Machine Learning
Totally Positive Matrices and the Highest-Order Coefficients of the Characteristic Polynomial
Tiago Closs and Leandro Farina
We investigate the extent to which totally positive
matrices can be distinguished through the highest-order coefficients of their characteristic
polynomials. To identify the most informative coefficients, we also employed neural-network classifiers together with feature-attribution methods. Using
datasets built from several structured totally positive families, including products of positive bidiagonal
matrices, Vandermonde
matrices, and Cauchy
matrices, we find that the coefficients (a_{n-1}, a_{n-2}, a_{n-3}) already contain strong discriminatory information for separating totally positive from non-totally positive
matrices in dimensions 5, 10, and 30. The resulting separation is markedly nonlinear and admits a natural
geometric description in the corresponding three-dimensional coefficient space by means of Mahalanobis ellipsoids. These ellipsoids enclose the totally positive samples while excluding most non-totally positive ones. Moreover, different structured totally positive families exhibit distinct ellipsoidal signatures, and the separation between these signatures increases with the dimension. These observations lead us to formulate a
conjecture on the
geometric separation of structured totally positive families in the space determined by the three highest-order characteristic coefficients.
Read the full abstract ▾
Machine Learning
Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints
Thomas MacDougall, Maksim Kuznetsov, Roman Schutski et al. (+5 more)
Structure-based drug design (SBDD) leverages the 3D structure of
protein targets, often complemented by other spatial constraints, to generate candidate binding molecules. While
diffusion models have dominated as a leading paradigm for high-quality 3D molecule generation, LLM-based methods are rapidly emerging in molecular design and have shown competitive performance in pocket-conditioned molecular generation. However, their ability to reason about physics and 3D spatial environments is largely underexplored. In this work, we systematically analyze whether current general-purpose LLMs are capable of navigating complex 3D constraints compared to established baselines such as specialized
diffusion models. We consider 3D ligand generation conditioned on
protein pockets together with ligand- and interaction-derived spatial constraints, including anchor fragments, pharmacophore points, and mandatory pocket-ligand interactions. To enable this evaluation, we introduce 3D-Fit - a
token-efficient benchmarking strategy for assessing LLM performance on multi-conditioned spatial molecule generation. Our findings reveal a clear pattern in LLM spatial capabilities: while they still lag behind state-of-the-art approaches, they are promising and can handle multiple spatial constraints simultaneously, enabling scaling to heterogeneous setups.
Read the full abstract ▾
All authors Thomas MacDougall, Maksim Kuznetsov, Roman Schutski, Rim Shayakhmetov, Maxim Malkov, Vladimir Aladinskiy, Alex Aliper, Alex Zhavoronkov
Machine Learning · Cross-listed from cs.RO
Isaac Sim-to-Real: Reinforcement Learning based Locomotion for Quadrupeds
Jordan Dowdy and Jean Chagas Vaz
Learning-based approaches to locomotion have risen in popularity in recent years, showing the capability for complex legged locomotion and whole-body control. Reinforcement learning (RL), the primary learning-based approach for locomotion, often utilizes a high-performance simulation tool, providing a controlled and efficient training and development environment. However, policies that perform well in simulation frequently encounter unexpected challenges when deployed on a physical system, known as the sim-to-real gap. This work presents a robust RL locomotion framework capable of whole-body control. The proposed RL framework utilizes Nvidia's new set of simulation tools, Isaac Sim, and its companion RL framework, Isaac Lab, for training, achieving a zero-shot sim-to-real policy. The performance of our policy is validated on physical hardware using the Unitree Go1, with experimental results showing similar velocity tracking performance to the quadruped's integrated controller, with a greater ability to recover from large disturbances, and achieve linear velocities of 2.0 m/s and angular velocities of 1.8 rad/s.
Read the full abstract ▾
Machine Learning
Manifold-Constrained Hyper-Connections for Parameter-Efficient Finetuning
Valentijn Oldenburg, Floris de Kam, Bente Zuijdam et al. (+5 more)
Finetuning methods for foundation models usually change weights,
prompts, or hidden states, while leaving the residual
topology fixed. We ask whether residual
topology itself can become a finetuning object. To study this, we adapt
manifold-constrained hyper-connections (mHC), recently introduced for pre-training, to frozen-backbone finetuning. mHC turns a
Transformer into an input-dependent multi-stream residual architecture, routing representations through multiple streams at every sub-layer. Across mHC variants, we find that dynamic residual routing can finetune
Transformers, but that its role differs from pre-training: by preserving stream mixing and learning only how sub-layers access streams, loss is improved and trainable parameters are reduced. Overall, our results identify residual routing as a promising architectural axis for efficient finetuning of foundation models.
Read the full abstract ▾
All authors Valentijn Oldenburg, Floris de Kam, Bente Zuijdam, Lieve Eberson, Nicky van Zutphen, Stef de Wildt, Ivo Verhoeven, Cees Snoek
Machine Learning · Cross-listed from cs.NI
ClouDens: Operational Context-Aware Anomaly Detection for Large-scale Cloud System Monitoring
Thu T. H. Doan, Mohammad Saiful Islam, Andriy Miranskyy et al. (+3 more)
With the rapid growth of cloud computing infrastructures in scale and complexity, network monitoring for Large-scale Cloud Systems (LCSs) has become increasingly challenging, requiring automated and reliable anomaly detection to maintain service availability. Modern LCSs continuously generate telemetry logs from distributed cloud services, producing high-dimensional multivariate time series that capture system operations. Detecting anomalies in this context is difficult due to extreme dimensionality, complex dependencies among distributed components, and severe sparsity from intermittently active services. Taking these challenges into account, we first conduct an empirical study on telemetry logs from the IBM Cloud Console platform, and then propose ClouDens, an anomaly detection framework tailored to LCS monitoring that leverages operational-context attributes encoded in the telemetry log schema to improve detection accuracy and early identification of anomalies. ClouDens partitions high-dimensional telemetry logs into domain-guided subsets, constructs a context-aware graph modeling operational service dependencies, and employs Spatio-Temporal Graph Neural Networks for
forecasting-based anomaly detection. We evaluate ClouDens on the recently released IBM Cloud Telemetry
Dataset and provide practical insights into designing reliable anomaly detection solutions for LCS monitoring. Results show ClouDens achieves higher NAB scores in count-based telemetry features, indicating more accurate, earlier anomaly detection with broader coverage than a GRU-based model. Our study further reveals that telemetry feature subsets, operational-context modeling, scoring strategies, and sparsity imputation all substantially influence detection performance, offering practical guidance for designing and fairly benchmarking anomaly detection approaches for LCS monitoring.
Read the full abstract ▾
All authors Thu T. H. Doan, Mohammad Saiful Islam, Andriy Miranskyy, Ngoc-Thanh Nguyen, Rogardt Heldal, Patrizio Pelliccione
Machine Learning · Cross-listed from stat.ML
COVAriance-Induced Fairness Gap Penalty for Subgroup-Fair Clustering
Kyungseon Lee, Hankyo Jeong, Kunwoong Kim et al. (+2 more)
Fair clustering aims to make cluster assignments independent of sensitive attributes, but this goal becomes challenging when multiple sensitive attributes jointly define many subgroups. In such settings, directly extending existing fair clustering
algorithms is computationally expensive or numerically unstable, especially when the number of subgroups grows exponentially and some subgroups contain only a few instances. To address these challenges, we define a subgroup-
fairness gap for clustering and derive a covariance-based surrogate that exactly matches this gap. We then introduce a continuous relaxation of the surrogate, enabling efficient gradient-based optimization and yielding our proposed
algorithm, COVA-FC. We also show that subgroup
fairness alone does not imply marginal
fairness, and extend our framework to capture a subgroup-marginal-
fairness gap. Experiments on
benchmark datasets show that COVA-FC achieves competitive cost-
fairness trade-offs and improves computational efficiency over existing baselines in both subgroup and higher-order marginal settings.
Read the full abstract ▾
All authors Kyungseon Lee, Hankyo Jeong, Kunwoong Kim, Kwanho Lee, Yongdai Kim
Machine Learning · Cross-listed from cs.CL
How Does Alignment Tuning Shape Representations of Sycophancy and Related Cue-Induced Biases in LLMs?
Prakhar Gupta, Terry Jingchen Zhang, Florent Draye et al. (+2 more)
Modern LLMs are alarmingly susceptible to surprisingly simple immaterial changes of input
prompts: a casual hint, an incorrectly labeled few-shot example, or a fake prior assistant turn often flips an originally correct answer. We study where this susceptibility, spanning sycophancy and related cue-induced biases, lives inside the model. Across five model families and seven bias types, we extract a per-bias direction from hidden states and triangulate it through three measures: probing, leave-one-
dataset-out (LODO) transfer, and causal intervention. The susceptibility is largely shaped by
alignment tuning rather than pretraining: pretrained base models generally cave much less to these biases, and their activations carry much weaker cue-specific signal beyond question content. Within aligned models, each bias has a coherent linear direction that we can both decode and steer along, recovering the unbiased answer across every family we test. The biases do not collapse into a single shared representation, however: cross-bias overlap is model-specific, and even behaviorally similar biases occupy different directions. The same intervention also provides a proof-of-concept debiasing tool, recovering a meaningful share of bias-induced errors while preserving most correct answers across all instruct families. Cue-induced bias is therefore best understood not as a single flaw in LLMs but as a family of causally effective linear directions that are largely shaped by
alignment tuning.
Read the full abstract ▾
All authors Prakhar Gupta, Terry Jingchen Zhang, Florent Draye, Bernhard Schölkopf, Zhijing Jin
Machine Learning
LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks
Tianzhu Ye, Li Dong, Guanheng Chen et al. (+4 more)
Reinforcement learning (RL) on open-ended tasks compresses an LLM's rubric-based evaluation into a scalar reward, discarding rich textual feedback and conflating responses with distinct quality profiles. We propose Experiential Learning (EL), which repurposes the feedback model from an LLM-as-a-Judge into an LLM-as-a-Coach. The coach distills its assessment of each on-policy response into transferable experiential knowledge, which conditions a teacher model and is internalized by the policy through on-policy context
distillation. Compared with scalar rewards, this higher-bandwidth feedback channel provides dense supervision and preserves fine-grained preferences among high-quality responses. Across two policy families, with feedback from the policy itself or a proprietary model, EL consistently outperforms rubric-based RL on held-out and unseen open-ended tasks. Notably, EL generalizes better beyond the training distribution, and mitigates reward hacking. These findings establish experiential knowledge as a richer and more generalizable learning signal for post-training on non-verifiable tasks.
Read the full abstract ▾
All authors Tianzhu Ye, Li Dong, Guanheng Chen, He Zhu, Xun Wu, Shaohan Huang, Furu Wei
Machine Learning
Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator
Mateusz Piechocki, Alessandro Capotondi and Marek Kraft
On-device model adaptation is essential to enable lifelong personalization on resource-constrained hardware, but compute, power, and
memory limitations of such devices make end-to-end backpropagation impractical for modern deep neural networks. This work proposes a heterogeneous adaptation pipeline that repurposes a commercial edge AI inference accelerator, Hailo-8L, for frozen-backbone feature extraction during on-device training. The computational graph is partitioned so that the pre-trained backbone is quantized to INT8 and run on the accelerator, while only a lightweight FP32 classification head is fine-tuned on the host CPU, enabling frequent, energy-efficient in-field updates with most weights remaining fixed. Across multiple architectures and
datasets, this pipeline achieves up to 15.4x faster wall-clock training time compared to a Raspberry Pi 5 CPU baseline, offers competitive throughput in favorable settings, and consistently reduces energy per sample. Post-training quantization restoration is shown to be crucial for preserving the quality of accelerator-generated features and mitigating accuracy loss in quantization-sensitive architectures. Overall, the results demonstrate a practical approach to efficient on-device adaptation using inference-oriented edge accelerators. The implementation is available at https://github.com/MatPiech/accelerator-training.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
SciForma: Structure-Faithful Generation of Scientific Diagrams
Yuxuan Luo, Peng Zhang, Xinjie Zhang et al. (+3 more)
Structural fidelity is essential to scientific methodology diagrams. To communicate research logic, these diagrams must faithfully render components, directional relations, and textual annotations. Since a single error, such as a reversed arrow or an unreadable equation, can invalidate the entire figure, structural fidelity is inherently conjunctive: correctness on one axis cannot compensate for failure on another. Current open-source models fail to satisfy this criterion. Supervised fine-tuning (SFT) learns plausible layouts but cannot reliably ensure structural correctness, while scalar reward-based post-training obscures which structural dimension has failed. To address this, we introduce SciForma, a framework for the structure faithful generation of scientific methodology diagrams. Specifically, SciForma decomposes diagram quality into three structural axes: Component, Arrow, and Text, guided by a structural inventory. Built on this foundation, we curate SciFormaData-700K for structured training and SciFormaBench-2K for logic-verified evaluation. To close the gap left by SFT, we develop Multi-Dimensional Conjunctive Preference Optimization (M-DPO), which enforces simultaneous correctness across all axes and adaptively routes gradients to the most deficient dimension in post-training. The same structural inventory also enables iterative editing at inference time to correct residual errors. This combination allows SciForma-9B to exceed all open-source baselines and GPT-Image-1.5 on both SciFormaBench-2K and AIBench, bringing open scientific diagram generation close to proprietary-level structural fidelity. Our code and data will be available at: https://github.com/microsoft/SciForma.
Read the full abstract ▾
All authors Yuxuan Luo, Peng Zhang, Xinjie Zhang, Xun Guo, Zhouhui Lian, Yan Lu
Machine Learning
The Label Complexity of Useful Class-Conditional Prediction Sets under Distribution Shift
Weijia Han, Lisha Qu, Tianxin Zhou et al. (+2 more)
Prediction sets can make deployed classifiers safer by returning several plausible labels when a single prediction is uncertain. Their value depends on classwise reliability: average coverage can meet its target while rare or difficult classes fail repeatedly. This concern is sharper after distribution shift, when calibration labels come from a source environment but reliability is needed on the target. We ask what labeled source data and unlabeled target inputs reveal about class-conditional prediction sets, and when target labels are necessary. Under unrestricted joint shift, two target laws can produce the same observable data while requiring different classwise thresholds; any label-free rule covering both must enlarge its sets on one law. We give a labeled target audit that estimates the missing
quantiles with a simultaneous guarantee. Probability-scale error is invariant to increasing score transformations, and threshold recovery follows under local regularity. At fixed confidence, achieving threshold tolerance $\varepsilon$ with fixed, nonadaptive class-stratified labeled pairs has total complexity $\Theta(K\varepsilon^{-2}\log K)$, or $\Theta(\varepsilon^{-2}\log K)$ labels per class under equal allocation. Class imbalance creates a separate acquisition cost; for foreground class probabilities of order $1/K$, the mixed-stream label complexity is also $\Theta(K\varepsilon^{-2}\log K)$ at fixed confidence. Experiments on action-recognition and image shifts show that marginal coverage can conceal severe class failures and that source classwise calibration depends on the shift. The results connect the information available at deployment to the target labels needed for useful class-conditional prediction.
Read the full abstract ▾
All authors Weijia Han, Lisha Qu, Tianxin Zhou, Zhenda Li, Liying Liang
Machine Learning · Cross-listed from cs.AI
WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting
Zhaokai Wang, Tianlin Gui, Jiayuan Rao et al. (+3 more)
Predicting a football match before kickoff requires more than knowing past results: a model must use changing information and make a clear prediction before the answer is available. We present WorldCupArena, a dynamic
benchmark for
language models and deep-research
agents. The 2026 FIFA World Cup is its first evaluation, and the same process can be reused for future leagues and cups. Before each match, a model either receives a common evidence package or searches for information itself. It predicts the result and score, likely players and events, match statistics, and the outcome of the competition. After the match, these predictions are compared with the recorded result. We report result accuracy, exact-score accuracy, and a scoreline score that gives some credit when a predicted score is close but not exact, together with scores for the other prediction tasks. Across systems, similar result accuracy can mask larger differences in detailed predictions. Four systems predicted champion Spain, and two of them also recovered the exact final pairing. Compared with betting-
market and human-fan baselines, the best system shows only small gains in result and exact-score accuracy, but a clearer gain in Scoreline. New schedules can be added as they begin, allowing the
benchmark to evaluate future models without using outcomes that are already known. Code, predictions and evaluation scripts will be publicly released.
Read the full abstract ▾
All authors Zhaokai Wang, Tianlin Gui, Jiayuan Rao, Shangzhe Di, Yihong Tang, Dingli Liang
Machine Learning
CriPO: Enhancing Rubric-based RL via Self-Distillation
Mingxuan Xia, Yuhang Yang, Chao Ye et al. (+7 more)
Rubric-based Reinforcement Learning (RL) has recently shown promise in improving Large
Language Models (LLMs) on open-ended tasks. A widely recognized limitation of rubric-based RL is limited exploration: criteria that no rollout manages to satisfy (Unexplored Criteria) receive no optimization signal. Recent methods address this by incorporating rubric information as external guidance during rollout generation, yet they introduce a train-inference mismatch: the policy is optimized on rollouts produced under external guidance while this guidance is absent at inference time, causing error accumulation through autoregressive decoding. Moreover, these exploration-focused approaches overlook a fundamentally different failure mode that we term Suppressed Criteria—criteria that are satisfied by some rollouts yet whose learning signals might be lost during optimization because scalar reward aggregation assigns them non-positive aggregate advantages. Our analysis reveals that suppressed criteria constitute a persistent and non-negligible failure mode—over 25% of samples exhibit this issue throughout training. To simultaneously address both unexplored and suppressed criteria without introducing training-inference mismatch, we propose Criterion-Distilled Policy Optimization (CriPO), which enhances rubric-based RL via on-policy self-
distillation. For unexplored criteria, CriPO constructs a behavior-injection teacher and computes a filtered forward-KL loss to inject missing behaviors into the policy. For suppressed criteria, CriPO uses a counterfactual teacher to locate criterion-relevant
tokens in negative-advantage rollouts, and corrects their advantages in GRPO to preserve useful patterns. Experiments on medicine and science
benchmarks demonstrate that CriPO outperforms existing rubric-based RL methods, e.g., achieving an average gain of 3.3 points over GRPO on Qwen3-4B.
Read the full abstract ▾
All authors Mingxuan Xia, Yuhang Yang, Chao Ye, Shuai Zhu, Shenzhi Yang, Guangcheng Zhu, Yuhang Zhang, Cheng Peng, Haobo Wang, Chenglong Wang
Machine Learning
SelectInfer: Selective Neuron Loading and Computation for On-Device LLMs
Huzaifa Shaaban Kabakibo, Eric Schniedermeyer, Artem Burchanow et al. (+1 more)
Large
Language Models (LLMs) have demonstrated remarkable capabilities across a range of Natural
Language Processing (NLP) tasks, but their high computational and
memory demands pose significant challenges for deployment on resource-constrained edge devices. Existing approaches to model compression and optimization often rely on coarse-grained
pruning or quantization, which can compromise accuracy or require re-training and fine-tuning. In this work, we introduce SelectInfer, a
neuron-level optimization framework that enables efficient LLM inference on edge devices through selective
neuron loading and computation. By profiling and identifying both task-specific and general-purpose
neurons using an offline LLM profiler, SelectInfer implements two key optimizations: selective loading, which reduces
memory footprint by selectively loading a subset of
neurons that were identified to be most important during the offline stage, and selective computation, which dynamically computes only the most relevant
neurons at runtime. Evaluation across multiple
datasets shows that SelectInfer achieves significant reductions in
memory footprint and computation while preserving task performance, making it a practical step towards enabling LLM deployment on edge devices
Read the full abstract ▾
All authors Huzaifa Shaaban Kabakibo, Eric Schniedermeyer, Artem Burchanow, Lin Wang
Machine Learning
Generalised Bellman recurrence and three dualities in sequential decision-making
Fernando E. Rosas, David Hyland and Daniel Polani
What gives the Bellman equation its form? We show that the recursive properties of optimal value functions follow from three conditions: that the dynamics decomposes through sufficient statistics, that the return decomposes recursively, and that the aggregation of uncertainty is compatible with both. When all three conditions hold on a common state, the Bellman equation arises from their mutual consistency; when one fails, tractability can often be recovered by augmenting the state or by deforming return or dynamics. The same conditions are shown to give rise to three dualities: one between probability and return, one between return and aggregation, and one between aggregation and probability. Our framework reveals these dualities as arising from a single construction, unifying methods developed separately across reinforcement learning, control, and decision theory.
Read the full abstract ▾
Machine Learning
Sobek: Streaming Equivariant Tensor Product Convolutions
Vladimir Chorošajev and Cédric Bény
Equivariant graph neural networks repeatedly apply edge-conditioned tensor-product convolutions over graph edges. Conventional implementations materialize edge-specific weights, messages, and adjoints, causing tensor-product workspace and
memory traffic to grow rapidly with graph size and operator width. This limits feasible workloads and can prevent larger problems from fully utilizing the GPU. We show that these edge-sized intermediates are artifacts of the execution schedule, not requirements of the equivariant operator. By reassociating radial projection, spherical-harmonic coupling, and graph aggregation, edge-local products can be consumed directly into bounded receiver-side state. The resulting streaming formulation preserves fully connected multiplicity mixing and extends through forward, backward, and double backward. We implement this formulation in Sobek, a generated-CUDA backend, and evaluate it across edge-scaling regimes and varied feature structures. Across two operator families and all three differentiation orders, Sobek is faster in all 75 capacity-matched comparisons, with speedups ranging from $1.2\times$ to $49.7\times$, and reduces peak allocated
memory by up to 99%. It also executes workloads up to two orders of magnitude beyond OpenEquivariance's capacity while retaining near-peak throughput. These results show that edge-scaled tensor-product workspace is a property of the conventional schedule, not of equivariant convolution itself.
Read the full abstract ▾
Machine Learning
SGN: A Similarity-based Generative Network for Data Generation under Distribution Shift
Jiaqi Zhu, Xincheng Chen, Yuncheng Wu et al. (+2 more)
Generative models trained on a source domain often produce samples that are poorly aligned with shifted target domains, limiting their effectiveness for target-domain data augmentation. Although target-specific adaptation can reduce this mismatch, it typically requires additional optimization and domain-specific parameters. We propose a Similarity-based Generative Network (SGN), a reusable framework that is trained once on labeled source data and applied to new target domains without parameter updates. SGN learns a latent space structured by label-induced pairwise similarities while preserving reconstructive information through an encoder-decoder architecture. At generation time, a small labeled representative set from the target domain is encoded and combined in the learned latent space, allowing the generated samples to inherit target-specific characteristics while maintaining class consistency. We further analyze the realizability and dimensionality requirements of the proposed similarity structure. Experiments on image and tabular
datasets demonstrate the effectiveness of SGN for target-guided data augmentation under source-to-target distribution shifts.
Read the full abstract ▾
All authors Jiaqi Zhu, Xincheng Chen, Yuncheng Wu, Zhaojing Luo, Beng Chin Ooi
Machine Learning · Cross-listed from cs.AR
Hardware Mechanisms to Dynamically Throttle AI Performance
Haiyue Ma, Lauren Malek, Joseph Forzani et al. (+1 more)
As more capable AI models are increasingly integrated into critical computer systems, the lack of control over AI intent motivates safety mechanisms. Existing software safeguards impose only behavioral constraints that can potentially be bypassed by sufficiently intelligent models. While hardware-level safety enforcement has been recognized as an essential last line of defense, few mechanisms have been proposed beyond policy regulations on unauthorized accesses or coarse full-chip shutdown. What is missing is a fine-grained, dynamic intervention mechanism at the architecture level. In this paper, we introduce a set of microarchitecture knobs which dynamically control the available hardware resources to limit AI performance at runtime. We evaluate candidate knobs spanning the GPU
memory subsystem, across capacity, bandwidth, latency and frequency dimensions, and narrow down to four strong candidates: L2 size, L2 latency, L2 bandwidth, and shared
memory port access rate. To minimize new logic and extra design cost, we build all four mechanisms from well-established microarchitectural primitives: cache way masking, credit-based rate limiting, latency insertion, and bank arbitration. We show that these knobs achieve high performance sensitivity (up to 80% performance cut at 1/8 resource availability), negligible implementation cost (<~10K flip flops), fast stabilization after dynamic throttling (5-80K cycles), and minimal collateral impact on the rest of the chip. Further, multi-knob analysis reveals combinations of knobs that amplify the performance degradation beyond the effect of each knob individually, which enables a broader range of performance targets.
Read the full abstract ▾
All authors Haiyue Ma, Lauren Malek, Joseph Forzani, David Wentzlaff
Machine Learning · Cross-listed from cs.CR
Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security
Devina Jain, David Hartmann and Chuan Li
LLM-based
agents process external content, exposing them to
prompt injection and multi-turn manipulation. We present a 21-scenario
benchmark for adaptive cross-session attacks against fresh-session LLM defenders: an autonomous LLM attacker observes prior defender responses and pivots across rounds, while each defender response is evaluated as a fresh interaction. A controlled 3 x 3 attacker-defender
matrix contains 945 battles. Restricting scoring to the first round yields 0-1% attack success rate (ASR); allowing 15 rounds yields 7.9-16.8%. Pooling three attacker LLMs uncovers 1.7-2.2 times as many unique successful inputs as the best single attacker, at three times the battle budget. Aggregate rates conceal opposing scenario-specific weaknesses in session-secret protection and authority handling, preserved in two higher-sample evaluations. On six scenarios, adding one provenance paragraph reduces ASR from 110/270 to 70/270, with selective effects across tasks. History and defender-state controls, together with frozen replay, characterize how the interaction protocol changes the result. A competition adds 18,422 held-out battles on a fixed gpt-oss-20b backbone and complementary benign-task evaluations. The
benchmark exposes attacker and defender models, harnesses, scenarios, session state, and interaction budgets as configurable choices for systematic security evaluation.
Read the full abstract ▾
Machine Learning
SEE: Structure-aware Exploring & Exploiting for Long-horizon GUI Agent Trajectory Synthesis
Zhuohang Fan, Beichen Zhang, Yuanfa Li et al. (+4 more)
Graphical User Interface (GUI)
agents powered by
vision-
language models hold promise for automating real-world mobile tasks. However, progress is limited by the lack of high-coverage, long-horizon interaction trajectories collected from element-rich and rapidly evolving apps. Existing pipelines often rely on costly human demonstrations or on-policy framework, which tends to over-sample common flows while missing rare transitions and complex multi-step procedures. To address this problem, we propose SEE, a two-stage data synthesis framework consisting of (i) an efficient exploration stage that builds an explicit UI transition graph over screens and elements, and (ii) a graph-based synthesis stage that composes diverse multi-step trajectories via planning and controlled sampling. This design yields reproducible and explainable data generation, while explicitly preventing spurious cycles and enabling long-horizon composition. Across multiple real-world apps, SEE produces trajectories with an average length of 14.8 steps while avoiding spurious loops, and
agents fine-tuned on SEE achieve improved task success and generalization to unseen screens. We will publicly release our synthesis code and
dataset.
Read the full abstract ▾
All authors Zhuohang Fan, Beichen Zhang, Yuanfa Li, Changqiao Wu, Wei Liu, Jian Luan, Weigang Zhang
Machine Learning
Adaptive Mamba Neural Operators
Zeyuan Song and Zheyu Jiang
Accurately solving partial differential equations (PDEs) on arbitrary geometries and a variety of meshes is an important task in science and engineering applications. In this paper, we propose Adaptive Mamba Neural Operators (AMO), which integrates reproducing kernels for state-space models (SSMs) rather than the kernel integral formulation of SSMs. This is achieved by constructing Takenaka-Malmquist systems for the PDEs. AMO offers new representations that align well with the adaptive
Fourier decomposition (AFD) theory and can approximate the solution
manifold of PDEs on a wide range of geometries and meshes. In several challenging
benchmark PDE problems in the fields of fluid physics, solid physics, and finance on point clouds, structured meshes, regular grids, and irregular domains, AMO consistently outperforms state-of-the-art solvers in terms of relative $L^2$ error. Overall, this work presents a new paradigm for designing explainable neural operator frameworks.
Read the full abstract ▾
Machine Learning
L1 Augmented Attention as an Improved Vector Similarity Metric
Kurt Godden
Scaled dot product
attention conflates directional
alignment and vector magnitude, limiting its effectiveness as a similarity metric in
Transformer models. We introduce L1 augmented
attention, a simple and computationally parallelizable modification that subtracts a learned, head specific L1 distance between queries and keys from the dot product score. This hybrid similarity captures complementary
geometric information. Dot product rewards directional
alignment, while L1 penalizes coordinate deviations. To reduce the cost of L1 computation, we project queries and keys into low dimensional subspaces whose parameters specialize to preserve informative L1 structure. Evaluated on WikiText 2 using a compact
transformer, L1 augmented
attention achieves up to a 14.5% reduction in perplexity over the original
transformer baseline and outperforms an RBF L2 kernel. Analysis of norm variance and learned L1 weights reveals distinct
geometric roles across layers and strong head level specialization. These results demonstrate that enriching
attention with L1 geometry provides a principled and effective improvement to similarity computation in modern
language models, with practical benefits for both accuracy and parallel efficiency.
Read the full abstract ▾
Machine Learning
FlashPDE: A Drop-In Fused Triton Operator Library for Neural PDE Solvers
Peiyu Zang, Bosen Xie, Ruoxiang Xu et al. (+1 more)
Physics-Informed Neural Networks (PINNs) solve PDEs by incorporating physical constraints into neural-network training, but large-scale problems are limited by automatic-differentiation
memory overhead and inefficient execution of grid-based PDE operators. We present FlashPDE, a drop-in fused operator library for grid-based scientific machine learning. FlashPDE replaces fragmented PyTorch finite-difference execution with differentiable Triton kernels. Each operator integrates fused stencil evaluation, an analytic discrete-adjoint backward pass, and boundary-gradient correction within a unified PyTorch autograd Function interface. The library provides 14 differentiable PDE operators covering 17 configurations across 1D–3D
elliptic,
parabolic, and Navier–Stokes systems, while remaining independent of neural architectures and training strategies. Experiments on an NVIDIA A100 GPU show that FlashPDE reduces peak
memory usage by up to 37.0x compared with coordinate-based automatic differentiation and reduces CUDA kernel launches by up to 3.5x compared with eager PyTorch finite-difference implementations. Across six representative PDE
benchmarks, FlashPDE achieves up to 2.30x end-to-end time-to-solution speedup and up to 19.2x kernel-level acceleration while maintaining numerical agreement with PyTorch finite-difference references. FlashPDE provides a hardware-efficient execution layer that bridges differentiable PDE solvers and GPU-optimized numerical computation within the PyTorch ecosystem.
Read the full abstract ▾
All authors Peiyu Zang, Bosen Xie, Ruoxiang Xu, Yongqiang Cai
Machine Learning · Cross-listed from cs.IR
Remote Awareness of Seafloor Images Collected by AUVs over Low-Bandwidth Communication Links
Adrian Bodenmann, Cailei Liang, Miquel Massot-Campos et al. (+8 more)
This paper introduces a method for real-time processing and transmission of autonomous
underwater vehicle (AUV) imagery over low-bandwidth communication links. It leverages artificial intelligence (AI) techniques to identify a set of images that best represent an entire
dataset, or automatically finds the most similar images to a given query image for transmission to operators. Combined with metadata of a larger set of images, compressed versions of the selected images can be transmitted over satellite communication links or
underwater modems, and provide operators on shore with information about the type of imagery the AUV is collecting while it is still deployed. Data from three deployments off the coast of the UK and in Gran Canaria using different AUVs and imaging systems demonstrate the method in the field. It achieved an almost 400,000-fold reduction in data volume compared to the raw data size, enabling transmission of data summaries of a 2-hour 47-minute-long mapping mission in just over 34 minutes over low-bandwidth satellite communication.
Read the full abstract ▾
All authors Adrian Bodenmann, Cailei Liang, Miquel Massot-Campos, Samuel Simmons, Alexander B. Phillips, Alberto Consensi, Matthew Kingsland, Rashiid Sherif, Stan Brown, Adam Riese, Blair Thornton
Machine Learning
MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasoning in Compact Models
Martino M. L. Pulici, Cuong Xuan Chu, Evgeny Kharlamov et al. (+3 more)
Large
language models achieve strong
reasoning performance, but often at prohibitive training cost - a challenge that is especially acute for compact models ($\leq 4 \, \mathrm{B}$ parameters) trained under limited budgets. We introduce MADA-RL, a post-training framework that specializes compact models into generator and critic roles and trains them with a debate-aware learning signal, fine-tuning only a small subset of parameters via LoRA adapters. Our central contribution is a counterfactual critic advantage: a dynamic, role-conditioned baseline that redefines the critic's advantage as its reward minus the generator ensemble's per-instance accuracy. This explicitly optimizes critics to improve over generator consensus rather than to merely reproduce a correct answer, yielding more targeted credit assignment than static mean-reward normalization. At deployment, the specialized
agents are composed in a lightweight multi-round protocol. Across five mathematical
reasoning benchmarks, MADA-RL raises the accuracy of the DeepSeek-R1-Distill-Qwen-1.5B model from $39.9 \, \%$ to $41.9 \, \%$ ($+2.0$ points, $p < 0.001$) using $16$ times fewer trainable parameters than fully fine-tuned baselines, placing it on the accuracy-trainable-parameter Pareto front. It approaches, but does not surpass, the strongest baselines (DeepScaleR, STILL-3), which are trained on substantially larger
datasets; we analyse this gap and the associated inference-time cost directly. A controlled study isolates the source of MADA-RL's gains: the counterfactual advantage produces the highest critic improvement rate of any model evaluated, indicating that trained critics learn to correct generator errors rather than to imitate them.
Read the full abstract ▾
All authors Martino M. L. Pulici, Cuong Xuan Chu, Evgeny Kharlamov, Zifeng Ding, Volker Tresp, Yunpu Ma
Machine Learning · Cross-listed from cs.AI
PAMD: Structured Adaptive Distances for Bisimulation Representations in Visual Reinforcement Learning
Daegyeong Roh, Juho Bae and Han-Lim Choi
Many visual reinforcement learning (RL)
algorithms learn representations by matching latent distances to a behavioral distance induced by reward and transition similarity. In practice, the choice of the latent distance can strongly affect performance: using a fixed, pre-specified global norms (e.g., $\ell_p$ norms or other hand-designed metrics) may be overly restrictive to capture the behavioral distance. In contrast, unconstrained pairwise distances may admit degenerate solutions that drive the metric loss down without improving the representation. To address this gap, we introduce **PAMD: Pairwise Adaptive Mahalanobis Distance**, which parameterizes a positive-definite, pair-conditioned metric for measuring latent state similarity. PAMD is a simple plug-in for existing bisimulation-based methods, offering a more expressive yet structured alternative to fixed, pre-specified latent distances. We empirically validate our method on visual MuJoCo continuous-control tasks, where final performance of several recent bisimulation-based RL
algorithms is substantially improved when equipped with the distance we propose.
Read the full abstract ▾
Machine Learning
fSRD: Fuzzy Spectral Region Decomposition – Automated Multi Operator Koopman Representations via an Adaptive Spectral Learning Architecture
Charles Bokor, Mark Cary, Denise Morrey et al. (+1 more)
Highly nonlinear chaotic dynamical systems remain difficult to model due to fundamental trade-offs between complexity, expressivity, and data efficiency. Modern machine learning methods achieve strong predictive performance but often rely on a-priori system knowledge or curated data with limited interpretability. Koopman operator theory offers a promising direction via linear representation in an infinite-dimensional observable space. However, many data-driven Koopman methods seek globally valid operators for which useful finite-dimensional spectral
embeddings remain difficult to identify under these constraints. To overcome associated limitations, we introduce Fuzzy Spectral Region Decomposition (fSRD), a fully automated learning framework for estimating finite Koopman representation via multiple operators. The proposed method realizes a data-adaptive framework for assembling locally invariant
embeddings, termed Invariant Decomposition. fSRD achieves highly accurate linear reconstructions of nonlinear systems while learning finite-dimensional representations of their induced
evolution operators, bridging interpretable operator-theoretic models with expressive data-driven sequence learning. These
embeddings are adaptively constructed via a global fuzzy tree model, drawing inspiration from fuzzy neural architectures to learn the induced dynamics while prioritizing parsimonious solutions. Empirical results across canonical chaotic systems (e.g., Lorenz and Duffing) and high-dimensional real-world data demonstrate strong predictive accuracy, interpretability, and robust expressivity across data-rich and data-limited regimes, highlighting the method's generality.
Read the full abstract ▾
All authors Charles Bokor, Mark Cary, Denise Morrey, Fabrizio Bonatesta
Machine Learning
Information-Based Exploration via Random Features for Reinforcement Learning
Waris Radji and Odalric-Ambrym Maillard
Representation learning has enabled classical exploration strategies to be extended to deep Reinforcement Learning (RL), but often makes
algorithms more complex and theoretical guarantees harder to establish. We introduce Random Feature Information Gain (RFIG), grounded in
Bayesian kernel methods theory, which uses random
Fourier features to approximate information gain and compute exploration bonuses in non-countable spaces. We provide error bounds on information gain approximation and avoid the black-box aspects of neural network-based uncertainty estimation, for optimism-based exploration. We present practical details that make RFIG scalable to deep RL scenarios, enabling smooth integration into standard deep RL
algorithms. Experimental evaluation across diverse control and
navigation tasks demonstrates that RFIG achieves competitive performance with well-established deep exploration methods while offering superior theoretical interpretation.
Read the full abstract ▾
Machine Learning
Harness Engineering for LLM-Driven GPU Kernel Generation
Yue Shui, Chenyu Ma, Hangfei Xu et al. (+2 more)
Large
language models (LLMs) can assist GPU kernel generation, but their practical effectiveness depends on whether generated code can be reliably constrained, validated, profiled, and selected. This paper presents a harness-centered system for LLM-driven GPU kernel optimization in the MLSys 2026 FlashInfer AI Kernel Generation Contest on NVIDIA Blackwell B200 GPUs. The system separates an evaluation harness from a profile-backed optimization controller: the harness enforces compilation, correctness, official-aligned timing, and artifact archival, while the controller turns profiler and workload evidence into bounded candidate-generation decisions. Human-authored skills capture operator constraints, references, profiling procedures, and promotion rules, while Codex and Claude Code
agents generate candidate kernels inside those constraints. Across five operator definitions, the retained official-aligned artifacts achieved mean-latency speedups over supplied FlashInfer baselines of 1.62x, 18.05x, 29.68x, 1.12x, and 13.70x. The
Agent-Assisted kernels outperform the Full-
Agent artifacts across the evaluated definitions, indicating that expert-provided optimization directions, high-quality references, and workload context remain critical for reliable AI-driven kernel optimization.
Read the full abstract ▾
All authors Yue Shui, Chenyu Ma, Hangfei Xu, Shengzhao Wen, Yanpeng Wang
Machine Learning
DiFA: Inference-Time Forward-Process Alignment for Diffusion Models
Shigui Li and Delu Zeng
The prevailing inference framework for
diffusion models formulates generation fundamentally as a problem of numerical integration. This perspective casts the model as an exact
estimator, neglecting the inherent statistical uncertainty of the denoising process. In this work, we propose Forward-Process Aligned
Diffusion prediction (DiFA), a training-free framework that reframes inference-time data prediction refinement as a sequential state estimation problem. Rather than reusing past outputs solely for numerical integration, DiFA treats iterative data predictions along the reverse trajectory as correlated observations to build a forward-aligned temporal consensus. Inspired by Kalman filtering, this consensus aggregates historical predictions according to structural consistency and noise-level compatibility. To counteract the over-smoothing tendency of temporal consensus, we introduce a deviation guidance mechanism to adaptively preserve residual details. Empirically, DiFA yields significant improvements on CIFAR-10 and ImageNet across the evaluated metrics, including FID, IS, and FD-DINOv2, demonstrating that aligning inference with the forward statistical structure substantially improves generative fidelity.
Read the full abstract ▾