Software Engineering
Code That Works, Environments That Don't: Measuring Environment Reproducibility in AI-Generated Software
Bhanu Prakash Vangala and Tanu Malik
Code generation has emerged as a central capability of large
language models, with coding
agents now able to produce functionally correct software projects from natural
language prompts. However, functional correctness alone does not capture a critical dimension of generation quality: environment specification, defined as the accurate identification of the dependencies required to execute generated code, is equally critical. We develop an
agent protocol for environment specification and introduce a three-layer framework comprising declared, runtime-installed, and necessary-and-sufficient dependencies to systematically assess coding
agents for environment specification. Using this protocol, we evaluate the extent to which coding
agents systematically misspecify software environment dependencies and how this misspecification varies across three
agents, four
languages, and fifty programming tasks. Our results show that current coding
agents exhibit systematic generalization failures along this dimension, producing dependency specifications that are inconsistent, redundant, or incomplete in ways that functional tests do not detect. Across
agents, dependency set agreement is as low as 7% for identical tasks, and newer
agents show no meaningful improvement, suggesting the failure is not resolved by scale or recency. The largest divergence occurs between the declared and runtime dependency layers, implicating environment priors learned from the models' training distributions as the primary driver. Our findings establish environment specification as a distinct, measurable axis of code generation quality that current
benchmarks do not capture, and motivate training objectives and evaluation protocols that jointly optimize for functional correctness and environmental portability.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from stat.ML
Target-Dependent Limits of Causal Repair: A Leading-Log Frontier in a Gaussian Model
Qinchuan Cheng, Jiaqi Liu and Ruixuan Xie
Knowing how much a causal predictor could improve need not reveal the gain of the repair actually learned. We quantify this gap in a scalar Gaussian causal experiment with known intervention geometry: auxiliary data identify effect magnitude up to bounded contamination, while diagnostics identify direction. The target is the squared-loss gain of the realized trained repair relative to a fitted reference. Jointly optimizing the learner and assessor under uniform learning MSE $\eta$ avoids the trivial solution of making no repair. At the usual $1/k$ learning scale, every feasible learner incurs a $k^{-2}$ assessment floor, even when oracle potential is estimable at a faster rate. In the magnitude-rich regime, we characterize a sharp leading-log frontier: the assessment exponent is $\min{\ell_k,2k\eta_k/U}$ to first relative order, where $\ell_k=\log(1/(k^2E_k))$ and $E_k$ is auxiliary precision. A diagnostic-abstention rule attains this exponent with unknown nuisance parameters. We also bound the critical allowance window and transfer the frontier to adaptive sampling by exact Gaussian simulation. Finite-grid experiments distinguish sign-tail suppression from total MSE and expose conservative finite-budget behavior. The result isolates how the assessment target changes information requirements in this experiment; it is not a general causal identifiability claim.
Read the full abstract ▾
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 ▾
Artificial Intelligence · 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
Computer Vision
Scores That Hold, Benchmarks That Leak: Measuring Dataset Contamination in Public Brain-Tumor MRI Classification
Bhanu Prakash Vangala, Sowmya Guda, Latha Peddi et al. (+1 more)
Automated classification of
brain tumors from MRI is a heavily published application of deep learning in medical imaging, with reported accuracies on public
benchmarks routinely exceeding 98%. However, accuracy does not capture a critical dimension of
benchmark quality:
dataset integrity, defined as the independence of test from training data at the image, patient, and acquisition-source levels. We introduce a three-layer contamination framework comprising duplicate, patient, and source-label leakage to assess the public corpora on which this literature rests. We audit the three most widely used corpora against a chest-radiograph negative control and quantify each layer's effect on measured performance across nine architectures and three evaluation conditions. Contamination is severe at every layer: 28.8% of the dominant corpus's official test split has a near-twin in its own training split, a second corpus leaks 22.3% of its test images byte-identically, 95.5% of traceable test images share a patient with training, and file-header features containing no anatomy separate tumor from no-tumor at 0.959 balanced accuracy, at parity with fine-tuned ResNet backbones. The unexpected result is that removing every identified leaked test image leaves balanced accuracy essentially unchanged: stable performance after deduplication does not establish
benchmark integrity. Our findings establish
dataset integrity as a distinct, measurable axis of
benchmark quality that a stable leaderboard cannot certify. For biomedical research, reported accuracy on these corpora alone does not establish that a model has learned to recognize tumors rather than exploit
dataset-specific cues. We release the contaminated-file lists, recovered patient identifiers, and deduplicated splits.
Read the full abstract ▾
All authors Bhanu Prakash Vangala, Sowmya Guda, Latha Peddi, Navya Vangala
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
Sound
ProxyMOS: Label-Free Speech Quality Assessment by Multi-Teacher Distillation with Adaptive Routing
Maxim Trokunov, Kirill Borodin, Nikita Vasiliev et al. (+1 more)
Human mean opinion scores (MOS) are costly to collect, and non-intrusive MOS predictors degrade sharply outside their training domain. ProxyMOS turns a pool of public MOS predictors into a single stronger model without new human labels. Eight predictors are benchmarked against human ratings; the five most informative enter a subset search under uniform, correlation-weighted, error-weighted, MSE-optimised and adaptive per-utterance routing; and the best routed four-model ensemble labels 807k unlabeled utterances that train a wav2vec 2.0 student. On URGENT the student reaches Spearman $\rho=0.802$ against $0.773$ for the best teacher. On mos260, a new Russian TTS
benchmark of 4,600 utterances from 38 synthesis conditions, it reaches $\rho=0.636$ against $0.613$ per utterance and $0.95$ per condition, matching its own routed ensemble in one forward pass. Adaptive routing is the only rule that does not degrade when weak predictors are added. Model, ONNX exports and mos260 are released. It's about 950 characters; arXiv's limit is 1,920. I kept $\rho$ because arXiv renders it on the abstract page. If you'd rather avoid math, replace $\rho=0.802$ with rho = 0.802 and do the same for the other $...$ values.
Read the full abstract ▾
All authors Maxim Trokunov, Kirill Borodin, Nikita Vasiliev, Grach Mkrtchian
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 ▾
Artificial Intelligence
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 ▾
Computer Vision
From Image Latent Space to Fuzzy Rules: Interpretable Analysis of Gastrointestinal Foundation Model
Michael D. Vasilakakis and Dimitris K. Iakovidis
Foundation models pretrained on large-scale
datasets demonstrate strong transferability to medical imaging tasks. However, understanding how their latent representations encode clinically relevant information remains an open challenge in safety-critical domains. This study proposes a prototype-based fuzzy-rule framework that interprets the patch-level features produced by the inner layers of pretrained foundation models, without any fine-tuning. Class-specific prototypes are learned by clustering in the feature space, yielding compact visual patterns. Patch features are then expressed as prototype similarities and classified by fuzzy rules with linguistic IF-THEN conditions that are human readable. The framework is applied across the final two blocks of ViT-S/16 backbones pretrained on ImageNet-1K and GastroNet-5M, and benchmarked against k-nearest neighbours, kernel SVM, and linear probing under identical frozen features, on wireless capsule endoscopy classification, gastrointestinal endoscopy classification, and colonic polyp
segmentation. The experimental analysis shows that the proposed method, without backbone fine-tuning, reaches accuracy comparable to these black-box classifiers, and that domain-specific pretraining yields features that are both discriminative and symbolically compressible. Because the resulting rules are extracted from real data and expressed in interpretable terms, they are further used as an instrument to investigate synthetic medical images, providing a human-readable account of which real prototypes and rules a generator reproduces or fails to reproduce, localising where a synthetic image departs from real tissue rather than summarising it with a single score. The framework thus offers a transparent, depth-resolved view of how foundation models organise clinically relevant structure, together with a practical downstream use of the extracted rules.
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
Computation and Language
UniBuc at SemEval-2024 Task 2: Tailored Prompting with Solar for Clinical NLI
Marius Micluta-Campeanu, Claudiu Creanga, Ana-Maria Bucur et al. (+2 more)
This paper describes the approach of the UniBuc team in tackling the SemEval 2024 Task 2: Safe Biomedical Natural
Language Inference for Clinical Trials. We used
SOLAR Instruct, without any fine-tuning, while focusing on input manipulation and tailored prompting. By customizing
prompts for individual CTR sections, in both zero-shot and few-shots settings, we managed to achieve a consistency score of 0.72, ranking 14th in the leaderboard. Our thorough error analysis revealed that our model has a tendency to take shortcuts and rely on simple heuristics, especially when dealing with semantic-preserving changes.
Read the full abstract ▾
All authors Marius Micluta-Campeanu, Claudiu Creanga, Ana-Maria Bucur, Ana Sabina Uban, Liviu P. Dinu
Computation and Language
LLM-as-a-Judge for Low-Resource Languages: Adapting Ragas and Comparative Ranking for Romanian
Claudiu Creanga and Liviu P. Dinu
Evaluating
Retrieval-Augmented Generation (RAG) systems remains a challenge for Low-Resource
Languages (LRLs), where standard reference-based metrics fall short. This paper investigates the viability of the "LLM-as-a-Judge" paradigm for Romanian by adapting the Ragas framework using next-generation models (Gemini 2.5 and Gemini 3). We introduce AdminRo-Eval, a curated
dataset of Romanian administrative documents annotated by native speakers, to serve as a ground truth for benchmarking automated evaluators. We compare three evaluation methodologies - direct scoring, comparative ranking, and granular decomposition - across metrics for Faithfulness, Answer Relevance, and Context Relevance. Our findings reveal that evaluation strategies must be metric-specific: granular decomposition achieves the highest human
alignment for Faithfulness (96% with Gemini 2.5 Pro), while comparative ranking outperforms in Answer Relevance (90%). Furthermore, we demonstrate that while lightweight models struggle with complex
reasoning in LRLs, the Gemini 2.5 Pro architecture establishes a robust, transferable baseline for automated Romanian RAG evaluation.
Read the full abstract ▾
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
Robotics
Whole-Body Aerial Grasping and Lifting via Partial Visual Observations
Jiaye Jin, Rui Jin, Xinhang Xu et al. (+6 more)
Aerial grasp-and-lift tasks require whole-body coordination across approach, acquisition, and lifting under partial target observations. Early approach failures can limit exposure to later task stages during training, while changing visibility complicates
alignment and closure timing during execution. We present a recurrent teacher-student framework that learns a single policy in simulation to jointly command flight, arm motion, and gripper closure without an explicit task-phase input. A privileged teacher learns through reinforcement learning with a critical-state curriculum that exposes acquisition and lifting states before connecting them to normal approach trajectories. Its behavior is distilled into a recurrent visual student that replaces privileged target states with dual-view point clouds and proprioception, integrating observation history for closed-loop control. A dedicated closure objective supervises closure timing from sustained model-defined readiness sequences. Training and primary evaluation use a simulated acquisition-and-payload model with condition-triggered latching, virtual attachment, and wrench-based payload loading for short-distance lifting. Across 8,996 completed simulation episodes under this model, the frozen student achieves full-task success rates of 99.97%, 97.14%, and 95.84% under nominal, physics/control-randomized, and additional camera-randomized conditions, respectively. The nominal latch-count-weighted mean of per-seed 90th-percentile
alignment errors at acquisition is 8.12 mm.
Read the full abstract ▾
All authors Jiaye Jin, Rui Jin, Xinhang Xu, Haotian Jin, Ruiyang Liu, Yi Wang, Jiayan Zhao, Kun Cao, Lihua Xie
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 ▾
Computation and Language
Dissonant ballerinas and crafty carrots: a comparative multi-modal analysis of Italian brain rot
Anca Dinu, Andra-Maria Florescu, Marius Micluta-Campeanu et al. (+3 more)
This paper presents a comparative multi-modal analysis of Italian and Romanian
brain rot memes, investigating the factors that contribute to its appeal and the linguistic and cultural distinctions between the two versions. To conduct this analysis, we introduce a multi-modal
brain rot
dataset named CRIB (Collection of Romanian and Italian
Brain rot), a manually curated collection of 240 TikTok
videos stratified by
language (Italian, Romanian) and popularity, on which we examine textual, acoustic, and visual features. Our findings indicate that popularity is not significantly correlated with textual elements like sentiment, absurdity, or rhyme, or acoustic elements such as vocal features or sentiment of the sound. Instead, in Romanian
language,
video-level dynamics, specifically faster cutting speeds and a more rapid overall pace, are strong predictors of a
video's success. The cross-linguistic analysis reveals significant differences. Italian
brain rot is textually more negative, exhibits higher perplexity, and uses more rhyme, while its sound is characterized by higher melodic range and loudness. Romanian audio is spectrally brighter with more erratic pitch variations.
Read the full abstract ▾
All authors Anca Dinu, Andra-Maria Florescu, Marius Micluta-Campeanu, Stefana-Arina Tabusca, Claudiu Creanga, Andreiana Mihail
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
Cryptography and Security
Measuring LLM Agent Defenses by Layer: GDA Measurement and an Envelope-Layer Attack-Defense Model
Yuelin Han
Agent interaction protocols such as ACP and A2A let a remote peer deliver a task the receiving
agent treats as legitimate, opening a channel for indirect
prompt injection. Evaluating and defending such
agents is difficult because the attack success rate (ASR) cannot distinguish an LLM recognition failure from an
agent-layer block, and so cannot indicate which layer to strengthen. We contribute three artifacts. (1) GDA Measurement, a red-team method that captures the raw
agent-LLM context at the gateway, preserves conversation and raw-capture data, and judges outcomes autonomously with an
agent selected by an inter-annotator-agreement (IAA) study over six candidates; its four classes, A/B/C/D, replace ASR with the semantic refusal, semantic breach, interception and penetration rates - a layer-resolved view of defense. (2) A2A-TIBA, an implant-command-exfiltration principle on A2A that generates this method's validation corpus, designed to spread outcomes across the four classes rather than to maximize the success rate. (3) ELA-ITL, a three-layer isomorphic attack-defense model induced from that corpus, which identifies the envelope layer - the channel through which content enters an
agent - as a defense surface; ablating the A2A, tool and
memory channels shows that annotating untrusted content markedly improves recognition of malicious content.
Read the full abstract ▾
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