Machine Learning · Cross-listed from cs.CV
AnswerMap: Faithful Spatial Interpretability of VLMs from Answer Posteriors
Mohamed Eltahir, Fardows Adam, Duaa M. Tahir et al. (+6 more)
When a VLM answers a visual query, current interpretability tools rely on text rationales, which use a mismatched modality, or on internal read-outs, which originate too early to reflect the final output and require white-box access to the model. We introduce AnswerMap, a training-free, task-agnostic, black-box visual rationale constructed from the output head. The image is cut into K row and K column bands, each shown alone to the frozen model along with the query in the format of a yes/no relevance question. The outer product of the row and column “yes” posteriors gives the query-conditioned spatial map. Crucially, by defining a fixed read-out R (e.g., expectation, maximum) on top of AnswerMap, we can derive continuous outputs like location natively. This bypasses the reliance on discrete text
tokens for continuous-output tasks and guarantees an image-dependent answer by construction. However, a rationale can be confabulated, so we validate AnswerMap across four models and three query distributions with two tests: (a) agreement with the model's own generated point and (b) deletion of the map's region. The map lands where the model points (AUC 0.85 against 0.38 for
attention), and deleting its region flips 53% of correct answers (against 19% for
attention's). Beyond establishing faithfulness, we demonstrate the map's task-agnostic utility through three distinct read-outs: its maximum flags hallucinated objects without generation, its expectation localizes correctly when the model's own pointing fails, and its top-mass region, fed back as a crop, fixes half of the model's wrong answers. AnswerMap thus offers a new lens on VLM interpretability and, through its read-outs, a new output interface for visual tasks beyond text
tokens.
Read the full abstract ▾
All authors Mohamed Eltahir, Fardows Adam, Duaa M. Tahir, Lama Alamoudi, Sana Ammar, Atheer A. Alboloshi, Jory Albluey, Tanveer Hussain, Naeemullah Khan
Machine Learning
Disentangling Lung-Cancer CT/LDCT AI: A Systematic Evidence Map of Clinical Tasks, Evidence Chains, and Translational Gaps
Surajit Das
Artificial-intelligence studies using computed
tomography (CT) for lung cancer are often broadly labelled "prediction" despite addressing clinically distinct tasks. We systematically mapped CT/low-dose CT (LDCT)-centered lung-cancer AI using five-database
retrieval, full-text eligibility assessment, role-aware modality/omics extraction, clinical-task classification, and a Multi-Tier Evidence Graph (MTEG). The final corpus comprised 293 studies (2016-2026): 230 Detection, 8 future Risk-prediction, and 55 Other studies. Clinical variables (96.2%), 3D CT/LDCT (73.0%), and radiomics (63.5%) predominated, whereas external validation (29.0%), calibration (20.5%), decision-curve analysis (13.0%), longitudinal CT (17.7%), and saliency/attribution XAI (21.5%) were less frequent. The MTEG comprised 377 nodes and 3,444 edges; only 31 studies (10.6%) completed the six-tier substantive evidence chain, with greatest attrition at
reasoning/explanation. Overall, the literature is detection-dominated, genuine future risk prediction remains uncommon, and complete translational evidence chains are rare.
Read the full abstract ▾
Machine Learning
Long-Horizon Scaling: How Model Capabilities Shape the Returns to Computation
Haoyu Zheng, Zhengyu Chen, Huaisheng Zhu et al. (+5 more)
Long-horizon
agents improve solutions through sustained interaction, execution, and task feedback. Scaling studies relate performance to resources and capabilities, yet how existing capabilities shape returns to extended interaction remains less understood. To address this gap, we analyze AutoLab and EdgeBench, two long-horizon
benchmarks. We find that starting performance and subsequent growth are associated with different capabilities: within a task category, similar early scores can precede different later gains. To formalize this finding, we model capability-time scaling with category-specific logistic power laws shared across models. Fitted to early trajectories, these curves extrapolate the observed models' category-average scores to later computation. However, rising average scores mask narrowing improvement opportunities: later gains concentrate among fewer improving models. High final scores and continued improvement also have distinct capability profiles. Predicted mean gains estimate each model's fraction of improving tasks; averaging these estimates forecasts the average share of improving models. These uneven returns motivate deciding whether a specific run should continue. We therefore derive a continuation policy to save time and compute with limited score loss. The policy conditions growth predictions on the run's observed progress and weighs immediate and delayed gains against computation costs. In replay with training and price calibration based on other models' histories, the policy saves roughly one-third of full-run time, with relative score losses of 2.4% on AutoLab individual runs and 3.3% on EdgeBench published mean curves. Our repository is available at https://github.com/Chihaya-Anon-chan/long-horizon-scaling.
Read the full abstract ▾
All authors Haoyu Zheng, Zhengyu Chen, Huaisheng Zhu, Ruishan Fang, Teng Xiao, Yiwei Li, Jingang Wang, Wenqiao Zhang
Machine Learning · Cross-listed from cs.CV
Beyond Selection: Token Parameterization for Extreme Visual Token Compression
Rui Zhong, Yu Li, Zheyu Yan et al. (+1 more)
Visual-
token compression is effective for improving the efficiency of
vision-
language models, but under extreme compression budgets,
token pruning can break visual grounding while learned resamplers increase parameter count,
attention cost, and training complexity. We revisit compression through a
token parameterization lens, separating (i) basis transformation and structured truncation (retained subspace/compressibility) from (ii) coordinate organization (optimization and cross-modal
alignment). This view yields two coupled objectives, compressibility and learnability, which we formalize as unified functionals. Guided by these objectives, we design Braco, a lightweight four-step coder that combines transform-basis truncation, input-independent basis-coordinate
embeddings, budget-dependent orthogonal re-parameterization, and learned spatial residual
tokens from lightweight pooling. Experiments show that Braco forms the favorable empirical accuracy-efficiency frontier under $23\times$–$64\times$ compression and remains competitive at $144\times$, reaching 95.2% accuracy while reducing prefill FLOPs by 84.2%–86.7% relative to the uncompressed upper bound. Against prior methods, Braco matches or improves accuracy while achieving up to approximately 36% end-to-end speedup and using $16.6\times$/$78.8\times$ lower compressor latency/FLOPs.
Read the full abstract ▾
All authors Rui Zhong, Yu Li, Zheyu Yan, Cheng Zhuo
Machine Learning
TANGO: Watermarking Masked Diffusion Language Models in Token Pairs
Kasra Arabi, Nir Weinberger, Micah Goldblum et al. (+1 more)
Masked-
diffusion language models fill in masked positions in parallel and in no fixed order. Most practical text watermarks assume left-to-right generation. They key each
token to the
tokens before it, and in a
diffusion model those
tokens may still be masked. A fixed green list needs no such context, but it favors the same
tokens at every position, so these
tokens appear more often in watermarked text. An attacker who compares
token frequencies in watermarked and unwatermarked text can recover the list and forge text that the provider's own detector accepts. We present TANGO, a watermark for masked-
diffusion language models that keys each new
token to a nearby
token that is already unmasked. A secret key splits the vocabulary into color classes, and TANGO biases the new
token toward a color determined by the key and the nearby
token's color. The watermark is therefore embedded in pairs of
tokens. Because the favored color changes from position to position,
token frequencies stay much closer to those of unwatermarked text than under a fixed green list. Detection needs only the text and the key, and it does not assume any unmasking order. On two masked-
diffusion models, TANGO detects nearly all unedited watermarked texts and most edited ones, and frequency attacks that forge the fixed green list fail against it.
Read the full abstract ▾
All authors Kasra Arabi, Nir Weinberger, Micah Goldblum, Niv Cohen
Machine Learning
Temporal Heterogeneous Graph Pretraining for Relational Deep Learning
Yixin Peng, Er Jin, Diego Collarana et al. (+1 more)
Relational deep learning models database rows and foreign-key links as a heterogeneous graph for prediction from record attributes and relational context. These graphs contain two distinct temporal signals: record age changes with the prediction cutoff, while intervals between observed records remain fixed. Prior work often treats time as a single signal or studies temporal representation and pretraining separately. We investigate how explicitly encoding both signals affects temporal pretraining for downstream tasks. Our framework combines Multi-scale Time Encoding, which captures record age using learnable time scales and type-specific projections, with Rotary Time Encoding, which represents signed inter-record intervals through rotary transformations during graph propagation. We pair these encodings with three self-supervised objectives: historical relation recovery, horizon-aware future relation activity prediction, and temporal subgraph contrast. All inputs respect their observation cutoffs. Pretraining proceeds in two stages: subgraph contrast first learns neighborhood representations, followed by refinement through either relation recovery or future activity prediction. We evaluate on five RelBench
datasets across 11 classification and regression tasks using heterogeneous GNN and graph
Transformer backbones. With both encodings, the best evaluated staged schedules improve over supervised training with the same encodings by 3.02% and 1.06% on the two backbones, respectively, and over controls without pretraining or either encoding by 3.24% and 2.37%.
Read the full abstract ▾
All authors Yixin Peng, Er Jin, Diego Collarana, Stefan Decker
Machine Learning · Cross-listed from stat.ML
A Hierarchy of Entropy-Shapley Games for Multivariate Predictive Uncertainty
Niklas Koenen, Claudia Battistin, Jeriek Van den Abeele et al. (+1 more)
Modern probabilistic machine learning models increasingly produce multivariate outputs with complex dependence structure, from multi-step time-series forecasts to sample path predictions. Understanding which input features drive the predictive uncertainty is important for risk-aware decisions, model diagnostics, and deciding whether the uncertainty should be mitigated or hedged against. This attribution problem requires a choice of how dependencies between output components are treated. Existing approaches reduce the output to a scalar through aggregation or projection before attribution, thereby obscuring whether features affect marginal uncertainty, dependence structure, or both, while component-wise analyses can miss dependence effects entirely. We close this gap by introducing a hierarchy of three
entropy-based Shapley games that make this output-side choice explicit for any ordered multivariate outcome, ranging from per-component marginal
entropy to fully joint
entropy. The hierarchy isolates a cross-component attribution term that captures how each feature shifts the dependence between output components, a quantity invisible to component-wise methods. We establish a chain-rule decomposition of the joint attribution and characterize the cross-component term through conditional total correlation, providing both closed-form and sample-based
estimators. Finally, we demonstrate how the framework captures differences in learned joint structure across probabilistic models from distributional regression to a zero-shot time series foundation model.
Read the full abstract ▾
All authors Niklas Koenen, Claudia Battistin, Jeriek Van den Abeele, Martin Jullum
Machine Learning · Cross-listed from q-bio.QM
Uncertainty Quantification in Cardiac Model Personalisation from Ultrafast Ultrasound
Camilla Ferrario, Maelys Venet, Olivier Villemain et al. (+1 more)
Cardiac model personalisation requires inferring mechanical parameters that are not directly measurable in vivo. Ultrafast ultrasound shear wave elastography (SWE) enables non-invasive tracking of myocardial stiffness dynamics over the cardiac cycle, providing a target for personalisation. However, mapping these observations to subject specific model parameters remains ill-posed, as multiple parameter sets can reproduce the same stiffness dynamics. We formulate SWE-informed personalisation as a statistical inference problem using simulation-based inference (SBI). Using a subject-adapted 0D cardiovascular model and neural posterior estimation, we estimate model-conditional posterior distributions over active stiffness scale k0, contraction rate kATP, and relaxation rate kSR, conditioned on SWE-derived curve features and subject specific context. Among six healthy volunteers, four passed objective prior-support diagnostics and were retained for quantitative posterior analysis. Curve-level RMSE against the observed SWE target decreased from 12.61 $\pm$ 5.55 kPa for the prior predictive median to 1.14 $\pm$ 0.38 kPa for the posterior predictive median, an 89.7 $\pm$ 4.2% reduction. Posterior analysis revealed parameter-specific uncertainty, k0-kATP compensation, weaker constraint of kSR, and the importance of prior-predictive diagnostics for assessing whether each subject is represented within the modelled SWE feature space. These results support SBI for uncertainty aware SWE-based personalisation, while identifying prior support and forward-model adequacy as key diagnostics.
Read the full abstract ▾
All authors Camilla Ferrario, Maelys Venet, Olivier Villemain, Maxime Sermesant
Machine Learning
Adversarial Consistency-Guided Representation Learning for Multi-view Clustering
Yuchen Lin, Kunpeng Xu, Ying Fang et al. (+1 more)
Multi-view clustering aims to capture cross-view consistency while exploiting view-specific information. However, shared representations learned to capture cross-view consistency may still retain view-identifying information, potentially compromising the consistency of cross-view clustering structures. To address this issue, we propose ACGRL, an
adversarial consistency-guided representation learning framework for multi-view clustering. ACGRL employs a gradient-reversal view discriminator to reduce view identifiability and obtain invariant reference representations. These representations are then frozen to provide fixed references for disentangling view-specific information from cross-view common information in the subsequent learning stage. The fixed reference representations are concatenated with the learned view-specific representations for reconstruction and clustering, with cross-view cluster
alignment encouraging consistent clustering assignments. Experiments on four
benchmark datasets demonstrate the superior clustering performance of ACGRL compared with representative multi-view clustering methods.
Read the full abstract ▾
All authors Yuchen Lin, Kunpeng Xu, Ying Fang, Lifei Chen
Machine Learning · Cross-listed from cs.RO
ReCAT: Remember, Count, and Time: Structured Recurrent Memory for Robot Manipulation
Pankhuri Vanjani, Mostafa Hatab, Can Mizrakli et al. (+4 more)
Memory-dependent manipulation requires
robots to make decisions using information that is no longer available to their current sensors, such as recalling an earlier visual cue, tracking task progress, counting repeated events, or estimating elapsed time. We present ReCAT, a
language-conditioned policy with structured recurrent
memory. An instruction-conditioned encoder forms features from the current observation. A recurrent
memory integrates the observation stream through Mamba-2 layers and one causal
attention layer. A flow-matching
Transformer decoder reads the current and the historical representation through separate cross-
attention in every block. ReCAT reaches 95.3% average success on LIBERO and 62.4% on RMBench, with the best or tied-best result on six of nine tasks. On three real-
robot tasks probing spatial recall, event counting, and interval timing, the best ReCAT variant reaches 66.7% average success, against 8.3% for the strongest short-history baseline. Controlled comparisons within ReCAT show that the observation encoder and every-block
memory conditioning are needed for this performance. They also show that update rules developed for efficient sequence modeling behave differently as
robot memory: additive updates have the highest observed success on counting and timing, and delta-rule updates on spatial recall. Project website is at https://intuitive-
robots.github.io/ReCAT
Read the full abstract ▾
All authors Pankhuri Vanjani, Mostafa Hatab, Can Mizrakli, Vaisakh Shaj, Zhuoyue Li, Moritz Reuss, Rudolf Lioutikov
Machine Learning
ConRAG: Lightweight inference of multi-hop relations
Kilian Bänziger, Sonia Laguna, Markus Kreft et al. (+4 more)
Understanding how two entities are connected often requires tracing multi-hop relations across documents to identify intermediate entities and supporting evidence that explain a connection. This is a task that appears frequently in scientific research and other knowledge-intensive analyses. We formalise this setting as multi-hop relation inference: given two known endpoint entities, we aim to recover the bridge entities and evidence-grounded
reasoning chains that connect them across a document corpus, and to generate an explanation grounded in the retrieved evidence. Existing multi-hop RAG systems typically seek an unknown answer entity rather than explicitly recovering the connection between two known endpoints and graph-based approaches often rely on costly LLM-extracted knowledge graphs that limit scalability to large document collections. We introduce ConRAG, which builds a lightweight entity-document graph from entity co-occurrence and LLM-based entity filtering. Its connective
retrieval infers and semantically ranks paths between two endpoints. On MuSiQue and 2WikiMultiHopQA, ConRAG consistently improves bridge entity and
reasoning chain recovery over strong RAG baselines, while reducing graph-indexing
token cost by up to roughly 1.5 orders of magnitude. Our results show that endpoint-constrained path
retrieval provides an effective and index-efficient approach to evidence-grounded relation discovery.
Read the full abstract ▾
All authors Kilian Bänziger, Sonia Laguna, Markus Kreft, Robert Jakob, Kevin O'Sullivan, Lasse B. Strand, Julia E. Vogt
Machine Learning · Cross-listed from cs.CV
G$^3$-LoRA: Organizing Reward-Weighted Video Data with Gradient-Guided Grouped LoRA
Jia Song, Wenhow Li, Lichen Bai et al. (+2 more)
Post-training foundation
video models on heterogeneous reward-weighted data usually assume that all data categories induce compatible updates. This assumption is fragile when categories correspond to different skills, domains, or evaluation dimensions. We study this problem in text-to-
video post-training, where VBench2.0 dimensions define data buckets and an external
multimodal reward pipeline assigns sample weights. We propose G$^3$-LoRA (Gradient-Guided Grouped LoRA), a data organization procedure that probes category-level gradients induced by reward-weighted
video samples, removes the shared global update direction, clusters categories by residual gradient compatibility, trains group-specific LoRA experts, and consolidates them into one adapter by weight merging followed by on-policy
distillation from the experts. We motivate this procedure by viewing reward-weighted flow matching as velocity-field regression: incompatible reward dimensions may prefer different denoising directions in overlapping noisy latent regions, causing shared LoRA training to average capabilities. On Wan2.1-T2V-1.3B-Diffusers, the merged grouped adapter improves the matched VBench2.0 evaluation over the base model, a joint reward-weighted LoRA baseline, and random, semantic, and raw-gradient partitions trained with the same pipeline; an independent evaluator agrees, and on CogVideoX-2B grouping avoids the negative transfer of joint training. The gain is not uniform: merging compresses the largest specialist gains,
distillation recovers part of this loss, and camera motion and several local-quality dimensions remain challenging. Together, these results suggest that gradient compatibility can serve as a practical diagnostic for organizing reward-weighted
video post-training data.
Read the full abstract ▾
All authors Jia Song, Wenhow Li, Lichen Bai, Bada Ye, Zeke Xie
Machine Learning
Subgroup Rank-1 Lattice for Practical High-dimensional Black-box Integral Approximation
Yueming Lyu
Estimating integrals of black-box, high-dimensional functions, from expectations and kernel mean
embeddings to the softmax kernel in self-
attention, is a basic subroutine in machine learning. Rank-1
lattice rules suit this setting: they query the integrand only at a fixed point set and need no gradients. When the $n$ points serve as a design
matrix $X\in\mathbb{R}^{n\times d}$ for a feature map, however, computing $\Psi(X)^\top v$ or $\Psi(X)w$ for an elementwise nonlinearity $\Psi$ costs $O(nd)$ time and
memory for any standard quasi-Monte Carlo point set. We study subgroup rank-1
lattices, whose Korobov generator $(1,t,\dots,t^{d-1})$ uses a scalar $t$ of fixed multiplicative order $m$. Splitting $\mathbb{F}_n^\times$ into cosets of $\langle t\rangle$ reduces both maps to short cyclic correlations evaluated by FFT, giving exact results for arbitrary $\Psi$ in $O(n\log m)$ time and $O(n)$
memory, without forming $X$. Since fixing $m$ falls outside classical component-by-component theory, we prove convergence directly: via resultants with the cyclotomic
polynomial $\Phi_m$, the squared worst-case error in the Korobov space decays as $O(n^{-(\alpha-1)/(m-1)})$ for
prime $m\ge d+1$, and this threshold is exact. Using the splitting of $n$ in $\mathbb{Q}(\zeta_m)$, averaging over the $m-1$ admissible generators improves the constant by a factor $\Theta(m-1)$. Empirically, the subgroup
lattice beats Gaussian and orthogonal random features and scrambled Sobol' and Halton points in 49 of 54 synthetic kernel-estimation settings and all 45 softmax-
attention settings on nine real
datasets, and builds a sample set with $d=2048$, $n\approx4.1\times10^7$ in 2.3 ms.
Read the full abstract ▾
Machine Learning
ProtoSeam: Lifting Classifier Training with Latent Gaussian Mixture Models
Robert Lampel, Timon Klein and Sebastian Sager
We propose a lifted reformulation of supervised classification that improves the final accuracy of standard classifiers without changing the architecture at inference time. A network $N=N_2\circ N_1$ is split at a single semantic interface and one learnable prototype per class is inserted there. Training combines a quadratic consensus penalty that pulls $N_1(x)$ toward the prototype of its class with a classification loss of $N_2$ evaluated on samples drawn around the prototypes, whereat no gradient crosses the interface. At inference the prototypes are discarded and the unmodified network $N_2\circ N_1$ is used. Across CIFAR-10, CIFAR-100, and TinyImageNet with ResNet and
vision transformer backbones, lifted training improves test accuracy by up to five percentage points over variants without lifting under a shared tuning protocol. Moreover, we provide theoretical justification of those results.
Read the full abstract ▾
Machine Learning
QAM: Quadratic-Accurate Checkpoint Merging via Sequential Consistency
Shihao Wang, Rui Kong, Xinran Chen et al. (+7 more)
Saved checkpoints record states along a training trajectory, but generally do not determine the updates at states that would be visited under a different schedule. We study how accurately these checkpoints can reconstruct the endpoint of a sequential reference with prescribed update strengths. Under a common local transition model, two checkpoint-index moment conditions characterize all convex merges that agree with this reference through second order. We then prove an information limit that for nondegenerate profiles, no
algorithm using only a fixed-length gradient-descent (GD) history with step size $h$ can achieve $o(h^3)$ endpoint error uniformly over a fixed class of smooth, strongly convex losses. The lower bound follows from two losses with identical GD checkpoint histories but sequential reference endpoints separated by $\Omega(h^3)$. Quadratic-Accurate Merging (QAM) achieves a matching uniform $O(h^3)$ endpoint error bound. Its explicit coefficients also define the unique profile-dependent merge that exactly matches the sequential GD reference across all fixed quadratic objectives. Across two public Adam checkpoint trajectories (SmolLM3-3B and OpenEuroLLM-Prelude-9B), three windows and three profiles per model, and 15 tasks, QAM shows mixed results for short windows and broader advantages over Warmup-Stable and Merge (WSM) for longer windows. Matched-moment GSM8K diagnostics further show that local consistency alone does not fully determine downstream scores. These results characterize the reconstruction limits of saved histories, provide a coefficient rule that attains the optimal rate, and assess its practical utility.
Read the full abstract ▾
All authors Shihao Wang, Rui Kong, Xinran Chen, Hui Wu, Qipeng Qian, Jinman Zhao, Jiashu Zhao, Yuchen Li, Jimmy Huang, Dawei Yin
Machine Learning
EdgeCraft: Automated Model Crafting for Edge IoT
Genglin Wang, Kaiwei Liu, Liekang Zeng et al. (+4 more)
Machine learning (ML) increasingly powers Internet of Things (IoT) applications at the edge. Yet producing a deployable edge ML artifact for a specific scenario requires navigating a huge search space spanning data representation, model design, training on domain-specific data, and runtime customization. This workflow is fragmented and difficult to scale across diverse edge applications. We present EdgeCraft, an LLM-driven system that turns high-level intent into deployable edge ML artifacts. Building such a system raises two challenges: (1) How can an LLM be guided to find high-quality solutions that meet dynamic SLOs for task quality, latency, and energy? (2) How can trustworthy target-device verification be obtained at low cost? EdgeCraft addresses these challenges with two designs. (1) A constraint-aware synthesis tree explores alternative candidates and uses measured SLO gaps to guide each improvement. (2) A multi-fidelity verifier progressively combines low-cost checks with full target-device verification to reduce verification cost while preserving reliable verification results. It also records verified failures for reuse, avoiding repeated device work. To support concurrency, EdgeCraft provides a multi-tenant runtime that runs cloud training and target-device verification in parallel while isolating requests. Across 50 public tasks, EdgeCraft exceeds the task-specific Reference in best-observed quality on 40 tasks and finds an SLO-feasible artifact on 45, with the two outcomes overlapping on 38 tasks. Moreover, EdgeCraft achieves competitive performance on our self-collected SEN
dataset, suggesting its generalizability to real-world IoT sensing tasks.
Read the full abstract ▾
All authors Genglin Wang, Kaiwei Liu, Liekang Zeng, Wangsong Yin, Shangcheng Jin, Guoliang Xing, Zhenyu Yan
Machine Learning
Learning to Re-Draft: A Variational Stackelberg Game for Discrete Diffusion
Dmitrii Moor, Federico Tomasi, Paul N. Bennett et al. (+2 more)
Discrete
diffusion models offer the ability to re-draft, revisiting and correcting earlier
tokens throughout generation. This capability depends on the forward corruption process that defines what the denoiser learns to correct. Masked
diffusion models fix
tokens once they are unmasked, while uniform
diffusion permits revisions but relies on uniformly random
token substitutions. We instead learn which substitutions are most useful for training the denoiser to re-draft. We introduce Variational Stackelberg Discrete
Diffusion (VSDD), a framework for learning a semantically aware corruption process. VSDD formulates training as a leader-follower game: the leader defines a Markovian corruption process parameterized by the denoiser's
token embeddings, while the follower optimizes a variational denoising objective with the corruption process held fixed. The leader rewards corruptions based on how much the denoiser improves after learning from them, rather than on how easily the current denoiser can reconstruct them. We measure this improvement under a fixed reference corruption process, approximate the follower's response with a one-step gradient update, and optimize the leader using a score-function
estimator. We evaluate VSDD across molecular, text, and playlist generation. VSDD substantially improves molecular validity over uniform and masked
diffusion, reduces text perplexity relative to uniform
diffusion while remaining competitive with masked
diffusion, and achieves sizable improvements in offline playlist recommendation metrics.
Read the full abstract ▾
All authors Dmitrii Moor, Federico Tomasi, Paul N. Bennett, Alice Wang, Mounia Lalmas
Machine Learning
Small transformers track Bayesian evidence for latent common causes via a context-invariant mechanism
Amir Mohammadpour and Michael Franke
We present an in-depth investigation of how a form of
Bayesian reasoning about common causes can emerge as a cross-contextual generalization in small, tractable
transformers. Incrementing on recent work, our set-up (i) disentangles causal mechanisms in the model from the causal structure of the true data-generating process, (ii) orients more towards natural
language prediction by considering inference of latent common causes, and (iii) considers whether and how
Bayesian evidence accumulation for latent common causes can be implemented in representations and mechanisms that allow for cross-context generalization to novel test cases.
Read the full abstract ▾
Machine Learning · Cross-listed from math.OC
Coordinated Lane-Level Variable Speed Limits and Ramp Metering for Successive Weaving Segments Considering Merging/Diverging Risks: A Hybrid Model Predictive Control and Multi-Agent Reinforcement Learning Approach
Guodong Ma, Baofeng Sun, Wenyu Yang et al. (+1 more)
Successive weaving segments (SWSs) on urban expressways are bottlenecks prone to recurrent congestion and collisions, requiring fine-grained active traffic management (ATM). Existing approaches struggle to balance the adaptive performance of data-driven optimization with the resilience and transferability of model-based control. We propose a hybrid framework to coordinate lane-level variable speed limits (VSLs) and ramp metering across SWSs. First, we reconstruct L-METANET, a lane-level macroscopic traffic flow model that captures free and forced lane changes. Second, we combine XGBoost-SHAP with a random-parameters binary logit (RPBL) model to derive analytical equations for merging and diverging collision risks and formulate system cost and reward functions. Third, we develop MPC-STMAPPO, a hierarchical controller integrating model predictive control (MPC) and multi-
agent reinforcement learning (MARL). Its upper MPC layer uses L-METANET for long-horizon rolling optimization and generates baseline commands; its lower spatiotemporal MAPPO (ST-MAPPO) layer, enhanced with Mamba
cells and graph
attention, produces residual actions for short-horizon adjustment. Real-world experiments on the 18-km Eastern Expressway in Changchun, China, show that L-METANET accurately reproduces lane-changing-induced flow redistribution and capacity drops, with state
evolution aligned with ground truth. XGBoost-SHAP-RPBL achieves AUCs above 0.80 in most tasks, outperforming conventional logit models. MPC-STMAPPO converges faster and performs better across multiple metrics than MPC- and MARL-based baselines. Under randomly fluctuating demand, it also significantly outperforms pure MARL in generalization, demonstrating strong potential for industrial deployment.
Read the full abstract ▾
All authors Guodong Ma, Baofeng Sun, Wenyu Yang, Zhihong Yao
Machine Learning
CacheRepair: Learning to Repair Cross-Chunk Context in RAG for KV Cache Fusion
Genglin Wang, Wangsong Yin, Yeerzhati Abudunuer et al. (+3 more)
Multi-document
retrieval-augmented generation (RAG) requires a
language model to process multiple retrieved text chunks before answering a question. Precomputing each chunk's KV cache independently and concatenating the caches when the chunks are retrieved can accelerate this step. However, the assembled cache lacks cross-chunk
attention information, reducing answer quality. Selective recomputation methods recover the missing cross-chunk context by rerunning the target LLM on selected
tokens, incurring substantial online computation. We introduce CacheRepair, a lightweight network that learns the difference between independently computed KV caches and those produced by processing the chunks together. The network combines compressed KV features with
token embeddings and uses
attention that is bidirectional within each chunk and flows from earlier to later chunks. Each repair block receives the compressed cache features, and the predicted residual is added to every document
token's cache. Each repair network is trained for a specific frozen target LLM on a generic
retrieval corpus and reused across downstream
datasets. Our analysis shows that repair reduces KV errors both near chunk boundaries and throughout chunk interiors. Evaluation across three target LLMs and four downstream
datasets places CacheRepair on the measured answer-quality-latency Pareto frontier in eleven of twelve model-
dataset combinations. Reported time to first
token (TTFT) includes online cache transfer and repair. Across all twelve combinations, the largest repairers achieve 1.69-4.61$\times$ speedups in median TTFT over full prefill and improve mean F1 by 2.1-26.1 percentage points over direct cache reuse.
Read the full abstract ▾
All authors Genglin Wang, Wangsong Yin, Yeerzhati Abudunuer, Haoxuan Xu, Guoliang Xing, Zhenyu Yan
Machine Learning
FlexiWorld: Learning and Planning via Flexible Action Chunks Across Multiple Time Scales
Shidu Ren, Qilin Gu, Zhenghao Ni et al. (+4 more)
Latent world models predict future states for goal-directed planning using action chunks spanning multiple primitive steps. Existing methods typically use fixed-length chunks and either omit goal-conditioned action generation or limit their supervision to short goal spans. We introduce FlexiWorld, a JEPA-based world model that combines mixed-span goal supervision with variable-length action chunks to improve long-horizon control. During training, we sample varying goal spans and randomly partition the actions into variable-length chunks. We jointly train the world model with a causal action encoder that embeds variable-length chunks and an autoregressive actor that generates primitive actions sequentially. Student Forcing reduces exposure bias by training on generated action prefixes. For planning, Actor-Residual Cross-
Entropy Method (ARCEM) combines action-residual search with within-chunk autoregressive feedback and chunk-boundary latent prediction. Across four
benchmarks and goal distances, FlexiWorld with ARCEM achieves 89.29% mean success, compared with 83.98% for the strongest baseline. PushT ablations show improved direct control from mixed-span supervision, variable-length chunks, and Student Forcing. Without retraining, FlexiWorld supports different planning chunk lengths: longer chunks accelerate ARCEM by approximately $1.3\times$ on average while maintaining comparable average success.
Read the full abstract ▾
All authors Shidu Ren, Qilin Gu, Zhenghao Ni, Junhan Sun, Jiaqi Wang, Damien Scieur, Yunze Liu
Machine Learning
CTP-FL: Common-Trajectory Gradient Prediction for Federated Learning
Junkang Liu
Communication-efficient
federated optimization commonly spends several gradient evaluations between server updates. Existing local-update methods use this computation to advance an independent model on each client. Under heterogeneous data, however, these models evaluate gradients at different locations, making the aggregated update difficult to interpret as a gradient of the global objective. We study an alternative use of the same computation budget: evaluate the global objective along a shared, predicted path. We propose Common-Trajectory Predictive
Federated Learning (CTP-FL). At each round, all clients construct the same sequence of query points from the current global model and the previous aggregated direction, evaluate $K$
stochastic gradients along this sequence, and upload their average. The server then performs a single global update. Thus, CTP-FL uses $K$ mini-batch gradients per client and one model-sized vector in each communication direction, matching the per-round computation and communication of full-participation FedAvg-M. Shared query points make the aggregated direction an unbiased
estimator of the average global gradient along the predicted path. The remaining discrepancy from the gradient at the current model is controlled by the path length, without assuming bounded client-gradient dissimilarity or bounded gradients. For smooth non-convex objectives, we establish an $\mathcal{O}\!\left( \sqrt{L\Delta\sigma^2/(NKR)}+L\Delta/R \right)$ average-stationarity bound under full participation. The analysis isolates a testable trade-off: extending the prediction path provides more forward-looking gradient information but increases its displacement bias.
Read the full abstract ▾
Machine Learning
Explaining Hyperbolic Neural Networks via Geometry-Aware Relevance Propagation
Ping Xiong, Shanglin Li, Yi Ding et al. (+2 more)
Hyperbolic neural networks introduce
geometric operations that require explicit treatment in relevance propagation. Equivalent
geometric realizations can produce different feature attributions, even when local relevance is conserved. We study this problem through
Geometric Representation Invariance (GRI), a specialization of Implementation Invariance, and zero-
curvature consistency, which requires identity relevance propagation when a
geometric module approaches the identity. We propose LRP-radial-all for origin-centered radial modules, treating
geometric scaling as modulation and assigning relevance entirely to the signal branch. The rule conserves relevance, is invariant to equivalent radial factorizations, and satisfies zero-
curvature consistency, yielding GRI for a specified Poincaré-Lorentz logarithmic-map construction. In contrast, a conservative LRP-half baseline can violate both consistency criteria. Experiments on
hyperbolic MNIST, sEEG, and CIFAR-10 classifiers assess attribution fidelity, qualitative explanations, and runtime. LRP-radial-all achieves competitive attribution fidelity across
datasets with runtime comparable to Gradient$\times$Input and substantially lower than Integrated Gradients. These findings motivate geometry-aware propagation rules that distinguish relevance conservation from consistency across equivalent computations.
Read the full abstract ▾
All authors Ping Xiong, Shanglin Li, Yi Ding, Thomas Schnake, Shinichi Nakajima
Machine Learning
A Multimodal Autonomic Sensing Framework for Objective Assessment of Patient Responses to Dental Pulp Stimulation
Youngsun Kong, Yubin Choi, Dongjin Song et al. (+3 more)
Patient responses to dental pulp testing, ranging from no sensation to intense pain, provide important information for assessing pulp status in endodontic diagnosis. However, pain is a subjective sensory and emotional experience that varies considerably across individuals and can be difficult to communicate. We investigated whether complementary autonomic signals could support objective assessment of responses during dental examination. Forty-nine patients underwent cold pulp testing, yielding no-response, mild-response, and intense-response conditions. The framework integrated ECG-derived skin nerve activity (SKNA) and R-R intervals (RRI), together with electrodermal activity (EDA), using temporal convolutional network encoders with
attention-based mid-level fusion. Individual baseline signals and subject-level
covariates, including anxiety scores and biological sex, were also incorporated. The framework achieved 80.2% balanced accuracy, 75.2% sensitivity, and 85.2% specificity for binary classification of no response versus mild or intense response. For three-class classification, it achieved 60.0% balanced accuracy and a 58.8% macro-averaged F1 score. Ablation and
attention-weight analyses indicated that EDA contributed most strongly to model performance, followed by RRI, while SKNA improved balanced accuracy by approximately five percentage points. Age was significantly associated with model performance. These findings support the feasibility of
multimodal autonomic sensing for objective, non-invasive assessment of responses to dental pulp stimulation.
Read the full abstract ▾
All authors Youngsun Kong, Yubin Choi, Dongjin Song, Dong-Guk Shin, I-Ping Chen, Ki Chon
Machine Learning
SymbolicArena: A Unified Infrastructure for Benchmark Distillation and Dynamic Evaluation in Symbolic Regression
Ziwen Zhang, Xiju Wu, Yuheng Jing et al. (+9 more)
Symbolic regression (SR) seeks concise and interpretable mathematical expressions from data for scientific equation discovery. Existing SR
benchmarks face a tradeoff between evaluation cost and
benchmark validity. Repeated evaluation of large task pools is expensive, and compact
benchmarks lack systematic evidence of preserved task diversity and
algorithm discriminability. SymbolicArena provides a unified infrastructure for
benchmark distillation and dynamic evaluation. The framework standardizes 664 heterogeneous tasks with executable ground truth expressions and distills the Full Task Set into Core50, a validated
benchmark of 50 tasks. The
distillation process preserves task coverage and
algorithm discrimination under explicit balance constraints. SymbolicArena applies a unified execution protocol to heterogeneous SR
algorithms and produces comparable outputs and search trajectories. Multi Axis Evaluation characterizes numerical quality, symbolic quality, and search behavior. Core50 reduces evaluation workload by 92.5% and maintains agreement with Full Task Set evaluations. Experiments show that SymbolicArena achieves 72.6% to 86.7% lower approximation error than alternative selectors, further supporting its fidelity to the Full Task Set. Evaluation reveals a substantial gap between numerical fitting and symbolic recovery across current SR methods, suggesting that reliable equation recovery remains an open challenge.
Read the full abstract ▾
All authors Ziwen Zhang, Xiju Wu, Yuheng Jing, Runxiang Wang, Boxiao Wang, Yifan Zang, Yifan Zhang, Yang Wang, Kai Li, Yifan Zhang, Huilin Xu, Jian Cheng
Machine Learning · Cross-listed from cs.AI
Sol-H3: Recursive Self-Improvement for MiniMax-H3 Inference Acceleration on Sol-Engine across Cloud and Edge
Yitong Li, Jincheng Yu, Junsong Chen et al. (+6 more)
Video diffusion models are rapidly scaling and exhibiting enhanced generation capabilities. Among these recent advancements, MiniMax-H3 stands out as a highly capable, production-level open-source model. However, its 33-billion parameters and multi-step iterative denoising process introduce substantial computational overhead. Consequently, their practical production is hindered by generation latency in the cloud deployment like NVIDIA-GB200, alongside strict
memory limits that pose further challenges at the edge device like DGX-Spark. To address these diverse hardware bottlenecks from cloud to edge device, we present a full-stack inference pipeline that integrates efficient algorithmic design with optimized operator implementations. Algorithmically, we introduce a cross-resolution two-stage generation scheduler that exploits the step-wise nature of
diffusion: early low-resolution steps rapidly establish the global layout, while later high-resolution steps focus refinements of local and perceptual details. These stages are connected by a learned latent-to-latent mapping module, completely eliminating the computationally expensive VAE decode-reencode cycle for resolution transferring cross different resolutions. For operator implementation, we deploy a Recursive Self-Improvement (RSI) loop that searches kernel fusions and
memory layouts, evaluating latency together with numerical agreement. Together, these optimizations deliver up to 30x end-to-end speedup and 20% lower
memory: a 5-second 1344x768
video with audio is generated 3.5x faster than real time on an 8xGB200 node, and in under a minute fully
memory-resident on a single DGX Spark.
Read the full abstract ▾
All authors Yitong Li, Jincheng Yu, Junsong Chen, Haopeng Li, Shuchen Xue, Haozhe Liu, Ping Luo, Song Han, Enze Xie
Machine Learning
DRIFT: Disentangled Responsive-Invariant Flow Transport for Single-Cell Perturbation Prediction
Mustapha Bounoua, Giulio Franzese and Pietro Michiardi
Predicting cellular responses to perturbations is a central problem in cellular biology, with broad applications in systems biology and drug discovery. This task is challenging because cellular responses can be complex and
cell-state dependent, intrinsic
cell-to-
cell variability can be confounded with perturbation effects, and destructive single-
cell RNA sequencing precludes paired measurements of the same
cell before and after treatment. Flow matching transports control
cells to perturbed states flexibly, but acting on the full
cell state can confound perturbation effects with pre-existing
cell-to-
cell variability. Disentangled approaches separate responsive from invariant components, but model perturbations through prescribed mechanisms, such as latent shifts or graph edits, limiting their flexibility. We address both limitations in a unified framework. A variational encoder disentangles each
cell into an invariant block, capturing state unaffected by the perturbation, and a responsive block, capturing state it changes, through conditional priors and an information-theoretic invariance constraint. Conditional flow matching transports only the responsive block, conditioned on the perturbation and invariant state, yielding a flexible, data-driven model of perturbation effects without confounding pre-existing variability. Across several
benchmarks, our method outperforms the strongest published method in settings involving combinatorial and unseen perturbation prediction.
Read the full abstract ▾
Machine Learning
E3J: An Efficient and Open-Source Backend for Euclidean Equivariant Operations on GPU and TPU
Olivier Peltre, Armand Picard, Adrien Pichard et al. (+6 more)
We present e3j, a fast Euclid-equivariance backend for
geometric deep learning applications with JAX bindings for GPU and TPU. Leveraging both optimized CUDA and Pallas kernels and algorithmic improvements, the library achieves state-of-the-art throughput and runtime on both forward and backward paths. On a machine learning interatomic potential (MLIP) use case, it outperforms established backends, measuring up to 34% speed-up over cuEquivariance on water box NPT simulation using MACE, while remaining fully open source. E3j achieves over 80% efficiency over the H100 maximum
memory bandwidth on tensor product operations, and in many cases more than doubles throughput of message passing convolutions forward compared to previously available backends. In addition, with the release of dedicated Pallas TPU kernel, e3j opens the possibility of large scale equivariant deep learning workloads on TPU architectures, which has so far been difficult to achieve. Our
benchmarks show that e3j also achieves over 80% of a TPUv6e
memory bandwidth, up to one order of magnitude more than e3nn-jax. The library is available on GitHub, PyPI and is released under an open source Apache 2.0 license.
Read the full abstract ▾
All authors Olivier Peltre, Armand Picard, Adrien Pichard, Miguel Bragança, Luca Giacomoni, Valentin Heyraud, Zachary Weller-Davies, Christoph Brunken, Jules Tilly
Machine Learning
SpikeLite: Lightweight Spiking Neural Networks for Time-Series Forecasting
Bang Hu, Changze Lv, Mingjie Li et al. (+3 more)
Spiking neural networks (SNNs) offer an energy-efficient paradigm for time-series
forecasting through spike-driven computation. However, recent SNN forecasters often pursue higher accuracy through increasingly complex
attention mechanisms, or specialized neuronal dynamics, weakening the lightweight motivation of SNNs. We introduce SpikeLite, a spiking
forecasting framework built around two modules: a Frequency-Selective Spiking Encoder (FSSE) for frequency-sensitive temporal encoding and a Sparse Spiking Channel
Attention (SSCA) module for selective cross-channel interaction. FSSE exploits the low-pass filtering behavior of LIF dynamics to reorganize each input sequence into frequency-sensitive components while collectively preserving the input at the decomposition stage. SSCA then learns a binary mask from encoded channel representations and uses it to selectively exchange information within spike-driven self-
attention, retaining informative cross-channel interactions while suppressing redundant ones. When explicit channel interaction is unnecessary, SpikeLite uses the lighter FSSE-only channel-independent path. Experiments under the SeqSNN and SpikF protocols cover four standard multivariate and eight long-term
forecasting benchmarks. SpikeLite achieves the best aggregate performance under both protocols, with an average $R^2$ of 0.790 and RSE of 0.440, and lowest average MSE/MAE of 0.343/0.345 in long-term
forecasting. Moreover, evaluation on the ECL
dataset shows that SpikeLite achieves the lowest reported energy consumption, further demonstrating its potential for energy-efficient time-series
forecasting.
Read the full abstract ▾
All authors Bang Hu, Changze Lv, Mingjie Li, Xiaoqing Zheng, Wei cao, Fan Zhang
Machine Learning · Cross-listed from cs.CV
DF-CBM: Region-Aware Concept Bottleneck Models for Deepfake Detection
Georgios Tsoumplekas, Vazgken Vanian, Alexandros Doumanoglou et al. (+4 more)
Deepfake detection methods have become increasingly effective yet most provide limited insight into the evidence behind their predictions. However, in forensic settings users also need to know which manipulation cues support the decision and where they appear. Existing explainability methods only partially address this need since localization-based approaches lack semantic descriptions while
language-based explanation methods are only weakly grounded in visual evidence. In this work, we propose DF-CBM, a region-aware concept bottleneck model for explainable deepfake detection. DF-CBM builds a compact vocabulary of manipulation-related concepts from textual artifact annotations and links each concept to plausible facial and boundary regions. It then predicts these concepts from visual features using a concept-specific masked
attention mechanism guided by parsed facial masks and the final real/fake decision is made from the predicted concept bottleneck. Our experiments show that DF-CBM outperforms concept-based baselines in concept prediction and deepfake classification while remaining competitive with state-of-the-art black-box detectors. Finally, qualitative results and intervention analyses demonstrate that DF-CBM provides spatially grounded concept evidence and enables counterfactual explanations of how individual manipulation concepts influence the final prediction. Our code is available at: https://github.com/GeorgeTsoumplekas/DF-CBM.
Read the full abstract ▾
All authors Georgios Tsoumplekas, Vazgken Vanian, Alexandros Doumanoglou, Panos K. Papadopoulos, Yannis Spyridis, Dimitrios Zarpalas, Vasileios Argyriou