Peer Revenue Fully funded

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Machine Learning

cs.LG Watch Machine Learning

Wednesday 30 September

Machine Learning

The Life Cycle of a Massive Activation: Stochastic Birth, Weight-Decay-Driven Growth, and Competitive Consolidation

S. Aaron McClendon, Jorge Gallego-Feliciano and Antonios Saravanos

Massive activations, residual-stream coordinates with magnitudes far larger than typical activations, are associated with attention sinks in transformers, but how their scale is regulated during training remains incompletely understood. Combining training-trajectory analyses and controlled interventions, we trace their emergence, growth, and consolidation. Sink-carrying channels vary across random seeds but stabilize early within each run. Over longer training, surrounding channels erode and the sink concentrates onto a few redundant carriers. Across ablations, gradient attenuation follows the sink token's collective root-mean-square magnitude rather than any single channel, making collective scale central to understanding their effects. Our central result is that weight decay causally controls the turnover of global activation scale. In controlled continuations, removing decay near the peak allows this scale to keep rising, whereas retaining it produces decline even at constant learning rate. We develop a balance model for the rise and peak of massive-activation magnitude, in which AdamW-preconditioned growth opposes weight decay. Sweeping the decay coefficient $\lambda$ shifts peak timing approximately log-linearly and yields peak magnitudes scaling approximately as $\lambda^{-1/2}$, consistent with this balance. Optimizer measurements further show that preconditioning sustains the large-channel cohort against decay even when raw maintaining forces are too small to do so. Together, these findings connect the observed life cycle to scale-regulating training dynamics and establish weight decay as a training-time lever on activation magnitude.
Read the full abstract

Machine Learning · Cross-listed from stat.ML

Learning to Cover Locally: Graph Neural Combinatorial Optimization under a Hard Information Horizon

Johannes F. Loevenich, Thies Moehlenhof, Laurin Holz et al. (+3 more)

Neural combinatorial optimization typically assumes a centralized solver that reads the whole instance. We study the opposite: combinatorial optimization under a hard information horizon, where every node commits to its share of a global solution seeing only its $k$-hop neighborhood, and those commitments must compose into a globally feasible solution. We formalize this as local set cover and instantiate it on weighted multipoint relay (MPR) selection, the NP-hard 2-hop covering problem of the Optimized Link State Routing Protocol version 2 (OLSRv2) routing protocol (RFC~7181), whose horizon is imposed by the protocol, not chosen by the modeler. We prove two results. Any deterministic selector whose horizon is one hop short must either fail coverage or land a factor $\Delta$ from optimal, and an $L$-layer graph neural network (GNN) read out at the deciding node is exactly an $L$-hop selector, so capacity cannot buy back radius. Conversely, at the horizon a \ac{GNN} of depth $O(\Delta)$ reproduces the RFC~7181 covering greedy, and at width $O(c_{\max}\Delta)$ its metric-aware weighted analogue, inheriting the $(1+\ln\Delta_2)$-approximation in both cases. Empirically, a 3-layer \ac{GATv2} with a coverage-completing decoder, behavior-cloned from the CP-SAT optimum, reaches $\text{cost}/\text{opt}=1.030\pm0.001$ against greedy's $1.138$, closing $79.1\%$ of the gap at $100\%$ coverage. Restricting the same learner to one hop, on identical instances with the same decoder and demonstrations, collapses it to $1.344$, far worse than greedy. Two transfer checks target real-world networks. OLSRv2's unmodified selection code matches our cardinality greedy on $200/200$ unit-cost instances, and on $40{,}308$ instances of real battalion mobility the frozen model closes $48\%$ of the gap at full coverage. The information horizon, not the model capacity, is the most significant variable.
Read the full abstract

All authors Johannes F. Loevenich, Thies Moehlenhof, Laurin Holz, Maxime Schwarzer, Tobias Huerten, Roberto Rigolin F. Lopes

Machine Learning · Cross-listed from stat.ML

Transferable Graph Metanetworks

Yuxin Ma, Adir Dayan, Yam Eitan et al. (+2 more)

A weight space network (or metanetwork) takes the weights of another neural network as input and predicts properties of it. Most prior work trains such models on input networks of one or a few fixed sizes and evaluates them in-distribution. The few attempts at out-of-distribution size generalization remain limited in scope and have achieved only modest success. Consequently, the potential efficiency gains of training on small networks and evaluating on much larger ones remain largely unrealized. We propose Transferable Graph Metanetworks, which extend the graph metanetwork paradigm with a set of modifications that make performance transferable across input networks of different widths. The modifications follow two principles: invariance to the ways in which networks of different widths represent the same function, and continuity, such that weights representing similar functions receive similar predictions. We further study whether size generalization is possible for input networks trained independently from random initialization. Empirically, our modifications significantly improve size generalization on every task we consider. Performance is strongest on input networks trained under the maximal-update parameterization ($\mu$P), where it remains robust up to $42\times$ the training width. Theoretically, we explain these observations with infinite-width limit theory: we prove size-generalization guarantees for our model on $\mu$P-trained inputs, and explain why it can fail under other parameterizations.
Read the full abstract

All authors Yuxin Ma, Adir Dayan, Yam Eitan, Haggai Maron, Soledad Villar

Machine Learning

CommunityKV: Efficient Long-Context Decoding via Graph Partitioning

Joe McKenna, Anastasios Alexandridis, Nathan Susanj et al. (+1 more)

Scaling Transformers to long contexts is constrained by the quadratic cost of self-attention and the linear growth of key-value cache memory transfer. Sparse attention mitigates this by retrieving only relevant tokens, but current approaches either require large-scale training or, within the training-free regime, rely on semantically coarse heuristics or expensive clustering that is difficult to update efficiently during decoding. We introduce CommunityKV, a framework that formulates sparse attention as a community detection problem. CommunityKV constructs a token graph from the $QK^T$ scores already computed during standard prefill, and partitions the graph into communities to enable retrieval of semantically coherent token groups. A local update rule assigns newly generated tokens to communities in constant time, enabling sparse retrieval throughout streaming decoding without global re-partitioning. We evaluate CommunityKV on Qwen3 and Llama-3.1 models across three long-context benchmarks. With one graph per query head, CommunityKV delivers up to $1.25\times$ the end-to-end generation throughput of dense attention, while query-group graph aggregation yields up to $1.71\times$ with comparable accuracy.
Read the full abstract

All authors Joe McKenna, Anastasios Alexandridis, Nathan Susanj, Jing Liu

Machine Learning

Source Identification Is Not Fitness Testing: Measuring the Limits of Synthetic-Data Attribution

Joss Armstrong

Repeated training on model-generated data can degrade later models. One possible response is to use provenance when deciding which generated examples to reuse. We test both how reliably that provenance can be recovered and whether it helps identify better training data. Using financial-risk text, we first identify the source of generated passages and then repeat the test after rewriting them. Generator attribution is 98.7% accurate on the original passages but falls to 53.1% after paraphrasing and 29.0% after style rewriting. Generated-versus-human detection remains close to perfect against the tested human comparison set. We then compare two ways of selecting generated examples over three rounds of generation and retraining. One uses source information. The other uses a score from a separate reference model. The two rules select different examples, but the planned comparison does not detect a stable difference in the degradation of the resulting models. The results show that identifying where data came from and identifying which data are useful for training are separate problems. The experiment therefore separates source identity, criterion-facing selection, and recursive training outcome: neither the provenance score nor the tested criterion-facing proxy is established as sufficient for future recursive behaviour.
Read the full abstract

Machine Learning · Cross-listed from cs.AI

Benchmarking Prompt Optimization of Large Language Models With Chess

Timothée Lesort, Alejandra López de Aberasturi Gómez, Tristan Karch et al. (+4 more)

Evaluating large language models becomes increasingly challenging as their capabilities advance: benchmarks can saturate, public test sets risk contamination, and assessing harder tasks can require expensive grading or execution infrastructure. These challenges are amplified in automatic prompt optimization (APO), where evaluation is repeated throughout the search for better prompts. Studying APO therefore requires a benchmark that is cheap and deterministic to score, hard enough to leave room for improvement, and renewable as models evolve. We introduce a chess benchmark built from 1,118 Lichess puzzles to study APO for frozen LLMs: we optimize their prompts without updating their model weights. Chess combines inexpensive exact-match scoring, engine-based evaluation of alternative moves, and a renewable supply of problems with adjustable difficulty. Unlike evaluations that report only success on isolated test items, the benchmark also connects puzzle-solving gains to short game-play rollouts within the same domain. We use it to evaluate six APO algorithms on eight target models, measuring not only baseline strength but also how much each model responds to optimization and whether optimized prompts transfer across models and to game play. Chess is thus a well-suited benchmark for APO: it is (i) challenging, as even the strongest evaluated model, Gemini 3.5 Flash (used as the meta-model), solves only about 55% of puzzles; (ii) discriminative, revealing gains, unchanged performance, and regressions across methods and models; (iii) renewable, with fresh puzzles to reduce contamination risk and adjustable difficulty to maintain headroom as models improve; and (iv) affordable, as the complete study runs for around \$800. We release the puzzles, optimization and evaluation code, and dataset-renewal scripts (https://github.com/imec-ailabs/Automatic-Prompt-Optimization-with-Chess).
Read the full abstract

All authors Timothée Lesort, Alejandra López de Aberasturi Gómez, Tristan Karch, Tom Veniat, Philippe Modard, Karl Tuyls, Ludovic Denoyer

Machine Learning

Do Better Scores Mean Better Physics? Physics-Grounded Explanations for Sim2Real Neural Operators

Somyajit Chakraborty and Xizhong Chen

Machine-learning surrogates accelerate physical simulation, but lower prediction error need not coincide with lower error in physically relevant flow statistics. We examine this question for flow around a NACA4418 airfoil using paired computational-fluid-dynamics simulations and experimental particle-image-velocimetry measurements. A mean-preserving input intervention removes velocity fluctuations from selected regions of observed flow histories. Across four neural operators, removing fluctuations from the most energetic 10% of valid observed cells changes forecasts more than equal-area random removal. Because the masks are not matched for removed fluctuation energy, this contrast measures sensitivity, not independent evidence of physical importance. Separately, a CNO has lower velocity-field error but substantially higher two-component fluctuation-energy error than the reference on both analysis subsets. An output attenuation stress test also demonstrates disagreement between benchmark errors and domain-summed fluctuation energy. These single-benchmark results motivate reporting complementary physical diagnostics alongside aggregate prediction scores; they do not establish counterfactual physical correctness.
Read the full abstract

Machine Learning

EchoPress: Query-Agnostic KV Cache Pruning via Virtual Context Reconstruction

Jiawei Lin, Saibo Geng and Thomas Bourgeat

KV cache pruning reduces long-context inference memory usage by evicting less important key-value pairs. KVzip estimates importance through context reconstruction: prompting a model to repeat the context chunk by chunk. This achieves strong compression quality at the cost of additional forward passes. Learned approximations reduce this cost but require model-specific training. We analyze how KVzip identifies important cached information and show how to approximate its reconstruction scores using information already computed during prefill. These findings motivate EchoPress, a training-free method that approximates reconstruction attention using queries and keys from standard prefill. For each request, it reconstructs only the first chunk to calibrate importance scores for the remaining context. Experiments on LongBench and RULER with Qwen3-8B and Llama-3.1-8B-Instruct show that EchoPress matches KVzip in task accuracy across eviction ratios from 50% to 90%, while reducing compression overhead by a factor of 1.7-19.6 and total prefill time by a factor of up to 2.9. Code is available at https://github.com/ljwljwljwljw/kvpress/tree/echo-press.
Read the full abstract

Machine Learning

VANDAM: Viewing a nucleotide sequence with DNA molecular priors

Jeremy Levy, Ariel Larey, Yury Nahshan et al. (+18 more)

Contemporary Genomic Foundation Models (GFMs) rely on a DNA-as-a-string paradigm that employs masked token prediction objectives for pretraining. However, this abstraction does not explicitly model the biochemical, structural, and physical properties essential to biological function. Many molecular properties can be estimated from sequence using established biophysical models, so their utility lies not in providing an independent modality, but in introducing priors that training objectives can explicitly exploit. We introduce VANDAM, a framework that extends the training of GFMs with DNA molecular priors. In self-supervised training, VANDAM predicts regional molecular properties from pooled representations. When functional labels are available and can reward retaining molecular priors, local features are additionally injected at the input. VANDAM consistently improves downstream performance across four architecture families and nine held-out genomic tasks by complementing token-based objectives. Probing experiments further demonstrate that the use of molecular priors generalizes to other unseen molecular properties.
Read the full abstract

All authors Jeremy Levy, Ariel Larey, Yury Nahshan, Raizy Kellerman, Elay Dahan, Amit Bleiweiss, Guy Leib, Omri Nayshool, Dan Ofer, Tal Zinger, Dan Dominissini, Gideon Rechavi, Marissa Wirth, Simon Lee, Dung Hoang, Noam D. Beckmann, Shane O'Connell, Nicole Bussola, Alexander W. Charney, Yoli Shavit, Nati Daniel

Machine Learning

RACE: Residual-Aware Test-Time Adaptation for Neighbor-Rich Time-Series Foundation Model Forecasting

Hao-Nan Shi, Tong Wu, Chen-Cong Sun et al. (+3 more)

Time-series foundation models (TSFMs) perform strongly across forecasting tasks, but their per-series inference is ill-suited to neighbor-rich forecasting, where each query has access to related but nonidentical historical series. Continuous glucose monitoring (CGM) and Web/cloud workloads exemplify this setting: CGM trajectories share physiological patterns but vary across individuals, devices, and conditions, while Web/cloud workloads combine common operating regimes with non-stationarity, heavy tails, and bursts. These histories share useful structure, yet neighbors are not equally relevant. Existing methods either fine-tune TSFMs for each target domain, incurring additional costs and offering limited transferability across backbones, or append retrieved series without verifying whether they support the current forecast. The key challenges are conflicting residual evidence from neighboring series and residual patterns that vary across TSFMs and forecasting tasks. We formulate test-time neighborhood scaling: using same-domain neighbor evidence without modifying the backbone. We propose RACE (Residual-Aware Correction of Forecasting Errors), a two-stage framework for using historical neighbors. We first retrieve query-compatible neighbors, align their residuals to the query scale, and aggregate coherent evidence into the training-free RACE-TF correction. Full RACE then uses a lightweight, domain-specific Gate to determine when applying the correction is beneficial, with a reusable training workflow across TSFM backbones. Across four TSFMs, RACE improves all three domain-aggregate metrics on both primary domains, with the largest gains on high-error queries. Within each domain, a Gate trained on one TSFM transfers to other backbones without adaptation, and the resulting pipeline improves all 72 cross-backbone metric comparisons over the matched frozen targets.
Read the full abstract

All authors Hao-Nan Shi, Tong Wu, Chen-Cong Sun, Yuan Jiang, Han-Jia Ye, De-Chuan Zhan

Machine Learning

The Conflict Between Logic and Memory: Training Conditions for Optimizer-Dependent Rule Acquisition

Gongyue Zhang and Honghai Liu

Optimizers can fit the same task while acquiring different generalizing relations. We study the training conditions governing these differences in single-hidden-layer ReLU networks, combining composite evidence tasks, parameter-level interventions, and a three-seed strict-parity scan. Our central finding is that nuisance-connected trainability reshapes both shared failures and relative optimizer advantages. In a nuisance-heavy task, all twenty tested optimizer configurations remain near chance on the hardest stage. Retaining every input but fixing nuisance-connected first-layer weights at initialization raises that stage's accuracy from approximately 50% to 70.56%, 68.47%, and 69.00% for momentum SGD, Adam, and Muon. Masking the same inputs only after full training does not recover this performance. On a separate pairwise-mode task, background freezing reduces Muon's rare-mode advantage over momentum SGD by 12.48 percentage points, while the target and mode frequencies remain fixed. Each intervention is evaluated under a common validation-selection protocol with condition-specific learning rates and checkpoints. A strict-parity sweep over orders 1–20 provides a complementary reference without spurious cues or extra nuisance coordinates: the optimizers separate at orders 9–11, then approach chance despite substantial remaining Bayes predictability. A mixed task establishes a recovery boundary, and CIFAR-10 supplies an external architecture comparison. Together, these findings connect optimizer comparison to the acquisition and use of specified relations, identifying permitted adaptation as a concrete training variable that changes what a fixed architecture learns.
Read the full abstract

Machine Learning

Representation Transitions Reveal Emerging Safety Risks in Multi-Turn LLM Agents

Haoyu Wang, Wei Zhao, Yedi Zhang et al. (+2 more)

Multi-turn attacks on agentic systems can compose individually permissible actions into harmful outcomes, challenging defenses that assess actions or states in isolation. We show that such attacks leave a detectable signature in the agent's internal representations: harmful behavior emerges as an accumulated representation transition across context updates, whose triggering context can be identified from the same signal. We further find that naive aggregation is confounded by benign representation drift, as a contrastive safety direction need not assign zero to benign transitions. We address this by denoising the direction, anchoring benign traffic at zero and removing its leading variation directions, with no runtime cost. These findings motivate DART, a runtime framework that detects and attributes representation shifts and intervenes with targeted reminders. Across six models and two multi-turn benchmarks, DART reduces attack success from 84% to 25% on MT-AgentRisk, catching every attack at a mean false-alarm rate of 12%, and from 97% to 52% on ASEval, at costs in benign non-refusal of 8% and 0%, respectively. On MT-AgentRisk, it outperforms ToolShield, the state-of-the-art multi-turn defense, on all six models: under the same protocol, ToolShield reaches only 55%. Denoising is critical: on ASEval, the undenoised monitor catches only 7%-40% of attacks, while the denoised monitor catches 60%-85%. The same monitor covers single-turn indirect injection without modification and adds only 0.14-0.56 s overhead per monitored step without requiring an auxiliary model, making it a lightweight complement to computation-heavy speculative defenses.
Read the full abstract

All authors Haoyu Wang, Wei Zhao, Yedi Zhang, Christopher M. Poskitt, Jun Sun

Machine Learning

Metacognitive Reasoning in Energy Based Models using Instance Based Learning Theory

Tailia Malloy, Prateek Kumar Rajput, Serge Lionel Nikiema et al. (+2 more)

Metacognition involves reasoning about cognitive processes themselves. An example is in resource allocation where we choose how much time and effort to put into a reasoning task before we begin based on our confidence. Current Artificial Intelligence (AI) systems that rely on Large Language Models (LLMs) cannot estimate their uncertainty about an output without first responding, and cannot dynamically allocate resources to producing an output, making this type of metacognitive process difficult. A recently proposed alternative to classic transformer architectures that addresses these two concerns is the Energy Based Model (EBM) which allows for interpretable uncertainty modeling and dynamic allocation of compute resources. While EBMs can allow for control of these two processes, the actual metacognitive task of determining compute allocation based on uncertainty is not directly addressed. Instance-Based Learning Theory (IBLT) provides an approach to modeling human-like decisions from experience that has previously been applied to predicting human metacognitive reasoning. In this paper we introduce a framework for MEtacognitive Reasoning with Instance-based Learning Theory and Energy Dynamics (MERITED). Grounded in IBLT, this framework allows for control of the computational effort allocated in an EBM to allow for metacognitive control over reasoning effort based on uncertainty while remaining computationally efficient. This work has two main contributions, the training and open weight sharing of a 191M parameter reasoning EBM, and an implementation of the MERITED framework for dynamic compute allocation using an IBL model.
Read the full abstract

All authors Tailia Malloy, Prateek Kumar Rajput, Serge Lionel Nikiema, Cleotilde Gonzalez, Tegawendé F. Bissyandé

Machine Learning

WIPSNet: Deep Learning for Paediatric Wheeze Detection from Overnight Impedance Pneumography

Felix Oury, Harley Day, Karina Mayoral et al. (+3 more)

Overnight impedance pneumography (IP) is used to monitor paediatric respiratory health. Its current clinical readout, the Expiratory Variability Index (EVI), compresses each IP recording into a single scalar and achieves an AUC of 0.633 for night-level wheeze classification. We introduce Wheeze Impedance Pneumography Scalogram Network (WIPSNet), a 3D ResNet operating on stacked continuous wavelet transform scalograms of overnight IP signals. On a 15-patient cohort (60 nights, 281 hours), WIPSNet achieves an AUC of $0.783 \pm 0.026$, outperforming EVI, a state-space model (Mamba), and two modern sleep-staging architectures. Performance peaks at a volumetric depth corresponding to 32 minutes of temporal context, suggesting that multi-scale temporal aggregation is important for modelling nocturnal respiratory dynamics. Overall, these results indicate that structured time-frequency representations combined with 3D convolutional architectures provide an effective approach for learning from long, irregular physiological time series.
Read the full abstract

All authors Felix Oury, Harley Day, Karina Mayoral, Ville-Pekka Seppä, Sejal Saglani, Reiko J. Tanaka

Machine Learning

NEUROTOKEN: Joint Source and Directional AAD with Envelope Decoding via Conditional Flow Matching

Ali Alavi and Donald S. Williamson

Identifying which speaker a listener is attending to in a noisy room – the cocktail-party problem – is the missing ingredient for next-generation hearing aids and brain-computer interfaces: it tells the device whose voice to amplify. Auditory attention decoding (AAD) reads this answer from EEG, but the literature splits into disconnected pieces: directional-AAD classifies side but does not map side to stream; regression-based source-AAD ranks candidate streams by a single Pearson correlation that is intrinsically noisy at the 1-5 s windows real devices need; and envelope reconstruction has no native AAD rule. We argue the right object is not any single statistic but the conditional likelihood of the attended envelope given EEG, and we make this practical with NEUROTOKEN: a single network whose three heads share one EEG front-end, with a conditional flow-matching head (ATTUNEFLOW) that scores candidates by an integrated velocity-residual likelihood ratio. Two inference-time ensembles – QUADTRACK (four complementary statistics) and ENV-FLOW (z-normalised QUADTRACK+ATTUNEFLOW) – absorb per-statistic failure modes for free. On KU Leuven, DTU, and NJU at 5 s, ATTUNEFLOW lifts per-segment source-AAD by 9%-16% over the strongest non-generative baseline and shrinks across-subject variance by ~3x; trial-level fusion exceeds 93% on two of three datasets. In parallel reproductions we show that canonical 95-97% direction-AAD numbers collapse by 17%-45% under a strict trial-disjoint protocol, clarifying both the true ceiling and why a likelihood-based formulation is needed.
Read the full abstract

Machine Learning

Specificity-Aware Diffusion Steering via Variance-Reduced Sequential Monte Carlo

Luran Wang, Linrui Ma, Hannes Stärk et al. (+1 more)

Inference-time steering enables pretrained diffusion models to satisfy new constraints without full retraining. However, specificity-aware generation is difficult: repelling samples from a negative reference distribution can also erode the positive distribution where the two overlap. The key challenge is to suppress negative mass while minimally distorting the positive distribution. We address this problem by formulating specificity-aware steering as a target-design problem and deriving a target distribution from an overlap-based objective. The resulting target keeps the desired reference distribution only in regions where it is sufficiently preferred over the undesired reference distribution, giving a likelihood-ratio interpretation of specificity. To sample from the corresponding time-dependent target path, we develop a Sequential Monte Carlo sampler with a variance-minimized local proposal. We further introduce a practical fixed-noise optimization procedure with the Jacobian–vector products with the desired and undesired score fields. Experiments on synthetic task, class-contrastive generation, text-to-image tasks and peptide-MHC (p-MHC) binder show that the proposed method suppresses undesired regions more effectively, reduces mode shift, and improves sampling stability by decreasing the SMC weight collapse compared with negative-guidance baselines. Code is available at: https://github.com/WangLuran/Specificity-Aware-Diffusion-Steering
Read the full abstract

All authors Luran Wang, Linrui Ma, Hannes Stärk, Regina Barzilay

Machine Learning

Forking: Sudden Overfitting Under Replay

Shanbin Yu, Shaoyang Guo, Haoran Zhao et al. (+2 more)

This paper studies forking, a generalization failure discovered in NanoGPT autoresearch. Under data replay, models with an over-encoding n-gram memory branch show a sharp separation of training and validation loss at epoch boundaries, resembling the shape of forks. We study this phenomenon in a controlled vanilla NanoGPT setting and reproduce it in a DeepSeek-style model with Engram. Mechanistically, repeated updates sharpen the continuations observed in training while suppressing the probability of unseen continuations, whose loss grows with each pass. The n-gram module creates weakly interacting context-specific subspaces, amplifying this effect. Low-frequency contexts contribute most of the gap, whereas larger training budgets and heavily crowded tables suppress it. We also observe forking in short-budget, heavily repeated SFT and RL-like regimes. The contributions of this paper are twofold: (1) Forking reveals yet another curious phenomenon in deep learning, in addition to grokking and double descent. (2) Forking is an unexpected and unpleasant by-product of tricks proposed by autoresearch agents. While these agents produce an enormous number of results that seem useful, we should always be careful with their results.
Read the full abstract

All authors Shanbin Yu, Shaoyang Guo, Haoran Zhao, Danni Yu, Ziming Liu

Machine Learning

Interpretable Synthetic Medical Tabular Data Generation for Clinical Decision Support Using Fuzzy Cognitive Maps

Michael Vasilakakis and Dimitris K. Iakovidis

Synthetic medical tabular data generation has become essential for developing and validating computer-based medical systems (CBMSs) when real clinical data is restricted due to privacy, ethical, or data availability limitations. Existing probabilistic and deep generative models often lack interpretability and fail to preserve clinically meaningful dependencies, limiting their suitability for safety-critical applications. This paper proposes a novel application of Fuzzy Cognitive Maps (FCMs) in a framework for synthetic medical tabular data generation with explicit causality and privacy preservation. Clinical features are described using linguistically interpretable fuzzy sets, and inter-feature dependencies are encoded as FCM edge weights computed from fuzzy set intersections. Synthetic patient records are generated by propagating randomly initialized linguistic activation vectors through the FCM until convergence, followed by defuzzification to produce clinically coherent numerical values. The approach natively handles mixed data types, and domain constraints common in health records. Experimental evaluation on UCI medical benchmark datasets demonstrates competitive performance under a Train-on-Synthetic-Test-on-Real (TSTR) protocol. The proposed method achieves accuracy of up to 0.81 and AUROC of up to 0.90 on the Heart Disease dataset, matching or exceeding TVAE and Gaussian Copula baselines while running exclusively on CPU. Fidelity metrics including KS Complement (up to 0.91) and Correlation Similarity (up to 0.95) confirm strong statistical coherence, and DCR Baseline Protection scores consistently exceed those of TVAE, confirming adequate privacy guarantees. These results demonstrate that causally grounded, interpretable fuzzy modeling offers a computationally efficient and transparent alternative to deep generative models for trustworthy synthetic data generation in CBMSs.
Read the full abstract

Machine Learning

MatrixReward: Reward from Rubric Matrix for Open-Ended Generation

Zihan Shen, Qi Liu, Zixuan Yang et al. (+4 more)

Open-ended query generation lacks standard answers, thus necessitating an effective reward mechanism. Pointwise scoring rubrics provide limited information about the relative quality of sample answers under the same prompt; merging multiple rubric judgments into a single score may also mask the differences between these answers. We propose MatrixReward, which constructs rewards from a rollout-by-rubric win-rate matrix obtained by comparing every pair of sampled responses under each rubric. The spread of each matrix column captures how strongly that rubric distinguishes the current rollouts, while correlations between columns reveal rubric repetition; together, these statistics yield data-dependent rubric weights. We combine these weights with the prior weights of rubrics. After column normalization and weighting, the observed per-rubric maxima and minima define positive and negative ideal profiles. Each rollout's distances to these two ideals determine its relative-closeness quality reward. Evaluated using Qwen3-8B on four open-ended query-answering benchmarks, MatrixReward achieves an average score of 63.02, outperforming the strongest baseline by approximately 2.0%. These results support the idea that matrices derived from relative comparisons can be used to construct rewards more reasonably for open-ended generative reinforcement learning.
Read the full abstract

All authors Zihan Shen, Qi Liu, Zixuan Yang, Yiqun Chen, Chenglong Zhao, Xiaozhao Wang, Lei He

Machine Learning

T2SPO: Trajectory-to-Step Policy Optimization for Agentic Reinforcement Learning

Bo-Wen Zhang, Junwei He, Maoqi Liu et al. (+6 more)

Reinforcement learning enables large language model (LLM) agents to learn multi-step behaviors through interaction with their environments. However, rewards in many interactive tasks reflect only the final outcome, providing limited guidance on which intermediate decisions advance the task. Successful training trajectories contain intermediate states that can provide supervision for subsequent interactions. We introduce Trajectory-to-Step Policy Optimization (T2SPO), a method that uses past interaction trajectories to provide step-level feedback for policy learning. T2SPO derives remaining-distance targets from successful trajectories and pairs them with representations of the states visited along the way. Conditioned on these examples, a pretrained TabPFN regressor estimates the remaining distance to success at each state of a new rollout. Changes in this distance estimate across consecutive states yield auxiliary credit for agent steps alongside task-level supervision. As training proceeds, newly completed trajectories refresh the estimator's context, incorporating new experience without updating its parameters. Experiments with 1.5B and 7B language models on ALFWorld and WebShop show that T2SPO consistently improves overall task success over GRPO.
Read the full abstract

All authors Bo-Wen Zhang, Junwei He, Maoqi Liu, Feiran Li, Song-Lin Lv, Wentao Ma, Rongyi Lin, Shuhan Zhong, Lan-Zhe Guo

Machine Learning

FAER: Auditable Utility-Aligned Trajectory Replay for Language Model Post-Training

Miaobo Hu, Shuhao Hu, Xiaobo Guo et al. (+4 more)

Replay selectors often rank cached trajectories by format feedback, confidence, freshness, or response length, although cache-level correctness and downstream learner utility are distinct objectives. We formalize this selection-to-learning gap and introduce FAER as an auditable full-trajectory replay framework. Its training-free fixed selector is a protocol baseline; FAER-UTILITY is the learner-aware selector fitted on disjoint calibration blocks. The normalized gradient alignment is reported as a baseline, while a disposable optimizer-aware virtual update supplies a magnitude-aware utility surface. The audit contract freezes observed fields and replay traces before evaluation labels are joined. On GSM8K with Qwen2.5-1.5B-Instruct, the matched learner study reports quality 0.6329 for the fixed selector, compared with 0.5482 for uniform and 0.6037 for format-feedback under 128 updates. Metadata-only cross-fitted calibration reaches $0.6476\!\pm\!0.0139$ over eight seeds (median 0.6481; paired 95% interval $[+0.079,+0.122]$) at 63,276 target-run tokens; its recorded full cost is 189,642 tokens and 3.48 GPU-hours including calibration. The completed FAER-UTILITY row reaches 0.6624 at 62,844 target-run tokens and 4.26 GPU-hours. Format-feedback selects records with correctness 0.6953, compared with 0.3594 for the fixed selector, despite the different downstream ranking. The completed comparison surfaces report the learner-aware ablation, same-seed gap, policy-optimization rows, and strict zero-shot transfer.
Read the full abstract

All authors Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang, Tianshu Fu, Daren Zha

Machine Learning

EvoGen-Harness: Learning Where and How to Evolve Image-Generation Harnesses

Jiabin Luo, Yinan Liu, Chunlei Meng et al. (+1 more)

Modern text-to-image (T2I) systems can be improved without modifying generator parameters by adapting the external system around frozen generators. However, existing approaches typically optimize a predefined dimension, such as prompts, routing, or workflows, restricting the space in which generation failures can be corrected. Allowing multiple generator-external responsibilities to evolve provides a broader adaptation space, but introduces a new challenge: visual feedback reveals what failed, but not where persistent evolution should occur or how this space should be explored efficiently. We introduce EvoGen-Harness, a generator-agnostic framework for multi-responsibility image-generation harness evolution, together with Trace (Trajectory-Relative Attribution and Coordinated Evolution). Trace aggregates evidence across stochastic executions, uses failure attribution as a search prior to focus candidate updates, and progressively re-attributes residual failures to coordinate evolution across responsibilities, while No-Patch and held-out validation prevent unnecessary or harmful updates. Across GenEval2, T2I-CompBench++, and WISE, EvoGen-Harness improves over the strongest evaluated baselines by +0.2633, +0.0720, and +0.0752, respectively, while achieving 87.9-91.4% attribution recall, 94.8% No-Patch accuracy, and only 1.9% regression. These results demonstrate that attribution-guided multi-responsibility evolution can substantially enhance frozen T2I systems beyond single-dimension adaptation.
Read the full abstract

All authors Jiabin Luo, Yinan Liu, Chunlei Meng, Yufei Guo

Machine Learning · Cross-listed from cs.CR

On the Relationship between Model Quantization and Model Inversion Attacks

Rongke Liu and Youwen Zhu

Model quantization reduces the numerical precision of neural network weights and activations to lower storage and computational costs. Model inversion attacks recover or reconstruct sensitive training data or inference inputs from model outputs or intermediate features, so quantization may also alter their effectiveness. However, two questions remain unresolved: How does model quantization affect model inversion? How do data characteristics influence this relationship? To address the first, we bound quantization-induced changes in mutual information between inputs and a categorical variable defined by prediction probabilities, distinguishing informational effects from attack optimization obstacles. To address the second, we identify data-dependent changes in feature distributions and inversion outcomes, with pronounced quantization sensitivity differences at 4 bits. These insights guide a privacy-aware post-training quantization method that improves inversion resistance while recovering utility. It uses a Fisher-type task-sensitivity proxy for budget-aware bit allocation, calibrates activation ranges, and jointly optimizes weight and activation scales and weight-rounding decisions with task-recovery and geometry-retention objectives and scale and rounding regularization. Experiments cover multiple metrics, neural network architectures, and face, palmprint, and iris recognition tasks. On ResNet-50, Palm at 4 bits reduces RL-MIA's strict success from 54% to 26%, while accuracy decreases from 99.01% to 96.55% relative to FP32. Our method also supports output-level defenses: adding Stealthy Shield Defense (SSD, epsilon = 0.1) to Iris at 4.5 bits reduces BREP-MI's strict success from 63.33% to 37.33%, while accuracy decreases from 92.8% to 87.6% relative to quantization alone.
Read the full abstract

Machine Learning

OmniMed-Jev: Calibrating LVLM Confidence for Trustworthy Medical Multimodal Decisions via System One

Luyao Tang and Cheng Chen

Medical models are judged not only on correctness, but on whether reported confidence matches actual accuracy. Generalist multimodal medical models have expanded what a single model can perceive, yet they still express bounded decisions such as diagnoses, findings or cell counts as generated text, so the reported probability reflects the next token rather than the decision itself. Motivated by decision-native interfaces such as Jev, we introduce OmniMed-Jev, which represents each medical decision as a Choice, Noul or Score decision over a runtime-supplied candidate set and returns a full distribution over that set: mutually exclusive classes, binary presence of a finding, or a bounded ordered value. The design is omni in three respects: it accepts diverse imaging modalities, covers different prediction tasks, and expresses them through one candidate-conditioned probability model, so heterogeneous outputs become comparable probabilities rather than task-specific strings. In an interface-controlled comparison against a generative baseline trained on the same backbone, data and schedule, OmniMed-Jev's reported probabilities track observed correctness far more closely, reducing calibration error by up to an order of magnitude and reliability error by up to two, while point-prediction performance remains comparable; counting is the one family where the generative baseline stays ahead. Making the decision distribution the model's output is not a format change but what turns reported numbers into probabilities that mean what they say. These results support explicit decision modeling as a way to make reported confidence meaningful within the evaluated tasks, and they are not evidence of clinical readiness: the comparison cannot separate the interface from associated training differences, which we state alongside the results. Code is available at github.com/lytang63/OmniMed-Jev.
Read the full abstract

Machine Learning

Fusion techniques of time frequency-based images to predict the outcome of rTMS depression therapy

Wael Korani, Md Fahimul Kabir Chowdhury, Mohammed Aledhari et al. (+2 more)

Depression is a mental condition that can lead to suicide and self-harm. Predicting the outcome of depression treatment is one of the most difficult tasks for clinicians. Among various treatment options, repetitive Transcranial Magnetic Stimulation (rTMS) is a widely used non-invasive method. Predicting rTMS response using Electroencephalogram (EEG) data is difficult because of high inter-subject variability and limited features from single-domain analysis. We introduce two fusion techniques, montage and blending, to overcome these limitations and extract richer features from EEG-derived Time-Frequency (TF) images. We then propose a lightweight custom Convolutional Neural Network (CNN) trained on fused TF representations. \textcolor{black}{We use a primary dataset of 15 patients and a secondary dataset of 46 patients. We run two sets of experiments. The first set uses segment-level 10-fold cross-validation. In this setup segments from the same patient can appear in both training and testing. The Montage CWT\_ST fusion reaches 99.90% accuracy on the primary dataset and 91.90% on the secondary dataset. The second set uses strict subject-disjoint cross-validation. All segments of a patient stay in one fold and no patient appears in both training and testing. Performance collapses. We test four time-frequency methods, six fusion mechanisms, and fourteen model architectures. With one exception, every configuration on both cohorts falls between AUC 0.31 and 0.54 and every 95% confidence interval contains 0.5. A patient-level permutation test on the best standalone method returns $p = 0.703$. The best subject-level result is Montage CWT\_ST on the primary cohort, which reaches AUC $0.874 \pm 0.183$ and 82.7% accuracy.
Read the full abstract

All authors Wael Korani, Md Fahimul Kabir Chowdhury, Mohammed Aledhari, Reza Rostami, Reza Kazemi

Machine Learning

STCFormer: Adaptive Spatio-Temporal Modeling with Dynamic Cluster Transformer for Station-based Weather Forecasting

Rongwen Li, Haixin Xie, Mingyang Wang et al. (+5 more)

Station-based weather forecasting supports daily life and economic activity, yet accurate forecasts require modeling complex spatial dependencies among stations. Recent clustering-based selective modeling offers a promising alternative to dense inter-station interactions. However, a grouping shared across an observation window may obscure local changes in station relationships, while intra-cluster interactions alone may miss important global context. The theoretical advantages of selective interactions over dense connectivity also remain insufficiently understood. We therefore propose STCFormer, an adaptive spatio-temporal Transformer that dynamically groups stations according to their local evolution within each temporal patch. Its Cluster-Guided Attention Block combines fine-grained local attention within clusters and global attention over regional state summaries, allowing each station to access information beyond its own cluster. We further show that a derived Lipschitz upper bound for cluster-conditioned local attention is no larger than its fully connected counterpart, explaining a potential robustness benefit and motivating the design of InfoLoss. Experiments on three real-world weather datasets spanning eight temperature and wind forecasting tasks show that STCFormer achieves the lowest 24-hour mean squared error on all eight tasks and ranks first or second in 47 of 48 comparisons across metrics and forecasting horizons. Ablations and case studies further confirm the benefits of locally adaptive grouping and complementary local-global interactions. Our code can be obtained at https://github.com/hnu-vis/STCFormer.
Read the full abstract

All authors Rongwen Li, Haixin Xie, Mingyang Wang, Hongwu Liu, Kun Fang, Changjian Chen, Zhuo Tang, Kenli Li

Machine Learning

A First Glance at Jev for Network Traffic Classification: Accuracy, Processing Time, and Cost

Shenghe Xu and Lifan Mei

We evaluate Jev on ten dataset-defined application labels in CESNET-QUICEXT-25 using only the first ten packets' sizes, directions, and inter-packet times. To the best of our knowledge, this is the first empirical study of general-purpose decision models, represented here by Jev, for application classification of network flows. Across 52,000 records from 26 collection weeks following the training period, 40 fixed labeled examples raise Jev's accuracy from 9.80% to 28.42%. Random Forest and Extra Trees trained on 8,000 records achieve 69.95% and 66.80% and outperform Jev in every week. Increasing Jev's context to 150 examples yields 34.50% on the first test week. On a paired 100-record subset, Jev with 40 examples achieves 29% accuracy at a median request time of 0.750 s, versus 37% and 6.036 s for the generative language model OpenAI GPT-5.6 Sol with high reasoning effort through Azure; Jev also incurs lower API charges. The paired subset does not establish an accuracy advantage for either service, and the timing reflects different service configurations. Thus, labeled examples substantially improve Jev, but the tested Jev configurations remain less accurate than trained tree ensembles; unequal supervision budgets and fixed configurations prevent attributing the gap to a single cause.
Read the full abstract

Machine Learning

When Do Attention-Head Ablations Support Causal Claims? Projection-Level Confounds, Floor Effects, and Matched Controls

Juli Huang

Attention-head ablation, zeroing a head and measuring the resulting change in task performance, is a common method for inferring which components of a language model are causally responsible for a behavior. We show using GPT-2 small that this inference can be fragile unless the intervention semantics, evaluation metric, and controls are carefully validated. A natural post-projection implementation of "zeroing a head" is nearly uncorrelated with a corrected pre-projection ablation (Pearson r = 0.057) and selects a completely disjoint top-5 set of important heads. We also show that binary accuracy can hide effects at behavioral floors and near ceilings, whereas gold-token log-probability remains graded. Using a discovery/held-out split and 1,000 matched random-head and layer-matched-head control draws, the corrected per-head effect ranking is highly stable across splits (Spearman rho = 0.974), and the top-5 selected heads significantly exceed both control distributions (Monte Carlo p = 0.001). However, evidence for task specificity is not robust on GPT-2. Replication on DistilGPT2 preserves the intervention-semantic and matched-control findings. These results show that single-head ablation does not by itself justify a causal claim; defensible interpretation requires correct intervention placement, a non-saturated continuous metric, and matched held-out controls.
Read the full abstract

Machine Learning

M$^2$Weather: A Benchmark for Joint Multi-Station and Multi-Variable Weather Forecasting

Rongwen Li, Xiao Wang, Mingyang Wang et al. (+4 more)

Station weather forecasting is fundamentally shaped by both complex spatial dependencies across stations and strong physical coupling among weather variables. However, existing studies often consider these relationships separately and use different datasets and experimental settings, hindering systematic assessment of their individual and joint contributions. In this paper, we introduce $M^2$Weather, a benchmark for joint multi-station and multi-variable weather forecasting. Through multi-criteria quality control and station stratification, we collect 2,809 high-quality stations with 5 physically coupled weather variables across three spatial scales: France, Europe, and Global. This multi-scale design lets us examine whether conclusions persist from national to global station networks. We also introduce unified training and evaluation protocols to enable fair comparison of different station-variable modeling paradigms. To further examine the benefits of modeling station-variable relationships, we design a lightweight, plug-and-play adapter. With a trained weather forecasting model, this adapter can introduce missing station or variable relationships without retraining the model. This enables fair and efficient investigation of station-variable relationships. Systematic evaluation of 16 representative models shows the benefits of jointly modeling station and variable relationships. Completing missing relationships further reduces MSE for all adapted models on all three datasets. Together, these results identify the complementary information across stations and variables as an important resource for improving station weather forecasting. Our code can be obtained at https://github.com/hnu-vis/M2-Weather.
Read the full abstract

All authors Rongwen Li, Xiao Wang, Mingyang Wang, Hongwu Liu, Changjian Chen, Zhuo Tang, Kenli Li

Machine Learning

MoRA: MoE Pruning via Router Bias Learning and Expert Approximation

Yushuai Sun, Zikun Zhou, Lin Gao et al. (+2 more)

Mixture-of-Experts (MoE) models enable parameter scaling with limited per-token computation by activating only a small subset of experts for each token, but deploying them still requires loading the complete expert pool into memory. Structured expert pruning can effectively reduce the memory usage by removing experts. However, existing pruning methods either use expert ranking criteria that are not well aligned with model performance or rely on effective expert subset searching that is computationally expensive. Moreover, these methods typically overlook the routing-behavior redundancy among the retained experts. In this paper, we propose MoE Pruning via Router Bias Learning and Expert Approximation (MoRA), a framework for structured MoE expert pruning. We introduce a learnable router bias for each expert and optimize these biases by minimizing the language-modeling loss and a routing-diversity regularizer. The learned router biases sharpen the routing probability distributions to identify experts critical to model performance while encouraging the selection of experts with diverse routing preferences. In addition, we introduce an expert approximation mechanism as a post-pruning enhancement. It leverages the remaining experts to approximate the outputs of pruned experts by affine transformation, further improving the performance of the pruned model. We evaluate MoRA on Qwen3-30B-A3B, DeepSeek-V2-Lite, and Moonlight-16B-A3B, removing 25% and 50% of the routed experts in each MoE layer. Extensive experiments on nine zero-shot benchmarks show that MoRA outperforms state-of-the-art pruning algorithms. Our code will be released.
Read the full abstract

All authors Yushuai Sun, Zikun Zhou, Lin Gao, Jun Yu, Wenjie Pei