Machine Learning · Cross-listed from cs.CL
CurveShift: Is Agent Progress Scalar? Separating Level from Shape
Hanwen Xing, Pengyun Wang, BingXu Meng et al. (+8 more)
Progress in large
language models is often summarized using a single scalar measure, such as a time horizon, a latent ability estimate, or an aggregate
benchmark score. These summaries capture the overall performance, but they do not test whether progress is distributed differently across task difficulty. We find that most of the apparent shift in gains toward harder tasks does not reflect a change in the shape of the difficulty-response curve. On METR time-horizon data, a single Rasch model with rising ability reproduces this pattern, so it is largely explained by ceiling effects rather than a qualitative change in capability. This echoes how the choice of metric can make claimed emergent abilities look like a property of the models themselves. We then identify a smaller hard-task effect that survives this control. Isolating it is difficult on agentic
benchmarks, because newer models are usually run with newer agentic harnesses, so a gain on hard tasks cannot be assigned to the model or its scaffold. We break the confound with LiveCodeBench, a public competitive programming
benchmark that runs no agentic scaffold while pairing dated models with an exogenous difficulty ordering. After accounting for the rise in overall ability, models released after September 2024 still gain on the hardest problems beyond what their easy and medium performance predicts, by about +0.40 logits under our most conservative assumption, raising the hard-problem solve rate from roughly 18% to 25%. The effect is led by the strongest
reasoning models and holds for hard tasks that need only short
reasoning, not autonomy over long horizons. We present this as a result specific to competitive programming, since our clean identification rests on a single coding
benchmark. We release the LiveCodeBench Difficulty Panel (66 dated models x 1,055 problems) and our analysis code.
Read the full abstract ▾
All authors Hanwen Xing, Pengyun Wang, BingXu Meng, Kumail Alhamoud, Xiang Li, Jicheng Wang, Xin Yu, Xinyang Han, Xiaomin Li, Philip Torr, Yuexing Hao
Machine Learning
Ensemble of Unsupervised Deep Learning for Clustering Imbalanced Tabular Data
Pulock Das, Yina Hou, Md. Kamrozzaman Bhuiyan et al. (+1 more)
Data imbalance poses a major challenge in supervised classification, where the majority-class bias contributes to false negatives and overestimates classification accuracy. Unsupervised deep clustering can be immune to class imbalance because representation learning for clustering is performed without class labels. Deep clustering has been proposed for images,
languages, and graphs, while its application to tabular data has only emerged recently. This paper is among the first to examine the performance of state-of-the-art deep clustering methods under varying levels of data imbalance. We introduce two novel cluster ensemble approaches: one aggregates deep clustering assignments across different
embedding dimensions, and the other applies majority voting to the best-performing clustering
algorithms. Experiments on 16 binary tabular
datasets with varying and artificially induced levels of imbalance reveal distinct strengths of different deep clustering methods. On average, our ensemble methods outperform individual clustering methods in ACC, NMI, and ARI scores, offering greater resilience to data imbalance when identifying ground-truth classes without supervision. Therefore, in an imbalanced data scenario, deep clustering can serve as a strong alternative to supervised classification.
Read the full abstract ▾
All authors Pulock Das, Yina Hou, Md. Kamrozzaman Bhuiyan, Manar D. Samad
Machine Learning · Cross-listed from cs.AI
RMSWeb: Reflection, Failure-Mode Mining, and Salvage-DS for Web Agent Reinforcement Learning
Chengbo Liu, Lifang Zhou, Ruijie Yan et al. (+8 more)
Compact web
agents can reduce deployment cost, but training them poses challenges in both data collection and post-SFT reinforcement learning (RL). Successful trajectories are expensive to collect and often contain inefficient detours. After supervised fine-tuning (SFT), full trajectory corpora are dominated by routine states; moreover, when group-relative RL is applied to web actions, inadequately designed action-level rewards can yield weak or misleading relative updates, while groups rejected as unsuitable for such updates receive no fallback learning signal. We present RMSWeb, a three-part recipe for Qwen3-VL-Instruct at 8B and 32B. Reflection-conditioned retries increase collection yield and shorten successful trajectories; failure-mode mining concentrates offline RL on critical states exposed by the SFT policy; and Salvage-DS combines an action-semantic polarized reward, contrast-and-competence-gated dynamic sampling, and an action-only anchor for rejected groups. Policies trained with reflection-collected data use up to 19.7% fewer action steps on solved tasks. On WebVoyager, Online-Mind2Web, and WebTailBench, RMSWeb improves over SFT by 2.4-7.0 points at 8B and 1.2-7.7 points at 32B. Our 8B model also achieves the strongest reported Online-Mind2Web result among similarly sized open-weight models in our comparison and a leading reported accuracy-cost trade-off on WebVoyager and WebTailBench, with the caveat that external evaluation protocols differ.
Read the full abstract ▾
All authors Chengbo Liu, Lifang Zhou, Ruijie Yan, Pei Tan, Ao Sun, Haojun Huang, Guichun Hua, Sining Wei, Yining Chen, Yingying He, Yutao Xie
Machine Learning
Neural Operator Learning for Collision-Aware Trajectory Planning of Spacecraft Swarms
Sidhdharth D. Sikka, Suyi Gao, Zehui Lu et al. (+2 more)
Satellite constellations require orbital transfers that are both fuel efficient and collision avoidant. Yet, the computational cost of optimization methods traditionally used to plan their trajectories scales poorly with both the number of satellites as well as the number of obstacles to avoid, due to the pairwise safety constraints. In this work, we introduce a permutation-equivariant neural operator for trajectory planning of spacecraft swarms. This neural operator maps distributions of spacecraft initial states, target states, and obstacle initial states to trajectories which avoid collision and conserve fuel. This neural operator output is then paired with a batched Gauss-Newton finish to enforce exact orbital dynamics, and further reduce fuel use. The operator is self-supervised, trained without optimal trajectory labels. When trained on ten spacecraft, the proposed method generalized zero-shot to swarms of 1,000 spacecraft and 11,000 obstacles. The generated trajectories matched a per-
agent optimal control solver's accuracy while retaining collision avoidance. Operator learning grounded in physics may offer a fast, scalable alternative to trajectory optimization in the increasingly crowded orbits of the future.
Read the full abstract ▾
All authors Sidhdharth D. Sikka, Suyi Gao, Zehui Lu, Rongjie Lai, Shaoshuai Mou
Machine Learning
Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch
Paul Brunzema, Louis Tiao, Nhat Le et al. (+3 more)
Bayesian optimization (BO) has become the standard tool for sample-efficient optimization and owes its efficiency to uncertainty-aware search driven by generic statistical priors. Richer domain priors can improve BO in principle, but encoding them through tailored kernels or problem structure is difficult and rarely done in practice. LLMs can help sidestep this difficulty by making informal priors from natural
language, code, and documentation directly available to the optimizer. However, existing LLM-based BO methods either insert the LLM into a fixed role (surrogate, acquisition proxy, or configuration interface) or hand it broad control, sacrificing the systematic exploration that makes BO reliable. We introduce agentic
Bayesian optimization: a paradigm in which an LLM
agent is the central decision maker in the BO loop while a
Bayesian backend provides the uncertainty-aware optimization substrate. The
agent configures the problem, queries the backend, selects and commits evaluations, and can revise the optimization strategy during the run by tightening bounds, switching acquisition functions, proposing targeted evaluations, or even reframing the problem following new instructions or observed evidence. We instantiate this idea in Sara, a surrogate-augmented autoresearch
agent, and lenz, a modular BoTorch-based backend that the
agent can inspect and modify through a structured interface. Across synthetic and real-world
benchmarks, Sara preserves the reliability of state-of-the-art BO without prior knowledge, outperforms LLM-based baselines, and uses natural-
language priors to improve beyond standard BO. We further demonstrate the practical value of agentic BO in dynamic settings, where Sara reconfigures the full optimization problem on the fly as requirements change, a capability not previously available in standard BO.
Read the full abstract ▾
All authors Paul Brunzema, Louis Tiao, Nhat Le, Kevin De Angeli, Yao Xuan, Djordje Gligorijevic
Machine Learning · Cross-listed from cs.RO
Towards General Language-Conditioned Latent Safety Filters
Ihab Tabbara, Yuxuan Yang and Hussein Sibai
Robot policies are becoming increasingly general, with
vision-
language-action (VLA) models enabling a single policy to execute diverse tasks specified in natural
language. Safe deployment, however, requires adapting not only to new tasks but also to varying safety requirements across users, environments, and applications. Existing safety filters remain largely constraint-specific and thus must be redesigned or relearned when safety requirements change. In this paper, we investigate
language-conditioned safety filtering, in which a Hamilton-Jacobi safety actor and critic are conditioned on
language-specified constraints. We evaluate this formulation across pick-and-place, table-wiping, and block-stacking tasks in the
vision-based setting, examining its ability to enforce
language-specified constraints and transfer to unseen constraint instances within the evaluated constraint families. Our experiments provide evidence that
language-conditioned safety filters reduce constraint violations and exhibit partial transfer to unseen constraint instances.
Read the full abstract ▾
Machine Learning
Abstention as an Action Can Kill Both the Reward Gradient and the KL Anchor: Collapse Law and Repair for Error-Penalized Reinforcement Learning
Xujun Che, Yuchen Yuan, Weida Zhao et al. (+1 more)
Error-penalized scoring rules ($+1$ for a correct answer, $-\lambda$ for a wrong one, $0$ for abstaining) are increasingly prescribed against
hallucination: a rational
agent facing such a rule answers exactly when its correctness probability exceeds Chow's threshold $t^\ast=\lambda/(1+\lambda)$. We prove that a KL-anchored gradient learner can do the opposite. When abstention is a discrete action, the reward gradient and the anchor's restoring force are throttled by the same gate-saturation factor and die together: under explicit conditions (among them, blanket answering loses score in expectation and
prompts share a bounded readout) the model drifts toward refusing everything, its mean training reward rising to zero like $1/t$ in training time $t$, so the curve reads as improvement while coverage collapses. The advantage
estimator compounds the failure: in its sparse-answer regime, group normalization silently replaces every designed penalty with an effective penalty of one, moving the learned threshold from $t^\ast$ to $1/2$. The repair is structural: train a mandatory confidence report with a strictly proper score plus a correctness reward, and abstain only at deployment by thresholding the report. The always-emitted report has no gate to saturate, so no shared factor can kill its reward gradient and its anchor together, and its calibrated optimum is attracting. Simulations confirm every prediction, and experiments on
language models at two scales confirm the mechanism live: the rule silences questions the models demonstrably still solve within ten optimizer steps, an ablation isolates the cause, and report-level training raises coverage, accuracy, and calibration together.
Read the full abstract ▾
All authors Xujun Che, Yuchen Yuan, Weida Zhao, Chenyang Yu
Machine Learning
Stabilized Best-of-$K$ Training for Neural Combinatorial Optimization
Melveena Jolly and Midhun Xavier
Leader Reward modifies POMO training to emphasize the best trajectory produced by repeated inference. We test a narrow extension: replace its binary leader/non-leader distinction with a stabilized rank signal indexed by a sampling budget $K$. With the POMO architecture, 3,050-epoch schedule, and TSP-100 test set held fixed, the Leader Reward reimplementation obtains $7.7662$ under 100-start, 8-augmentation greedy decoding, matching the reported $7.766$ at its displayed precision. Under independent sampling, the stabilized $K=8$ recipe lowers realized Best-of-8 cost in all three paired training seeds: $7.7944$ versus $7.8136$. This observation is estimation-only and decoder-specific: three seeds are below the six-seed testing floor, Leader Reward is better at sampled $K=1$, and it remains slightly better under its original augmented-greedy protocol. We make no unbiased-
estimator, universal superiority, or state-of-the-art claim.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
A reproducible and extensible framework for benchmarking competing risks survival models
Begoña B. Sierra, Colin McLean, Peter S. Hall et al. (+2 more)
A wide range of statistical and machine learning methods have been proposed for survival analysis with competing risks, where the occurrence of one event (i.e., cancer death) precludes the occurrence of other events (i.e., cardiovascular disease death). Despite these methodological advances, their systematic evaluation and adoption are limited by the lack of comprehensive, reproducible and extensible benchmarking frameworks. We developed an open-source benchmarking framework for competing risks models that enables their systematic comparison across multiple
datasets under different aspects of performance; calibration, discrimination, overall prediction error and clinical utility. We additionally introduce an extension of SHAP for competing risks, allowing model-agnostic interpretability of
covariates contributions over time. All our code is publicly available via GitHub:https://github.com/BBolosSierra/CompRisksBenchmark
Read the full abstract ▾
All authors Begoña B. Sierra, Colin McLean, Peter S. Hall, Sarah Friedrich-Welz, Catalina A. Vallejos
Machine Learning
Similarity-Aware Machine Unlearning
Madhavan Citalamangalam Kumaran, Midhun Parakkal Unni, Vicky Kouni et al. (+1 more)
Machine unlearning removes the influence of user-specified training examples from a trained model, avoiding the need to retrain it from scratch. Localization-based methods improve unlearning efficiency by identifying a subset of influential model parameters. However, existing approaches select parameters based solely on forget-set importance, neglecting their role in retained
dataset and often causing collateral damage to semantically similar retained examples. We address this limitation with a retain-aware localization method that considers parameter importance to both forgotten and retained data. We also introduce a retain-similar evaluation set, constructed using cosine similarity in the model
embedding space, to directly measure collateral damage. Across eleven experimental settings on CIFAR-10
dataset and ResNet18 model, our method consistently reduces collateral damage while improving standard unlearning metrics, demonstrating the effectiveness of retain-aware localization for similarity-aware machine unlearning.
Read the full abstract ▾
All authors Madhavan Citalamangalam Kumaran, Midhun Parakkal Unni, Vicky Kouni, Haripriya Harikumar
Machine Learning
Verifier-Induced Support Reshaping in On-Policy Optimization
Shaohang Wei, Zikun Su, Feifan Song et al. (+4 more)
We show that on-policy reinforcement learning with verifiable rewards (RLVR) can improve the current objective while making successful behaviors for later objectives too rare to sample and reinforce. We call this verifier-induced support reshaping and define effective rewardable support as successful trajectories reachable within a fixed rollout budget. Across two model families, we study this effect through repeated verifier-scored sampling and bidirectional training on mathematical
reasoning and constrained instruction following, including sequential training with the opposite verifier. Math-RLVR raises average instruction-following success but reduces the number of
prompts with any successful response under repeated sampling. On IFEval with Qwen3-8B-Base, pass@1 rises by 6.5 percentage points while best@32 falls by 9.8 percentage points, and the same divergence appears across both models and IF
benchmarks. Conversely, IF-RLVR shifts math responses from step-by-step openings toward direct answers, lowers best@k across sampling budgets, and reduces reward variation for later Math-RLVR.
Token-distribution analyses and controlled opening interventions show that these changes concentrate in the first few response
tokens. RLVR mainly reranks openings already available in the base policy, and the selected opening causally affects math searchability. The tested reference-policy constraints, routing priors, and on-policy
distillation preserve cross-task support only partially; MathIF and ReasonIF show that marginal gains translate only partly into responses that are both correct and constraint-following. Therefore, endpoint improvements do not guarantee future trainability or joint capability under on-policy optimization. Code is available at https://github.com/sylvain-wei/VISR
Read the full abstract ▾
All authors Shaohang Wei, Zikun Su, Feifan Song, Wen Luo, Wei Li, Guangyue Peng, Houfeng Wang
Machine Learning
A Physics-Chemistry-Informed Neural Network (PCINN) for Real-Time Spatial-ALD Coverage Prediction and Reliable Kinetics Inversion
Ning Hu, Chang Liu, Yunlei Jiang et al. (+1 more)
Spatial atomic layer deposition (SALD) is a leading atmospheric-pressure, high-throughput route to industrial ALD, but design and control are limited by the cost of predicting surface coverage: high-fidelity CFD is far too slow for operating-window scans, while analytic models miss transport modulation such as the gas curtain. We present a physics-chemistry-informed neural network (PCINN), a hybrid surrogate with CFD-level accuracy at real-time speed: a query returns coverage in about 7 ms, roughly 5x10^4 times faster than a CFD solve, reaching a test R^2_log = 0.998 (leave-one-out R^2_raw = 0.974) from only 30 training cases spanning four orders of magnitude in coverage. The architecture is not a black box: a small network learns only the operating-condition to near-wall concentration closure, while the known surface kinetics is a hard-coded, trainable chemistry layer integrated along the substrate trajectory. This single-scalar bottleneck keeps it accurate under sparse data, interpretable and invertible. We add a full identifiability analysis (Fisher information, profile likelihood). The adsorption energy E_ads and desorption rate k_des are robustly identifiable; k_ads is not separately identifiable at a single temperature (only k_ads*c_wall is). Across four temperatures the prefactor nu and E_ads bind along a weakly identifiable degeneracy valley of slope 0.065 eV/decade, derived analytically as k_B T_eff ln(10) and turned into a reliability diagnostic: a seven-chemistry mismatch
matrix shows it is invariant under any single-Arrhenius mismatch and shifts only when a second thermally activated process appears, so a slope departure flags unmodelled site heterogeneity. Data come from simulation with known ground truth inverted by the same kinetic form, so the study verifies pipeline self-consistency and the identifiability boundary, not real parameters.
Read the full abstract ▾
All authors Ning Hu, Chang Liu, Yunlei Jiang, Yuan Dong
Machine Learning · Cross-listed from cs.AI
TRACE-TS: Attribution-Grounded and Traceable Sensor-Language Reasoning for Human Activity Understanding
Sparsh Rastogi, Tanmay Kumar, Baiyu Chen et al. (+3 more)
Wearable sensors capture fine-grained motion patterns that support rich behavioral understanding, yet most existing methods reduce these signals to activity labels. Recent LM-based approaches generate natural-
language explanations for sensor data, but their
reasoning is weakly grounded in the underlying signal, leading to fluent yet unverifiable explanations. We introduce TRACE-TS (Traceable
Reasoning with Attribution-Grounded Evidence), a framework for structured and signal-grounded
reasoning over wearable time series. TRACE-TS uses attribution from an expert classifier to identify salient spatio-temporal sensor regions, uses them to construct DAG
reasoning traces with explicit evidence provenance, and trains a compact
language model to generate these traces through gated cross-
attention over sensor
memory tokens. At inference, the adapted model jointly outputs the activity prediction and its
reasoning trace, without requiring attribution computation or teacher guidance. We introduce Semantic Node Match(SNM), an LLM-as-judge metric that diagnoses
reasoning fidelity at the observation, inference, and synthesis levels, localizing hallucinated observations and broken evidence chains missed by standard NLG metrics. Across seven wearable
benchmarks, TRACE-TS achieves the best average accuracy and F1 among all evaluated methods (84.43%/81.24%), and outperforms the best LLM-based baseline by 17.96% in F1. Our code is available at https://github.com/SparshRastogi/TRACE-TS.
Read the full abstract ▾
All authors Sparsh Rastogi, Tanmay Kumar, Baiyu Chen, Jatin Bedi, Zechen Li, Flora D. Salim
Machine Learning
AutoCause: A Python framework that automates expert decisions in environmental time-series causal discovery
Marco Ruiz, Miguel Arana-Catania, David R. Ardila et al. (+1 more)
Environmental time-series causal discovery requires expert decisions about method choice, conditional-independence tests, lag horizons, sample-size adequacy, multiple-testing control, and evidence interpretation. Applied inconsistently across
datasets, these choices yield graphs that cannot be compared, reproduced, or audited. We present AutoCause, an open-source Python workflow that records each decision, derives defaults from an extended causal-audit module, and admits domain-informed overrides. The workflow wraps four established causal-discovery methods from three families, adds non-causal reference models, and grades links by method-count support. On 145
datasets from DGP-Atlas, TimeGraph, and a
topology-derived CausalRivers reference, the methods recover complementary parts of the reference graphs. Majority-supported links are more precise than single-method links on the synthetic
benchmarks but not against river
topology. AutoCause converts inconsistent expert practice into an auditable, repeatable analysis; causal interpretation remains with the analyst. Available at https://github.com/marcoruizrueda/autocause.
Read the full abstract ▾
All authors Marco Ruiz, Miguel Arana-Catania, David R. Ardila, Rodrigo Ventura
Machine Learning · Cross-listed from eess.IV
MedSAM2-Anatomy: Training-Free Inference-Time Optimization for Musculoskeletal Segmentation
John Garcia Henao, Nicholas Bünger, Benedikt Herzog et al. (+11 more)
High-resolution 3D
segmentation of hip and shoulder anatomy from CT and MRI is essential for
surgical planning, yet frozen
segmentation models often fail under domain shift. CNN-based expert models are fully automatic but lack adaptability, whereas promptable foundation models generalize better but require manual prompting. We present MedSAM2-Anatomy, a training-free inference-time optimization framework that improves frozen
segmentation models without retraining or human interaction. A frozen expert model generates anatomical priors that are automatically converted into multiple
prompt hypotheses for a frozen 3D foundation model. Candidate masks are fused while anatomically implausible priors are rejected. No model weights are updated and no manual
prompts are required. TotalSegmentator and MedSAM2 are used as representative expert and foundation models, allowing the contribution of the inference policy to be isolated. Evaluation on the independent Balgrist-V0 CT and MRI cohorts shows that inference-time optimization increases median Dice from 0.71 to 0.92 on hip MRI and from 0.89 to 0.92 on shoulder CT, while reducing median HD95 on hip MRI from 22.0 mm to 5.0 mm. On public TotalSegmentator
benchmarks, the expert model remains strongest, indicating that the optimal fusion strategy depends on the reliability of the expert prior. These results demonstrate that training-free inference-time optimization provides a practical strategy for improving frozen
segmentation models without manual prompting.
Read the full abstract ▾
All authors John Garcia Henao, Nicholas Bünger, Benedikt Herzog, Cindy Guerrero Toro, Benjamin Vella, Matthias Biner, Rico Brütsch, Carmen Castroviejo Fernandez, Felix Öttl, Norman Juchler, Armando Hoch, Bettina Hochreiter, Sven Hirsch, Sebastiano Caprara
Machine Learning · Cross-listed from cs.CV
SCALP: Semi-Supervised Statistical Shape Modeling from Imperfect 3D Photogrammetry via Landmark-Anchored Spectral Warp
Nawazish Khan, Sanjay Bhandari, Sarang Joshi et al. (+8 more)
Correspondence-based statistical shape modeling (SSM) is vital for population-level morphometric analysis, but conventional pipelines assume clean, fully registered surfaces. Real-world clinical photogrammetry scans are often noisy, partial, and cluttered, hindering the adoption of radiation-free surface imaging as a safe alternative to computed
tomography (CT) for infant craniosynostosis. We present SCALP (Semi-supervised Correspondence via lAndmark Localization and sPectral warping), a two-stage framework that constructs consistent shape models directly from raw, imperfect surface scans. First, a semi-supervised Point
Transformer leverages a small expert-annotated
dataset alongside a large unlabeled cohort to accurately localize craniofacial landmarks with minimal annotation overhead. Second, these landmarks anchor a Laplace–Beltrami spectral deformation of an anatomical template, generating dense correspondences while naturally isolating the cranium from peripheral scanning clutter without manual preprocessing. Experiments on infant photogrammetry scans demonstrate that SCALP consistently outperforms state-of-the-art unsupervised point-cloud approaches, offering a clinically practical pathway toward objective, radiation-free head shape analysis.
Read the full abstract ▾
All authors Nawazish Khan, Sanjay Bhandari, Sarang Joshi, Alzbeta Novotna, Tiffany Jeong, Loretta Bowman, Michael Hernandez, Tobi Somorin, Viraj Govani, Jesse Glodstein, Shireen Elhabian
Machine Learning · Cross-listed from cs.CL
C-Instrument: Automating RL Data Generation and Hillclimbing with a Constitution-Grid Instrument
Xianling Zhang
Conflicting objectives are general in RL
alignment, and training on them data-efficiently is hard. Training a safety guard with RL means optimizing two objectives that conflict: catch real harm, and do not refuse benign
prompts. Our finding is that over-refusal improves 22.4% to 12.8%, while under-refusal on
adversarial attacks silently worsens 0.27 to 0.33. We present C-Instrument, a constitution-grid data instrument that generates the RL training data, and C-LIM, a per-
cell learnability score that decides each
cell's move: prune, densify, amend, expand. C-LIM flags the dead-weight data region before any training budget is spent: 187 untargeted rows had bought zero gain, and our method lifts the same region's learning impact 0.733 to 0.80. Code and the constitution are open-sourced.
Read the full abstract ▾
Machine Learning
Inference-Time Policy Alignment for Fair Reinforcement Learning
Umer Siddique, Peilang Li, Conor Wallace et al. (+1 more)
Deep reinforcement learning (RL)
agents achieve strong performance by optimizing scalar reward functions. However, once deployed, the policies of these RL
agents are often rigid and costly to adapt to new performance criteria. For instance, an
agent trained to maximize expected cumulative reward may not accommodate previously unknown stakeholder preferences. Existing approaches to achieve
fairness, a type of preference, in RL typically assume that such preferences are known a priori and require complete retraining of the policy under a
fairness-oriented metric. Inspired by inference-time
alignment in large
language models, we investigate the problem of steering a pretrained RL policy toward welfare-based
fairness objectives at inference time without updating the base policy's parameters. We formalize inference-time
fairness alignment as a policy shaping problem and propose a multiplicative policy shaping framework that adjusts action probabilities using action-dependent welfare scores, thus requiring no modification to the base policy. Our framework is general and compatible with any deep RL
agent. Through extensive experiments across multiple domains, we demonstrate that inference-time policy shaping substantially improves welfare-based
fairness objectives while preserving core task performance.
Read the full abstract ▾
All authors Umer Siddique, Peilang Li, Conor Wallace, Yongcan Cao
Machine Learning · Cross-listed from eess.SP
Generative Models for Modeling and Synthesizing MIMO Channels in Adverse Weather Conditions
Vignesh Nandakumar, Faraz Barati and Brian L. Evans
The push for broader coverage in future cellular networks depends on reliable service, yet this is increasingly harder to do as we encounter more instances of extreme weather conditions. In extreme weather conditions, we have difficulty evaluating coverage due to limited access to channel measurements. In this paper, we generate channel state information (CSI) in low and moderate weather conditions to synthesize realistic
MIMO CSI under adverse weather conditions. Our primary contributions are to (1) synthesize
MIMO channel
datasets incorporating three weather types, each with three intensity levels, representative of practical 5G/6G scenarios; (2) train a
diffusion model conditioned on weather using channel samples obtained through conventional pilot-based estimation under low and moderate weather intensities, and subsequently use it to generate channel realizations for severe weather conditions; and (3) evaluate the downlink Bit Error Rate (BER) and Outage Probability measures using the generated channels. The results show that
diffusion-based generative models provide a scalable, data-driven alternative for channel modeling in harsh environments and can generalize to severe weather conditions using only low- and moderate-intensity training data.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?
Dong Yan, Jian Liang, Dapeng Hu et al. (+4 more)
Large
language model (LLM)
agents can self-evolve by continually improving from their own accumulated experience. However, existing studies predominantly adopt independent evaluation. Consequently, the behavior of self-evolving
agents in realistic streaming settings, where
agents adapt to diverse and complex task streams, remains poorly understood. To address this gap, we introduce AgentStream, a unified framework that evaluates self-evolving
agents spanning diverse
evolution components by organizing agentic
benchmarks into a configurable task stream and instantiating the Isolated, Sequential, and Interleaved streaming scenarios at test time, which progressively vary the scope and domain composition of the stream. Over these scenarios, we combinatorially evaluate five representative self-evolving methods across three frontier foundation models, disentangling how model capability, method architecture, and streaming scenario jointly shape self-
evolution. Our results show that self-
evolution reliability varies across streaming scenarios, the benefit of self-
evolution is gated by model capability and is non-monotonic in model strength, and no single method dominates across models and scenarios. These findings offer concrete guidance for selecting self-evolving methods across models and streaming scenarios. Overall, we advocate that self-evolving
agents should be evaluated under realistic task streams rather than isolated single-task settings.
Read the full abstract ▾
All authors Dong Yan, Jian Liang, Dapeng Hu, Ran He, Nicholas Jing Yuan, Qi Zhang, Tieniu Tan
Machine Learning
Can We Trust In-Distribution Success? Locked Evaluation Reveals Transfer Failure and Sampling-Depth Entanglement in CRISPRi Perturbation Prediction
Mehrdad Shoeibi and Niloofar Yousefi
AI evaluation can support the wrong inference when an in-domain
benchmark success does not survive distribution shift, or when the
benchmark endpoint is entangled with a design factor. We study this problem in CRISPRi perturbation-effect prediction, evaluating a frozen Geneformer representation under a locked, pre-registered protocol: heads and model selection were frozen before test evaluation; the protocol required external outcome labels to remain withheld until final unblinding; and analysis-governing decisions were fixed before the evaluations they govern. In-distribution on the Virtual
Cell Challenge (VCC), the frozen representation carries measurable predictive information beyond a dimension-matched random-feature control (Delta R^2 = +0.1645, 95% CI [+0.1375, +0.1920]), satisfying the pre-registered informativeness gate required before interpreting transfer. It then fails zero-shot transfer on both external screens (Spearman rho = -0.139 and -0.267), lying below that control on each. Adding a predefined magnitude block improves the representation externally (Delta rho = +0.032 and +0.143) but, under the frozen primary head, does not rescue transfer: both remain negative. A pre-registered, count-adjusted max-response secondary is positively associated with the outcome on both screens; we report it as correlational and secondary, not as a recovered magnitude signal. Finally, the VCC endpoint is strongly sample-size associated: a count-only linear model reaches R^2 = +0.4325, versus +0.2589 for the four magnitude scalars; adding those scalars to
cell count improves R^2 by only +0.0017, so much of the aggregate-magnitude signal overlaps with
cell count. This case study shows how locking the evaluation, harmonizing the measured endpoint, and separating primary from secondary evidence can change the inference supported by an AI
benchmark.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
RadPRISM: Schema-stratified radiology-report supervision for concept-disentangled image representations and visual grounding
Fabian Drexel, Marlene Fritzsche, Era Stambollxhiu et al. (+15 more)
Vision-
language pretraining learns rich medical image representations from radiology reports, but previous model variants commonly operate within a single shared
embedding space, so concept-level structure and interpretability must be recovered post hoc, limiting model transparency and, hence, clinical utility. We introduce RadPRISM, which makes a clinician-defined radiology schema a designated stratification axis: an on-premise large
language model extracts per-concept text spans from free-text reports, and each clinical concept is aligned in its own dedicated visual subspace, turning concept stratification into direct, top-level
alignment supervision. Instantiated on chest radiographs with a 19-concept schema over $203{,}602$ examinations from an internal multi-year archive, RadPRISM improved internal
dataset zero-shot classification from $0.717$ (95% CI, $0.710-0.723$) to $0.868$ (95% CI, $0.863-0.872$) macro AUROC over a matched global-
alignment baseline, performed on par with the purpose-built CARZero reference in external zero-shot classification while substantially outperforming it (up to 4.3-fold) in pointing-game visual grounding. In addition, a radiologist reader study demonstrated concept-stratified
retrieval ability ($0.78$ macro
retrieval correctness rate within rank 3), surfacing disentangled descriptive findings that report-level
retrieval and fixed-label vocabularies cannot express. RadPRISM yields discriminative, spatially faithful, natively concept-stratified representations shaped by and transparently inspectable by clinicians.
Read the full abstract ▾
All authors Fabian Drexel, Marlene Fritzsche, Era Stambollxhiu, Miriam Kumpf, Lena Schmitzer, Lea Schumann, Jannik Kahmann, Friedrich Puttkammer, Johannes Moll, Jannik Lübberstedt, Zeineb Ben Chaaben, Anirudh Narayanan, Cosmin I. Bercea, Sebastian Ziegelmayer, Marcus R. Makowski, Daniel Rueckert, Lisa C. Adams, Keno K. Bressem
Machine Learning
Leak It: Per-Document Extraction Beyond Aggregate Membership Inference
Victor Maricato
Membership inference (MIA) on
language models is usually summarised by aggregate ROC-AUC, but such evaluations are confounded: model-free blind baselines can separate members from non-members using surface text alone. Building on probabilistic discoverable extraction, we study black-box training-data leakage using N samples from p_theta(. | x), placing mean overlap, extreme-value overlap, and self-concentration on a common functional-estimation footing. On WikiMIA, a blind bag-of-words classifier reaches AUC 0.97 (TPR 0.90 at 5% FPR) while sampling adds nothing. On an IID Pile split (MIMIR), neither self-concentration nor gold-continuation recovery significantly exceeds a blind baseline in aggregate. Aggregate metrics hide the real harm: sampling verbatim-extracts training data for a tail of documents no blind attack can reach. On Pythia-6.9B, 16.6% of 500 Pile documents bearing a real identifier (83 documents; 21.3% of those bearing an email address) have that identifier reproduced and not reproduced under a mismatched-prefix control. Each leak is attributable to that document rather than a globally common string. This per-document disclosure is invisible to aggregate AUC. Risk is uneven: identifier leakage is about 3x stronger in code than prose, though prose remains positive and grows with capacity (4.0% to 12.1% from 410M to 6.9B); recovery of arbitrary held-out continuations is essentially confined to code (+0.44 member gap on GitHub vs at most +0.014 on prose). Temperature and
nucleus sampling have minor effect, a 16-
token prefix suffices, and the sample-budget relationship corroborates prior probabilistic-extraction results. We detect no reduction from deduplication.
Privacy audits should report per-document extraction, not only aggregate membership, and motivate differential
privacy as the mitigation. We release leakit, a black-box tool implementing this probe and its control.
Read the full abstract ▾
Machine Learning
Rethinking Pretraining for Specialized Design Data: Evidence from the JONES-19 Cultural Design Dataset
Alexandros Haridis and Charles Zhou
Design and architectural archives encode expert human knowledge in graphical formats, providing a critical testbed for design-inspired Machine Learning (ML) challenges absent with typical computer
vision benchmarks. Building on JONES-19, a small-size image
dataset based on The Grammar of Ornament (London, 1857), we evaluate the discriminative performance of Convolutional Neural Networks (CNNs) in two model training strategies: (a) ImageNet pretraining for domain-general "visual common sense," and (b) learning from scratch on the design data in JONES-19. We find that while domain-general priors improve discriminative performance, learning from scratch augmented with repeated local sampling (multi-crop) effectively recovers these gains. For highly structured design data, local design-driven representations provide sufficient foundation for learning, challenging a reliance on massive general-purpose pretraining. These findings suggest that in specialized design domains, careful curation of smaller high-quality
datasets that capture empirical and formal design principles may prove more effective and informative on the nature of a particular design domain than prioritizing large-scale data collection.
Read the full abstract ▾
Machine Learning
Progressive$^2$: A Teacher-Student Progressive Co-Evolving Knowledge Distillation Method for Substantial Model Compression
Tiancong Cheng, Ying Zhang, Zhiwen Yu et al. (+2 more)
Knowledge
distillation (KD) is a widely utilized technique for transferring knowledge from a large model (the teacher) to a smaller model (the student). Owing to its flexibility and broad applicability, KD has been extensively applied in the compression of server-side models to meet the Quality of Service (QoS) requirements of client users. Despite significant advancements, the performance of
distillation is substantially compromised when a large disparity exists between the capabilities of the server and the requirements of the client. To alleviate this problem, we propose a novel
distillation approach, named Progressive$^2$, which operates through the combination of a progressively stronger teacher and a progressively smaller student. On the side of the teacher, rather than involving all layers simultaneously, we progressively select additional layers for
distillation following a raw-to-rich semantic progression, establishing a systematic learning curriculum. Furthermore, we design a teacher-side multi-feature fusion adapter for the teacher to improve training stability, which is theoretically supported by the framework of Lipschitz continuity. On the side of the student, rather than directly training a tiny model, we gradually reduce the size of the network to facilitate an iterative co-
evolution with the teacher. Progressive$^2$ serves as a flexible framework; the progressive strategy of the teacher can be deployed independently to achieve an optimal balance between accuracy and training efficiency, while the joint integration of the teacher and the student yields further improvements in overall performance.
Read the full abstract ▾
All authors Tiancong Cheng, Ying Zhang, Zhiwen Yu, Yifang Yin, Bin Guo
Machine Learning · Cross-listed from cs.CL
LLM-OSDA: An Optimal-Stopping Dynamic Auction for Native Advertising in Multi-Turn LLM Conversations
Yan Fang, Jialin Chen, Chun Gan et al. (+5 more)
LLM-native advertising embeds sponsored content directly into model-generated responses, shifting the unit of sale from a fixed slot to a moment within an evolving conversation. Existing LLM ad-auction mechanisms primarily operate within a single response, settling the winner but not the timing. The extension is nontrivial: with one native insertion opportunity per session, the stopping time depends on bids, coupling timing with allocation, so static truthfulness arguments no longer apply. We propose the LLM-based Optimal Stopping Dynamic Auction (LLM-OSDA), a dynamic cost-per-click auction that integrates Bellman optimal stopping, winner allocation, and envelope pricing. A bid-independent LLM layer estimates contextual click quality and seamlessly renders the winning ad, while bids enter only the committed auction mechanism. Under an exact Bellman oracle, the expected discounted-click allocation is monotone in each advertiser's bid, and the corresponding envelope payment makes truthful bidding weakly dominant in expectation. For practical deployment, a learned StopNet approximates the Bellman action values. We show that its decisions differ from the optimal policy only near the stopping boundary and bound the resulting incentive loss in terms of its approximation error. Experiments on a simulated conversational advertising corpus show that LLM-OSDA improves net revenue by 11 percent over the strongest fixed-timing baseline while maintaining comparable user retention. Code is at https://github.com/2025Fang2025/llm-osda.
Read the full abstract ▾
All authors Yan Fang, Jialin Chen, Chun Gan, Hang Yu, Mingjun Nie, Yeyu Zhang, Fengxiang He, Ching Law
Machine Learning · Cross-listed from cs.CR
Deep Learning for Cyber Threat Detection and Mitigation in Healthcare-IoT
Mirza Akhi
Cybersecurity is a fundamental requirement for protecting wearable devices used in healthcare Internet of Things (H-IoT) systems. Security failures in these resource-constrained systems directly compromise patient safety. Physiological data and network traffic are frequent targets of cyberattacks in H-IoT environments. To address these risks, deep learning-based cybersecurity mechanisms for H-IoT often involve complex architectures with large parameter counts. Existing
datasets are also rarely assessed for quality, limiting their applicability. However, this research addresses these challenges by developing multiple realistic
datasets and proposing lightweight deep learning models, namely the Temporal Convolutional Network (TCN) and Residual TCN (Res-TCN), for H-IoT. It includes two binary classification
datasets for Distributed Denial of Service (DDoS) attacks and a multiclass
dataset representing Selective Forwarding (SF), Man-in-the-Middle (MITM), and DDoS attacks. The
datasets UL-ECE-MQTT-DDoS-H-IoT2025 and UL-ECE-UDP-DDoS-H-IoT2025 are generated in Cooja and ns-3 to capture transmission behaviours and protocol variations. The third
dataset, UL-ECE-MultiAttack-H-IoT2025, integrates physiological and network features to represent multiple cyber threats in H-IoT. Building on this, the TCN model is designed to detect and mitigate DDoS attacks over the MQTT and UDP-based
datasets. It incorporates a monitoring frequency-based detection mechanism and a dynamic threshold-based mitigation strategy. To enable edge deployment, the model is quantised and converted into TensorFlow Lite (TFLite) for real-time DDoS detection on Raspberry Pi 4, achieving low latency and power-efficient operation in H-IoT. This thesis establishes a deep learning-based cybersecurity defence mechanism encompassing realistic
dataset generation, lightweight model design, and edge deployment for securing H-IoT systems.
Read the full abstract ▾
Machine Learning · Cross-listed from eess.IV
FDIR: Harmonizing Fidelity and Human-Machine Preference in Lossy Compression Image Restoration
Kuan-Yen Chen, Fang-Yi Su, Philip Chikontwe et al. (+1 more)
Image restoration quality can be evaluated along three complementary facets: pixel-level fidelity, human perception, and downstream machine preference. However, existing lossy compression restoration methods optimize for at most one of these criteria: fidelity-oriented models often regress toward conditional means and produce over-smoothed outputs, while generative approaches hallucinate plausible but factually incorrect textures that degrade both ground-truth fidelity and downstream task accuracy. To navigate this three-way tradeoff, we propose FDIR, a two-stage architecture that decouples the conflicting demands through complementary inductive biases: Quality-Guided One-Step Flow Matching (QO-Flow) recovers global semantic structure in latent space via a single forward pass, while Flow-Conditioned Detail Refinement (FCDR) deterministically restores high-frequency textures and suppresses generative
hallucinations in pixel space. Extensive experiments demonstrate that FDIR achieves superior fidelity, with a favorable perceptual-fidelity balance and competitive machine preference.
Read the full abstract ▾
All authors Kuan-Yen Chen, Fang-Yi Su, Philip Chikontwe, Jung-Hsien Chiang
Machine Learning
MetaRoute-Bench: Evaluating Meta-Decision Policies for Agentic Workflow Routing
Natan Vidra, Alina Kapanova, Arun Kanhai et al. (+1 more)
Agentic systems must repeatedly decide whether to answer directly, decompose a task, invoke a tool, execute code, delegate to a specialist, verify an intermediate result, or recover from failure. These meta-decisions affect not only task success but also operating cost and latency, yet they are often embedded inside an orchestration framework and evaluated only through aggregate task accuracy. We present MetaRoute-Bench, an open, inspectable framework for comparing meta-decision policies under a shared execution model. The initial
benchmark contains 180 synthetic task profiles spanning data analysis, research, and document processing, eight routing policies, and 30 paired random seeds. Across 43,200 traces, a task-aware compositional policy achieves 79.4% success compared with 76.7% for a strong workload-specific static policy, 67.4% for one-shot task routing, and 52.9% for direct answering. Relative to the static policy, this is a 2.7 percentage-point improvement with paired 95% CI of plus or minus 2.0 points, at 4.7% higher mean cost and 6.4% higher latency. Ablations show the largest losses when route composition is restricted to one operation and when verification is removed. These results are generated by a seeded offline execution model rather than a live deployment; accordingly, the primary contribution is a reproducible evaluation method and an analysis of routing-policy tradeoffs, not evidence of production effectiveness. We release task generation, policies, traces, tests, and analysis artifacts to support live-system validation.
Read the full abstract ▾
All authors Natan Vidra, Alina Kapanova, Arun Kanhai, Spurthi Setty
Machine Learning
Learning Compositional Meta-Routing for Agentic Workflows: An Executable Benchmark
Natan Vidra, Alina Kapanova, Arun Kanhai et al. (+1 more)
Agentic systems must decide not only what answer to produce, but which
reasoning and execution operations should precede it. A controller may answer directly, decompose a request, retrieve evidence, execute code, delegate to a specialist, or verify an intermediate result. Existing routing work largely selects model endpoints,
retrieval depth, or tools in isolation. We introduce an executable
benchmark and a budget-aware meta-router that composes heterogeneous operations from raw task text. The
benchmark contains 216 training, 72 development, 108 held-out test, and 108 locked lexical-shift challenge tasks across data analysis, frozen-corpus research, and document processing. Outcomes are machine checked after operations execute. Independent regularized logistic heads predict operation probabilities from word and character features, are temperature-scaled on development data, and are greedily composed under route-cost and action-count budgets. On the held-out test, the learned policy achieves 100% success versus 93.5% for strong static and fixed workflows, with 43% lower cost than the static policy; a matched learned one-shot router reaches 56.5%. On the untouched challenge split, learned success falls to 75.9% and trails static routing at 93.5%, while remaining 49% cheaper and exceeding one-shot routing by 34.3 points. The gap identifies lexical generalization, rather than route execution, as the principal limitation. These results establish a reproducible testbed and a bounded proof of concept, not evidence of live-LLM performance.
Read the full abstract ▾
All authors Natan Vidra, Alina Kapanova, Arun Kanhai, Spurthi Setty