets scale per-sample with cosine similarity to the nearest class mean, preserving feature geometry where boundary structure matters. Four
theorems grounded in neural collapse justify the design. GEODE works across all seven standard scorers on CIFAR-10 (near-OOD AUROC 89.0-92.3, far-OOD reaching 93.05; no catastrophic failure on any scorer). Since the OOD regime is unknown at deployment, this is the test that matters. GEODE outperforms vanilla CE at matched epoch counts. Combined with OE, GEODE reaches 95.0 MSP / 94.8 KNN on CIFAR-10 and beats OE on every scorer on CIFAR-100. The gains hold on WRN-28-10 (+4.5 Energy, 3 seeds). Unlike methods that push OOD into the classifier null space (e.g., PFS, 14.38 KNN AUROC, worse than random), GEODE's adaptive target preserves the geometry that distance-based scorers depend on.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.DC
SURGE: SuperBatch Unified Resource-efficient GPU Encoding for Heterogeneous Partitioned Data
Shashank Kapadia, Deep Narayan Mishra, Sujal Reddy Alugubelli et al. (+3 more)
We present SURGE, a streaming GPU encoding system deployed in production to generate
embeddings for over 800 million texts across 40,000 logical partitions. Production
embedding pipelines face a tension between logical data partitioning and efficient GPU utilization: processing each partition independently incurs $P$ inter-process communication (IPC) calls whose overhead limits throughput for compute-light models. Our contributions are analytical: (i) a cost model (
Theorem 1) predicting throughput within 2% across three encoders spanning a 15$\times$ parameter range; (ii) a
memory-safety bound (Lemma 3) enabling a streaming two-threshold policy with peak
memory $O(B_{\min} + n_{\max})$ rather than $O(N)$; and (iii) a $\phi$/CV decision framework characterizing when the pattern applies beyond our workload. The naive fix of batching at fixed size requires $O(N)$ peak
memory (32.7 GB at 10M texts; infeasible beyond ~60M on 192 GB nodes), produces no output until all encoding completes, and offers no fault tolerance. SURGE achieves the same throughput with $O(B_{\min} + n_{\max})$ bounded
memory (2.6 GB), 68$\times$ faster time-to-first-output, and crash recovery at SuperBatch granularity. On 10M texts with 4 NVIDIA L4 GPUs, SURGE delivers 26,413 texts/s – matching fixed-batch throughput while using 12.6$\times$ less
memory. We validate on bge-base (109M, $d$=768, error 1.3%) and across log-normal $\sigma$ in {1.0, 1.72, 2.5} (speedup invariant within $\pm$3%), and compare against a partition-batched baseline (PB-PBP-LB), against which SURGE retains a 7% throughput edge and 2.5$\times$ faster TTFO. Complementary engineering – zero-copy Arrow serialization (22-25$\times$ speedup) and async I/O pipelining (up to 93% benefit) – realizes the design but is not the contribution.
Read the full abstract ▾
All authors Shashank Kapadia, Deep Narayan Mishra, Sujal Reddy Alugubelli, Ajay Kumar, Swapnil Yadav, Rishi Bhatia
Machine Learning
LEAP: Layer-wise Exit-Aware Pretraining for Efficient Transformer Inference
Shashank Kapadia, Deep Naryan Mishra, Sujal Reddy Alugubelli et al. (+4 more)
Layer-aligned
distillation and convergence-based early exit represent two predominant computational efficiency paradigms for
transformer inference; yet we establish that they exhibit systematic incompatibility under standard deployment conditions for convergence-based early exit.
Distillation objectives that align intermediate student layers to teacher representations suppress the representational convergence that early-exit mechanisms exploit, rendering such mechanisms ineffective on distilled models. We introduce LEAP (Layer-wise Exit-Aware Pretraining), an auxiliary training objective that reconciles this incompatibility. LEAP requires no architectural modifications; it augments standard
distillation with a single constraint ensuring intermediate layers approximate final-layer representations. LEAP-MiniLM achieves 1.61$\times$ measured wall-clock speedup (batch=1, NVIDIA L4) at $\theta$=0.95, with 91.9% of samples exiting by layer 7 and 1.80$\times$ theoretical layer reduction, where standard distilled models achieve zero effective speedup. We validate across sentence similarity (STS-B: 0.760 $\pm$ 0.006) and
retrieval benchmarks (BEIR), providing operational guidance including latency measurements, decision thresholds, and deployment criteria.
Read the full abstract ▾
All authors Shashank Kapadia, Deep Naryan Mishra, Sujal Reddy Alugubelli, Haoan Wang, Saipraveen Vabbilisetty, Rishi Bhatia, Anupriya Sharma
Machine Learning · Cross-listed from cs.RO
Value Functions for Temporal Logic: Optimal Policies and Safety Filters
Oswin So, William Sharpless, Sylvia Herbert et al. (+1 more)
While Bellman equations for basic reach, avoid, and reach-avoid problems are well studied, the relationship between value optimality and policy optimality becomes subtle in the undiscounted infinite-horizon setting, particularly for more complicated tasks. Greedily maximizing the Q-function can produce policies that indefinitely defer task completion for reach-avoid problems, or equivalently, Until specifications, even when the value function is optimal. Building upon recent results decomposing the value function for temporal logic (TL) into a graph of constituent value functions, we construct non-Markovian policies based on state history that avoid this pathology and prove their optimality with respect to the quantitative robustness score for nested Until, Globally, and Globally-Until specifications. We further show how the Q function can serve as a safety filter for complex TL specifications, extending prior results beyond simple avoid or reach-avoid tasks.
Read the full abstract ▾
All authors Oswin So, William Sharpless, Sylvia Herbert, Chuchu Fan
Machine Learning · Cross-listed from cs.CL
Compared to What? Baselines and Metrics for Counterfactual Prompting
Zihao Yang, Mosh Levy, Yoav Goldberg et al. (+1 more)
Counterfactual prompting (i.e., perturbing a single factor and measuring output change) is widely used to evaluate things like LLM bias and CoT faithfulness. But in this work we argue that observed effects cannot be attributed to the targeted factor without accounting for baseline "meaning-preserving" modifications to text that establish general model sensitivity. This is because every counterfactual edit is a compound treatment that bundles the variable of interest with incidental surface-form variation; this violates treatment variation irrelevance. We observe prediction flip rates on MedQA of 14.9% when we surgically change patient gender. However, this is statistically indistinguishable from the flip rates induced by simply paraphrasing inputs (14.1%). In this case, it would therefore be unwarranted to conclude that the LLM is especially sensitive to patient gender. To account for this and robustly measure the effects of targeted interventions, we propose a framework in which we compare (via statistical testing) differences observed under target interventions to those induced by paraphrasing inputs. We then use this framework to revisit a analysis done on the MedPerturb
dataset, which reported evidence of model sensitivity to patient demographics and stylistic cues. We find that these effects largely dissipate when we account for general model sensitivity, with only 5 of 120 tests reaching statistical significance. Applying the same framework to occupational biography classification, we detect clearly significant directional gender bias, showing that the framework identifies real directional effects even when they are small. We evaluate a range of metrics (aggregate, per-sample distributional, and regression) and find that per-sample metrics are dramatically more powerful than aggregate metrics and regression powerfully and uniquely characterizes effect direction and magnitude.
Read the full abstract ▾
All authors Zihao Yang, Mosh Levy, Yoav Goldberg, Byron C. Wallace
Machine Learning · Cross-listed from cs.CR
LLM Ghostbusters: Surgical Package Hallucination Suppression via Adaptive Unlearning
Joseph Spracklen, Pedram Aghazadeh, Farinaz Koushanfar et al. (+1 more)
Hallucinations remain an unsolved problem for LLMs, and package
hallucinations are a particularly dangerous instance of this phenomenon. Package
hallucinations occur during code generation when a model fabricates non-existent software packages, recommending imports and installation commands for fictional libraries. This creates a critical supply-chain vulnerability; an attacker can proactively register such packages on public registries with malicious payloads that are subsequently installed and executed by developers or autonomous
agents. These
hallucinations enable a class of package confusion attack known as slopsquatting. To address this issue, we present Adaptive Unlearning (AU), a post-deployment framework that surgically suppresses package
hallucinations while preserving general model utility. AU introduces a hybrid
token-level objective that simultaneously reinforces valid outputs and suppresses hallucinated ones. Combined with an adaptive discovery loop that continuously surfaces new
hallucination-inducing contexts without human supervision, AU enables generalization to unseen
prompts and
hallucinations. We demonstrate that AU reduces package
hallucination rates by 88%, while maintaining performance on standard coding
benchmarks. Our analysis shows that distributional changes are concentrated on package-related generations, leaving general coding behavior largely unaffected and confirming that AU's effect is isolated to the targeted distribution. AU relies entirely on model-generated data and requires no human annotation, representing a post-deployment
hallucination mitigation framework.
Read the full abstract ▾
All authors Joseph Spracklen, Pedram Aghazadeh, Farinaz Koushanfar, Murtuza Jadliwala
Machine Learning
Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning
Zhi-Quan Feng, Ying-Jia Lin and Hung-Yu Kao
LoRA adapts large
language models (LLMs) by restricting updates to low-rank subspaces of pre-trained weights. While this substantially reduces training cost, the effectiveness of adaptation critically depends on which subspace is chosen at initialization: a poor initialization that allocates capacity to task-irrelevant directions can severely hinder downstream performance. Existing initialization strategies primarily rely on the intrinsic properties of pre-trained weights, implicitly assuming that weight geometry alone reflects task relevance. However, such criteria overlook how the model interacts with the downstream data distribution. In this work, we formulate LoRA initialization as identifying the degree of impact of directions in parameter space under the target data distribution. We argue that data-aware sensitivity, rather than weight-only magnitude, should govern the choice of adaptation subspaces. Building on this perspective, we propose a Fisher-guided framework that leverages
curvature information induced by downstream data to characterize how parameter perturbations influence model predictions. This perspective yields a principled, task-dependent criterion for selecting LoRA directions that better align adaptation with the target objective. Empirical results across diverse tasks and modalities demonstrate that data-aware initialization consistently and significantly improves downstream performance over existing approaches.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.MA
Separation Assurance between Heterogeneous Fleets of Small Unmanned Aerial Systems via Multi-Agent Reinforcement Learning
Iman Sharifi, Hyeong Tae Kim, Maheed Hatem Ahmed et al. (+2 more)
In the envisioned future dense urban airspace, multiple companies will operate heterogeneous fleets of small unmanned aerial systems (sUASs), where each fleet includes several homogeneous aircraft with identical policies and configurations, e.g., equipage, sensing, and communication ranges, making tactical deconfliction highly complex for the aircraft. This paper aims to address two core questions: (1) Can tactical deconfliction policies converge or reach an
equilibrium to ensure a conflict-free airspace when companies operate heterogeneous fleets of homogeneous aircraft? (2) If so, will the converged policies discriminate against companies operating sUASs with weaker configurations? We investigate a multi-
agent reinforcement learning paradigm in which homogeneous aircraft within heterogeneous fleets operate concurrently to perform package delivery missions over Dallas, Texas, USA. An
attention-enhanced Proximal Policy Optimization-based Advantage Actor-Critic (PPOA2C) framework is employed to resolve intra- and inter-fleet conflicts, with each fleet independently training its own policy while preserving
privacy. Experimental results show that two fleets with distinct, shared PPOA2C policies can reach an
equilibrium to maintain safe separation. While two PPOA2C policies outperform two strong rule-based baselines in terms of conflict resolution, a PPOA2C policy exhibits safer interaction with a rule-based policy, indicating adaptive capabilities of PPOA2C policies. Furthermore, we conducted extensive policy-configuration evaluations, which reveal that
equilibria between similar policy types tend to favor fleets with stronger configurations. Even under similar configurations but different policy types, the
equilibrium favors one of the heterogeneous policies, underscoring the need for
fairness-aware conflict management in heterogeneous sUAS operations.
Read the full abstract ▾
All authors Iman Sharifi, Hyeong Tae Kim, Maheed Hatem Ahmed, Mahsa Ghasemi, Peng Wei
Machine Learning · Cross-listed from cs.CE
Differentiable Multiphysics Co-Optimization via Implicit Neural Representations: A Transient Hamburger-Cooking Benchmark
Navid Zobeiry
The co-optimization of geometry and physical parameters remains challenging in transient multiphysics systems involving moving boundaries, nonlinear material response, phase transitions, and competing objectives. Existing methods often optimize geometry and physical variables separately, rely on simplified steady-state physics, or require offline data generation and reduced design spaces. Here, we present an end-to-end differentiable co-optimization framework that couples an implicit neural representation of geometry with a JAX-compiled Eulerian multiphysics solver. Geometry is represented as a signed distance field using
Fourier-feature-encoded spatial coordinates, while boundary conditions, initial conditions, process controls, and material parameters are optimized within the same differentiable loop. Continuous relaxations represent non-smooth physical transitions while preserving compatibility with reverse-mode automatic differentiation and backpropagation through time. We demonstrate the framework using a transient hamburger-cooking
benchmark, selected as an interpretable multiphysics problem rather than a culinary optimization exercise. The
benchmark combines conductive and convective heat transfer, latent energy effects, moisture and fat transport, shrinkage-induced geometry
evolution, evolving contact boundary conditions, flipping-induced boundary-condition changes, and competing quality objectives. Results show that geometry-only optimization modifies shape to relieve thermal bottlenecks, while joint co-optimization distributes the design response across geometry, material state, process variables, and boundary conditions through gradients propagated over the full transient rollout.
Read the full abstract ▾
Machine Learning
Finite-Sample Analysis of Elimination in Active Hypothesis Testing
Ziyuan Lin, Hoang Ngoc Nguyen, Jie Xu et al. (+1 more)
A fixed-confidence, finite-sample problem of active hypothesis testing arises in many safety-critical applications. Situated in the context of sequential hypothesis testing, this paper studies the effect of hypothesis elimination on the stopping time. We introduce an elimination-augmented Track-and-Stop
algorithm, in which champion-specific active-opponent sets are progressively pruned, and sensing effort is reallocated toward the surviving alternatives. Our analysis derives a non-asymptotic upper bound on the expected stopping time. The gain in finite-sample from elimination appears on the scale of the non-leading term, resulting from tighter tracking and concentration constants on the reduced hypothesis set. Furthermore, we introduce an aggressiveness parameter to modulate the trade-off between faster elimination and weaker confidence guarantee. An experimental study on synthetic Gaussian instances confirms the theoretical predictions.
Read the full abstract ▾
All authors Ziyuan Lin, Hoang Ngoc Nguyen, Jie Xu, Ivan Ruchkin
Machine Learning
Continual Learning of Feedback-based Molecular Communication
Siddhant Setia, Junichi Suzuki and Tadashi Nakano
This paper proposes and evaluates a new performance estimation method that leverages continual learning (CL)
algorithms to carry out sequential simulation experiments for a feedback-based molecular communication protocol. As the protocol is sequentially examined in various experimental settings, the proposed CL-based performance
estimators incrementally learn a series of unexperienced estimation tasks without compromising those that have been learned in the past. They are designed to work on a standard neural network architecture by customizing regularization and replay strategies in the loss function. Experimental results demonstrate that the proposed
estimators can effectively learn on a continuous stream of simulation results and enhance the baseline neural network by improving estimation accuracy at a variety of computational costs. This paper's contribution is to establish the implications of CL in the field of molecular communication.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
CLEAR: Revealing How Noise and Ambiguity Degrade Reliability in LLMs for Medicine
Kevin H. Guo, Chao Yan, Avinash Baidya et al. (+5 more)
Medical large
language model (LLM) evaluations rely on simplified, exam-style
benchmarks that rarely reflect the ambiguity of real-world medical inquiries. We introduce the CLinical Evaluation of Ambiguity and Reliability (CLEAR) framework, which assesses how decision-space presentation, ambiguity, and uncertainty affect LLMs'
reasoning on medical
benchmarks. CLEAR systematically perturbs (1) the number of plausible answer options, (2) the presence of a ground truth or abstention option, and (3) the semantic framing of answer options. Applying CLEAR on three
benchmarks evaluated across 17 LLMs reveals three notable limitations of existing evaluation methods. First, increasing the number of plausible answers degrades a model's ability to identify the correct answer and abstain against incorrect ones. Second, this lack of caution intensifies as the framing of abstention shifts from assertive rejection like "None of the Above" to uncertainty admission like "I don't know" (IDK). Notably, just including IDK in the answer space increases incorrect answer selections. Lastly, we formalize the performance gap between identifying the correct answer and abstaining from incorrect ones as the humility deficit, which worsens with model scale. Our findings reveal limitations in standard medical
benchmarks and underscore that scaling alone does not resolve LLM reliability issues.
Read the full abstract ▾
All authors Kevin H. Guo, Chao Yan, Avinash Baidya, Katherine Brown, Xiang Gao, Juming Xiong, Zhijun Yin, Bradley A. Malin
Machine Learning · Cross-listed from stat.ME
Pi-Change: A Prior-Informed Multiple Change Point Detection Algorithm
Jonathon Jacobs and Shanshan Chen
Statistical change point (CP) detection methods typically rely on likelihood-based inference and ignore contextual information about plausible CP locations beyond the observed sequence. Although informative priors provide a natural way to incorporate such information, general and computationally efficient methods for doing so are lacking, especially for multiple CP detection. To address this gap, we propose a prior-informed CP detection
algorithm (Pi-Change) that incorporates prior information on CP locations through a time-varying penalty term. We prove that the proposed penalty can be embedded in the Pruned Exact Linear Time framework while preserving the dynamic programming recursion and
pruning rule required for efficient multiple CP detection. Across simulation studies and three time-series applications, Pi-Change discourages spurious CPs unsupported by prior information, remains robust to prior misspecification, and improves detection accuracy. More broadly, Pi-Change extends multiple CP detection beyond purely data-driven fitting by incorporating partial prior knowledge in a computationally efficient and interpretable way. It is particularly useful when CPs arise from heterogeneous mechanisms or are associated with known external events, helping quantify the delay between an event and the resulting structural change.
Read the full abstract ▾
Machine Learning
Physiology-Aware Masked Cross-Modal Reconstruction for Biosignal Representation Learning
Hao Zhou, Simon A. Lee, Cyrus Tanade et al. (+12 more)
Biosignals acquired from different locations on the body often provide temporally ordered views of the same underlying physiological process. However, most existing self supervised learning methods treat these signals as interchangeable views, overlooking the directional temporal dynamics that link them. A canonical example is the relationship between electrocardiography (ECG), which captures the electrical activation initiating each heartbeat, and photoplethysmography (PPG), which records the resulting peripheral pulse delayed by vascular dynamics. To capture this structured relationship, we introduce xMAE, a biosignal pretraining framework that leverages masked cross modal reconstruction across temporally ordered biosignals as a training time constraint to encourage physiologically meaningful timing structure in the learned representations. We show that pretraining with xMAE yields representations that outperform both unimodal and
multimodal baselines on 15 of 19 downstream tasks, including cardiovascular outcome prediction, abnormal laboratory test detection, sleep staging, and demographic inference, while generalizing across devices, body locations, and acquisition settings. Further analysis suggests that the ECG PPG timing structure is reflected in the learned PPG representations. More broadly, xMAE demonstrates the effectiveness of incorporating temporal structure into
multimodal pretraining when signals observe different stages of a shared underlying process. Code is available at https://github.com/hzhou3/xMAE.
Read the full abstract ▾
All authors Hao Zhou, Simon A. Lee, Cyrus Tanade, Keum San Chun, Juhyeon Lee, Migyeong Gwak, Megha Thukral, Justin Sung, Eugene Hwang, Mehrab Bin Morshed, Li Zhu, Viswam Nathan, Md Mahbubur Rahman, Subramaniam Venkatraman, Sharanya Arcot Desai
Machine Learning
Robust volatility updates for Hierarchical Gaussian Filtering
Christoph Mathys, Nicolas Legrand, Peter Thestrup Waade et al. (+2 more)
Hierarchical Gaussian Filtering (HGF) networks allow for efficient updating of posterior distributions (beliefs) about hidden states of an
agent's environment. HGF parent nodes can target the mean or variance of their children. New information entering at input nodes leads to a cascade of belief updates across the network according to one-step update equations for each node's mean and precision (inverse variance). However, the original form of the update equations for variance-targeting parents(
volatility coupling) can in some regions of parameter space lead to negative posterior precision, a logical impossibility which causes the updating
algorithm to terminate with an error. In this report, we introduce a modified quadratic approximation to the variational energy of
volatility-coupled nodes that avoids negative posterior precision. The key idea is to interpolate between two quadratic expansions of the variational energy: one at the prior prediction and one at a second mode whose location is obtained in closed form via the Lambert W function. The resulting update equations are robust across the entire parameter space and faithfully track the variational posterior even for large prediction errors.
Read the full abstract ▾
All authors Christoph Mathys, Nicolas Legrand, Peter Thestrup Waade, Nace Mikus, Lilian Aline Weber
Machine Learning
Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey
Hugo Attali, Nathalie Pernelle, Davide Buscaldi et al. (+1 more)
Graph Neural Networks are powerful models for learning from graph-structured data, yet their effectiveness is often limited by two critical challenges: over-squashing, where information from distant nodes is excessively compressed, and over-smoothing, where repeated propagation makes node representations indistinguishable. Both phenomena stem from the interaction between message passing and the input
topology, ultimately degrading information flow and limiting the performance of GNNs. In this survey, we examine graph rewiring techniques, a class of methods designed to modify the graph
topology to enhance information propagation in GNNs. We provide a comprehensive review of state-of-the-art rewiring approaches, delving into their theoretical underpinnings, practical implementations, and performance trade-offs.
Read the full abstract ▾
All authors Hugo Attali, Nathalie Pernelle, Davide Buscaldi, Fragkiskos D. Malliaros