Machine Learning
AsymVLM: Asymmetric Token Pruning for Efficient Vision-Language Model Inference
Yilin Feng, Ahmed Burak Gulhan and Mahmut Taylan Kandemir
Vision-
Language Models (VLMs) process thousands of visual
tokens per image alongside comparatively few text
tokens, yet existing compression methods treat both modalities uniformly. We observe that the two modalities have fundamentally different properties:
vision tokens are spatially redundant and dominate prefill, while text
tokens are causally dependent and accumulate during decoding. Based on this asymmetry, we propose and empirically evaluate AsymVLM, which applies aggressive
pruning to
vision tokens before prefill using a learned importance scorer with per-sample adaptive budgeting, and temporal threshold-based eviction to text
tokens only when they exceed a fixed budget. Our experiments indicate that AsymVLM achieves the highest FLOPs savings (up to 54%) among state-of-the-art methods while outperforming existing approaches by 2–3% on document and chart understanding tasks where visual information is spatially localized and query-specific, and maintaining competitive accuracy on holistic
benchmarks. In text-dominated scenarios, our eviction strategy substantially outperforms standard LLM cache compression methods by adapting to the short-context nature of VLM.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.SD
Half-Truth Audio Detection and Localisation: A Lightweight Cross-Attentive Architecture and a Cross-Corpus Diagnostic Study
S. Sutharya and Remya K. Sasi
Partially manipulated (half-truth)
speech, where a short synthesised segment is spliced into an otherwise genuine utterance, is a harder and more realistic forensic threat than the fully synthesised deepfakes that dominate the literature. We present CAFNet, a lightweight (576K-parameter, 2.24 MB) cross-attentive architecture that fuses MFCC, LFCC, and Chroma-STFT features to jointly classify audio as real, fully fake, or half-truth, and regress the temporal boundaries of the synthesised region, at approximately 14 ms CPU latency. A component ablation shows cross-
attention fusion is CAFNet's most load-bearing component; a deeply supervised auxiliary classification head from earlier iterations is not, and removing it improves every in-domain metric under 3-seed replication with substantially lower variance. On MLADDC T2+T3 the model reaches 97.55%$\pm$0.69% ternary accuracy and 0.037 s boundary mean absolute error (MAE), to our knowledge, the first reported continuous splice- boundary localisation result on this
benchmark. Zero-shot evaluation on two independent
benchmarks shows transfer is capability- and corpus-dependent rather than uniform: on Half-Truth Audio Detection
dataset (HAD), detection recall reaches 84.9% and ternary classification resolves half-truth correctly on half of true half-truth clips (50.4%), while on PartialSpoof, binary detection stays near chance (AUC 0.5544). We treat this asymmetry, not a single generalization verdict, as the finding. HAD localisation improves in absolute terms but degrades in relative terms, since in-domain localisation improved faster. An architectural change validated purely in-domain thus shifted the cross-corpus transfer profile, evidence that cross-corpus evaluation should accompany, not follow, in-domain architecture decisions.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
Temporal Motif-aware Graph Test-time Adaptation for OOD Blockchain Anomaly Detection
Runang He, Tongya Zheng, Huiling Peng et al. (+6 more)
Ever-evolving transaction patterns have significantly hindered anomaly detection on emerging cryptocurrency blockchains due to the vast number of addresses and diverse anomalous behaviors. Recently, advanced Graph Anomaly Detection (GAD) approaches applied to blockchains have faced two critical challenges:
adversarial pattern
evolution by malicious actors and the out-of-distribution (OOD) problem caused by varied transaction semantics on blockchains. To address these challenges, we propose a novel framework termed TEmporal Motif-aware Graph Test-Time Adaptation (TEMG-TTA). First, we comprehensively capture the 3-node temporal motif distribution of each active address using an efficient computational mechanism, enabling downstream temporal motif-aware graph learning. Second, we design a simple yet effective test-time adaptation strategy to facilitate the sharing of common patterns between training and testing graphs. Extensive experiments on 5 real-world
datasets demonstrate that our proposed TEMG-TTA outperforms state-of-the-art GAD approaches by an average of 54.88%. A further case study on interpretable motif patterns reveals that TEMG-TTA explicitly characterizes the complex transaction patterns of anomalous addresses, thereby verifying the effectiveness of our technical designs. Our code is publicly available at https://github.com/LuoXishuang0712/TEMG-TTA/.
Read the full abstract ▾
All authors Runang He, Tongya Zheng, Huiling Peng, Yuanyu Wan, Bingde Hu, Jiawei Chen, Canghong Jin, Mingli Song, Can Wang
Machine Learning
Learning to Perturb Hidden Representations for Generalizable Deep Learning
Hua Li
Deep neural networks process data through a cascade of representations: input features, hidden activations, logits, and loss. While perturbations at the input, logit, and label levels have been systematically studied, the intermediate hidden activations, which constitute the bulk of the network's computation, have received no unified perturbation analysis. In this paper, we establish a unified framework for hidden activation perturbation, revealing that Dropout,
Manifold Mixup,
adversarial feature perturbation, and related methods all impose specific forms of activation perturbation but with class-agnostic or random strategies. We
conjecture that expansive perturbation (increasing activation norm) acts as positive augmentation, while contractive perturbation (decreasing activation norm) acts as negative augmentation, and that the perturbation layer determines whether the effect resembles input-level augmentation (shallow layers) or logit-level manipulation (deep layers). We propose Learning to Perturb Activations (LPA), which adaptively perturbs activations at a selected hidden layer with class-level perturbations learned via PGD. We further provide theoretical analysis connecting activation perturbation to flat minima and perturbation amplification through layers. Experiments on balanced classification, long-tail classification, and domain generalization demonstrate that LPA consistently outperforms existing methods and provides complementary benefits to logit perturbation methods such as LPL.
Read the full abstract ▾
Machine Learning
K-FinHallu: A Hallucination Detection Benchmark for Multi-Turn RAG in Korean Finance
Eunbyeol Cho, Yunseung Lee, Mirae Kim et al. (+3 more)
Large
Language Models (LLMs) have advanced financial automation through
Retrieval-Augmented Generation (RAG), yet
hallucinations remain a critical barrier to deployment in high-stakes environments. Existing
benchmarks focus on single-turn, English-centric tasks, leaving the multi-turn dynamics and linguistic-regulatory nuances of the Korean financial domain unaddressed. We introduce K-FinHallu, the first
benchmark for
hallucination detection in multi-turn Korean financial RAG. We construct multi-turn dialogues from authentic Korean financial documents and inject
hallucinations under a proposed hierarchical taxonomy based on context answerability that explicitly accounts for justified abstention. Benchmarking frontier and open-source LLMs as
hallucination detectors, we find that even the strongest models struggle with fine-grained financial diagnostics and refusal behavior. While fine-tuning an 8B model on our training split yields performance competitive with frontier LLMs, justified abstention remains the weakest axis across all evaluated models.
Read the full abstract ▾
All authors Eunbyeol Cho, Yunseung Lee, Mirae Kim, Jeewon Yang, Youngjun Kwak, Edward Choi
Machine Learning · Cross-listed from cs.MA
DynaGraph: Lightweight Multi-Model Interaction Framework via Dynamic Topological Reconfiguration
Yanxing Guo, Zihao Zheng, Fangzhou Wu et al. (+4 more)
Tackling complex
reasoning tasks typically relies on massive monolithic LLMs, which suffer from severe computational redundancy. While task decomposition through structured pipelines or multi-
agent collaborations offers an alternative, these approaches inevitably fall into a critical dilemma: predefined static
topologies are highly vulnerable to cascading errors, whereas unconstrained dynamic
agents suffer from trajectory divergence and unpredictable
memory bloat. To address this, we present DynaGraph, a lightweight multi-model framework driven by dynamic topological reconfiguration. At the execution level, DynaGraph multiplexes time-division PEFT adapters over a shared base model, enabling both full system training and inference deployment on a single consumer-grade GPU. At the routing level, the Evaluator continuously monitors execution confidence to trigger hierarchical self-healing: Fine-grained Patching for localized data gaps and Subgraph Reconstruction for severe logical ruptures. Experiments on StrategyQA, MATH, and FinQA demonstrate our 8B model closely approximates the
reasoning capabilities of a 72B monolithic model (e.g., 87.6% on StrategyQA, 82.7% on MATH). Furthermore, it reduces latency by up to 68.1% and
token consumption by 68.6% compared to unconstrained dynamic architectures.
Read the full abstract ▾
All authors Yanxing Guo, Zihao Zheng, Fangzhou Wu, Ling Liang, Lin Bao, Zongwei Wang, Yimao Cai
Machine Learning
Quotient DAGs for Off-Policy Evaluation:Forward-Flow Importance Sampling and Exact Slate Propensities
Ziwen Xie, Shaowen Xiang, Hongyu He et al. (+1 more)
Off-policy evaluation estimates how a target policy would perform using data collected by a different behavior policy, which is crucial when online testing is costly or risky, such as in recommendation or healthcare. Standard importance sampling reweights each logged trajectory, but it can treat details of the generation process as meaningful even when the evaluation target ignores them: for example, an autoregressive slate recommender may generate an ordered sequence of items while the reward and downstream
estimator depend only on the unordered slate. This creates nuisance variance and a computational gap, since exact unordered slate propensities require summing over all generation orders. We introduce a quotient-DAG view that merges histories equivalent for evaluation and assigns weights using target-to-behavior forward-flow ratios on the merged graph. For slate recommendation under a set-sufficient next-item interface, this yields Forward-DP, a subset-DAG dynamic program that computes exact unordered propensities without factorial enumeration. The resulting propensity primitive enables practical propensity-based evaluation and model selection for context-dependent autoregressive slate loggers.
Read the full abstract ▾
All authors Ziwen Xie, Shaowen Xiang, Hongyu He, Dianbo Liu
Machine Learning
Convex Basins in Single-Index Model Loss Landscapes: Applications to Robust Recovery under Strong Adversarial Corruption
Santanu Das, Sagnik Chatterjee and Jatin Batra
We study the problem of robustly learning Gaussian Single Index Models (SIMs) in the presence of heavy-tailed noise and a constant fraction of adversarially corrupted
covariates and responses. Prior work on robust recovery has considered settings such as linear regression (Pensia et al., JASA 2024), strictly monotonic link functions (Awasthi et al., NeurIPS 2022), and phase
retrieval (Buna and Rebeschini, AISTATS 2025). However, these techniques do not extend to generic asymmetric non-monotonic link functions such as GeLU and Swish, which arise naturally as scalar primitives in modern gated neural architectures. We close this gap by giving the first robust recovery
algorithm with near-linear sample and time complexity for generic non-monotonic link functions, thereby establishing the first robust recovery guarantees for a broad family of nonlinear SIMs for which no guarantees were previously known. Our central contribution is a new structural understanding of the Gaussian squared-loss landscape under
adversarial contamination. Crucially, we prove that for a broad class of nonlinear non-monotonic SIMs, a dimension-independent, constant-radius convex basin exists around the ground truth and is efficiently reachable via robust spectral initialization even under
adversarial contamination. Prior works fail to establish both guarantees simultaneously, thereby either breaking down under
adversarial contamination or failing to handle generic non-monotonic link functions. Together, these structural insights yield a principled warm start for robust gradient descent that provably converges to a final estimation error of $O(\sigma\sqrt{\epsilon})$ in $\tilde{O}(nd)$ time with $\tilde{O}(d)$ samples, where $\epsilon$ is the contamination fraction.
Read the full abstract ▾
Machine Learning
On-Policy Replay for Continual Supervised Fine-Tuning
Yan Chen, Taojie Zhu, Meng Zhang et al. (+4 more)
Continual supervised fine-tuning (SFT) is the de facto recipe for adapting large
language models (LLMs) to a stream of downstream tasks, but it suffers from catastrophic forgetting of earlier capabilities. Recent work shows that on-policy signals – training on the model's own outputs – reduce forgetting more reliably than off-policy supervision. Existing on-policy methods route this signal through a new training objective (e.g., self-
distillation losses with a teacher copy), inheriting an extra forward pass, schedule sensitivity, and stylistic drift from the teacher.We instead route the on-policy signal through the training data source. Our method, On-Policy Replay (OPR), rolls out the most recent checkpoint on a small budget of historical
prompts, filters the generations by a task reward, and replays the surviving (
prompt, model response) pairs as ordinary SFT examples. There is no teacher, no auxiliary loss, and no on-the-fly
distillation. Across three 7–8B instruction-tuned backbones (Qwen2.5-7B-Instruct, Qwen3-8B, Llama3.1-8B-Instruct) on the TRACE continual-learning
benchmark, OPR consistently reduces forgetting; on the sharpest stress test (Qwen2.5-7B-Instruct, Sequential SFT BWT -13.93), OPR lifts BWT to -0.65 at a 10% replay budget and to -2.29 at a 1% budget – a 46% reduction in |BWT| over a tuned Vanilla Replay baseline, with 42–46% reductions observed across all three backbones. We give a KL-shrinkage interpretation that places OPR and prior on-policy
distillation methods on a single axis, and we present a counterintuitive finding that explains why Vanilla Replay is already a strong baseline: low-score replay is uniformly worse than Vanilla Replay, demonstrating that the active ingredient in OPR is the on-policy distribution, not the response quality alone.Our code is available at https://github.com/Yancey2024/OnPolicyReplay.
Read the full abstract ▾
All authors Yan Chen, Taojie Zhu, Meng Zhang, Xin Chen, Jiaqi Huang, Dongyang Xu, Yizhi Wang
Machine Learning
Gradient Perturbation: Learning to Perturb Gradients for Adaptive Training
Hua Li
Deep neural network training involves both forward propagation (from features through logits to loss) and backward propagation (from loss through gradients to parameter updates). While perturbations along the forward chain, including feature perturbation, logit perturbation, and label perturbation, have been extensively studied, the backward chain's gradient perturbation has received little systematic investigation. In this paper, we establish a unified framework for gradient perturbation, revealing that existing methods such as Sharpness-Aware Minimization (SAM), gradient clipping, and gradient noise injection can all be interpreted as imposing specific forms of gradient perturbation. Analogous to the recently proposed Logit Perturbation Learning (LPL), we
conjecture that amplifying the gradient norm for a class acts as positive augmentation (enhancing learning), while dampening it acts as negative augmentation (suppressing overfitting). Based on these observations, we propose Learning to Perturb Gradients (LPG), which adaptively perturbs logit-level gradients at the class level to achieve category-aware training. We also establish theoretical connections between gradient perturbation bounds and generalization guarantees via PAC-
Bayesian analysis. Experiments on balanced classification, long-tail classification, and noisy label learning demonstrate that LPG consistently outperforms existing methods and can be combined with them as a plug-in module.
Read the full abstract ▾
Machine Learning
Access Sets Matter: Budgeting Expert Reads for Scalable Weight-Space Model Merging
Yuanyi Wang, Yanggan Gu, Su Lu et al. (+5 more)
Weight-space model merging is usually formulated as an algebraic operation on checkpoints, yet at LLM scale the limiting resource is often the set of expert weights that must be read. We introduce MergePipe, a budget-aware execution layer that casts LLM merging as an expert access-set problem: given a merge operator and a checkpoint family in a shared weight coordinate system, choose which expert delta blocks to access under an explicit I/O budget. MergePipe indexes parameter blocks, builds deterministic access plans, and executes the induced budgeted merge with replayable manifests. The plan is budget-sound by construction and recovers the full-read merge at full budget; for fixed-coefficient additive operators, the omitted-update error is bounded by the norm of omitted deltas. Across Qwen and Llama merging workloads, MergePipe reduces expert-read I/O by up to an order of magnitude and achieves up to $11\times$ speedups. Representative budget sweeps show $O(10^{-3})$ parameter deviation from full-read merges and no monotonic degradation on downstream
benchmarks.
Read the full abstract ▾
All authors Yuanyi Wang, Yanggan Gu, Su Lu, Yifan Yang, Zhaoyi Yan, Congkai Xie, Jianmin Wu, Hongxia Yang
Machine Learning · Cross-listed from cs.CL
PhoneWorld: From Real-App Trajectories to Dynamic and Verifiable Environments for Phone-Use Agents
Yuxuan Liu, Xin Lai, Junyi Li et al. (+21 more)
Real applications provide the training setting closest to phone-
agent deployment, but are difficult to reset, scale safely, and verify programmatically. Static screenshots and interaction trajectories preserve realistic evidence but cannot generate new experience. We introduce PhoneWorld, a trace-grounded framework that converts such evidence into runnable, resettable, and verifiable Android environments. PhoneWorld induces a usage-weighted interaction skeleton from observed pages, transitions, and state-changing operations; translates it into a behavior-grounded app specification; realizes the specification through an autonomous build–inspect–repair loop; and synthesizes executable tasks with programmatic verifiers. The resulting suite spans 34 consumer-facing apps across 16 domains and supports an audited online
benchmark, verified trajectory generation, and online RL through common reset and verification interfaces. Evaluations with diverse general and open-source GUI
agents show that PhoneWorld supports reliable end-to-end online interaction and exposes capabilities complementary to AndroidWorld. Controlled SFT experiments further show that PhoneWorld trajectories complement AndroidWorld supervision, transfer across online and offline
benchmarks, and become more effective as data volume and app coverage increase. Under a matched RL budget, combining PhoneWorld mock-app rollouts with real-app rollouts improves performance over real-app RL alone on both real-phone tasks and AndroidWorld. Together, these results demonstrate that trace-grounded executable abstraction can bridge realistic mobile behavior and scalable
agent learning, turning limited real-app evidence into a growing supply of controllable and verifiable environments for training and evaluation.
Read the full abstract ▾
All authors Yuxuan Liu, Xin Lai, Junyi Li, Pengyuan Lyu, Jason, Yiduo Guo, Zhengyao Fang, Yang Ding, Yi Zhang, Weinong Wang, Huawen Shen, Xingran Zhou, Liang Wu, Fei Tang, Sunqi Fan, Shangpin Peng, Zheng Ruan, Anran Zhang, Chengquan Zhang, Han Hu, Benyou Wang, Ji-Rong Wen, Rui Yan, Zhengyang Tang
Machine Learning
Composing Non-Conjugate Factor Graphs with Closed-Form Variational Inference
Mykola Lukashchuk, Kyrylo Yemets, Wouter M. Kouw et al. (+4 more)
Stacking probabilistic building blocks into deeper architectures typically breaks closed-form inference. We show that closed-form inference can be preserved. We identify five factor-graph primitives: a bilinear factor, an exponential link, a Gamma prior, a Gaussian likelihood, and an equality node, and prove that any model composed from them admits closed-form variational message passing. The construction works because each primitive preserves a small set of message families: under mean-field factorization, messages on Gaussian variables remain Gaussian and messages on precision variables remain Gamma, while the only non-conjugate interface, the exponential link, remains tractable through the Gaussian moment-generating function and the sufficient statistics of the Gamma family. We demonstrate composition at increasing depth, from static ensembles through input-dependent gating to split-branch routing, and show that stacking routing layers encodes arbitrary decision trees, establishing universal function approximation with closed-form inference. Applied to ensemble time-series
forecasting, the framework yields a
Bayesian mixture of experts in which gating functions are inferred rather than learned, providing calibrated uncertainty over expert selection across five
benchmark datasets.
Read the full abstract ▾
All authors Mykola Lukashchuk, Kyrylo Yemets, Wouter M. Kouw, Dmitry Bagaev, İsmail Şenöz, Jeff Beck, Bert de Vries
Machine Learning · Cross-listed from stat.ML
Deep Optimal Individualized Treatment Rules for Bivariate Survival Outcomes via Adaptive Prediction-Powered Learning
Kun Ren, Yifan Cui and Wen Su
In randomized trials involving multiple treatments, bivariate survival outcomes present significant analytical challenges for making decisions. This paper addresses the problem of deriving optimal individualized treatment rules to maximize the joint survival probability beyond fixed time points $(t_1, t_2)$ through deep neural networks, while accounting for right censoring. We propose a novel approach that models treatment rules via
stochastic policies, coupling marginal accelerated failure time models via link function to capture bivariate dependence. To enhance robustness and effectiveness of decision making, we introduce an adaptive prediction-powered method that leverages auxiliary predictions from machine learning models.
Read the full abstract ▾
Machine Learning
Honest Lying: Understanding Memory Confabulation in Reflexive Agents
Prakhar Dixit, Sadia Kamal and Tim Oates
Reflexion-style
agents rely on self-generated reflections as
memory, implicitly assuming that
agents can accurately diagnose their own failures. We show that this assumption can fail systematically: across ALFWorld and HumanEval,
agents store confident but incorrect interpretations of the task and continue acting on them across trials, even though the environment resets to the correct task each time. We call this failure mode
memory confabulation and introduce the Reflection Repetition Rate (RRR), a log-based metric that detects repeated reliance on incorrect reflective content. Using RRR, we identify 16 frozen environments in ALFWorld, where 0 of 121 reflections mention the correct target object, and 4 analogous cases in HumanEval. Our mitigation replaces open-ended self-diagnosis with programmatic extraction of trajectory-level failure signals, increasing correct object mention from 0% to 86%, reducing RRR from 0.64 to 0.10, and solving 3 of 16 frozen ALFWorld environments, suggesting that reflective
memory can reinforce false beliefs rather than correct them.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Kronecker Embeddings: Byte-Level Structured Token Representations for Parameter-Efficient Language Models
Rohan Shravan
Large
language models route every input through a learned
embedding table of shape |V| x d_model, consuming hundreds of millions to billions of trainable parameters at frontier scale. We introduce Kronecker
Embeddings, a deterministic byte-level character-position factorization that replaces this table with a fixed encoder and a single learned projection, compatible with standard BPE tokenizers, eliminating 91–94% of input-side trainable parameters at frontier scale. We provide five contributions. First, a cross-model probe across six LMs (135M-671B parameters) shows trained input
embeddings cluster typographic variants of the probe word far more than morphological relatives; Kronecker escapes this clustering at the
embedding layer. Second, a controlled three-seed comparison on nanoGPT GPT-2 124M over 2.5B
tokens of FineWeb-Edu shows Kronecker reaching 2.5 +- 0.2% lower validation loss than the BPE-tied baseline (gap 0.083 +- 0.007 nats, ~9% lower perplexity), needing ~1.43x fewer steps to reach BPE's converged loss. Third, a spelling-robustness probe over 110 clean/typo pairs shows Kronecker preserves the top-1 prediction on 55.5% of pairs vs. 47.3% for BPE (+8.2 pp) and lowers KL by 7.6%, winning or tying in 10 of 11 categories; a generation probe shows Kronecker echoes byte-novel strings and typos through generation where BPE forgets them. Fourth, BPE
embedding norm drifts during training while Kronecker projection norm stays near 1.0, consistent with a stable representational target. Fifth, an on-the-fly runtime variant reconstructs
embeddings from a 4.5 MB byte buffer rather than a 2.15 GB table at vocabulary 131,072, with 0.01–0.24% step-time overhead. Byte-level locality has a tradeoff: byte-similar but semantically distant pairs (compute/commute, nation/notion) cluster together, shifting disambiguation to early
attention layers.
Read the full abstract ▾
Machine Learning
A Full-Pipeline Framework for Evaluating Membership Inference Attacks in Machine Learning
Ding Chen, Xinwen Cheng, Xuyang Zhong et al. (+3 more)
While Membership Inference Attacks (MIAs) are the prevailing method for identifying training data, their application has expanded into
privacy auditing and machine unlearning. Nevertheless, the field lacks a systematic framework for evaluating how different contexts affect MIA efficacy. Without such a characterization, practitioners risk deploying
algorithms that perform well on
benchmarks but become statistically irrelevant when faced with the nuances of specific, real-world
datasets. To bridge this gap and provide actionable insights, we introduce a comprehensive evaluation framework that systematically characterizes
privacy risks across the entire machine learning pipeline, spanning data, architectures,
algorithms, and post-training modules. Designed to inherently capture diverse operational contexts, our framework rigorously evaluates state-of-the-art MIAs across a broad spectrum of training configurations. To account for varying misclassification costs in real-world deployments, we employ three complementary metrics: Balanced Accuracy for symmetric costs, alongside TPR at low FPR (or TNR at low FNR) for asymmetric scenarios where false alarms or missed detections are strictly penalized. Furthermore, recognizing that existing MIAs assume divergent adversary capabilities, we formalize two standardized threat models and adapt these attacks into corresponding variants to ensure an equitable
benchmark. Extensive empirical evaluations demonstrate that the efficacy of specific MIA methodologies is highly sensitive to the assumed threat models and chosen evaluation metrics. Ultimately, we distill these findings into actionable guidelines and provide a ready-to-use
auditing toolkit, empowering practitioners to conduct better
privacy assessments.
Read the full abstract ▾
All authors Ding Chen, Xinwen Cheng, Xuyang Zhong, Xinping Chen, Xiaolin Huang, Chen Liu
Machine Learning
Forget Less, Generalize More: Unifying Temporal and Structural Adaptation for Dynamic Graphs
Qian Chang, Ciprian Doru Giurcaneanu, Runsong Jia et al. (+6 more)
Representation learning on dynamic graphs requires capturing complex dependencies that evolve across both time and structure. Existing approaches typically adopt fixed temporal decay schemes or predetermined structural propagation depths, limiting their ability to generalize across graphs with diverse interaction frequencies and topological characteristics. We propose Dual-Scale Retentive Dynamics (DSRD), a unified framework that maintains a retentive representation state encoding both temporal
memory and structural context. DSRD introduces two key components: (i) a retentive state with dual-scale adaptation that jointly models temporal dynamics and structural propagation within a single recurrent formulation, and (ii) adaptive decay kernels with learnable time-sensitivity parameters that automatically balance short-term responsiveness and long-term retention based on the underlying interaction patterns. We provide theoretical analysis establishing the equivalence between event-wise parallel aggregation and efficient recurrent state updates, as well as stability and boundedness guarantees for the learned dynamics. Extensive experiments on 14 real-world
benchmarks demonstrate that DSRD consistently achieves state-of-the-art performance on both link prediction and node classification tasks, with strong generalization across transductive and inductive settings.
Read the full abstract ▾
All authors Qian Chang, Ciprian Doru Giurcaneanu, Runsong Jia, Xia Li, Guoping Hu, Xiufeng Cheng, Jinqing Yang, Mengjia Wu, Yi Zhang
Machine Learning
How Much Is a Dataset Worth? Scaling Laws, the Vendi Score, and Matrix Spectral Functions
Jeff A. Bilmes, Gantavya Bhatt and Arnav M. Das
Neural scaling laws appraise data through
dataset size, while the Vendi Score uses
quantum entropy to measure
dataset value. We show both that common neural-scaling-law objectives and the Vendi Score are submodular. We further show that the Vendi Score is a special case of a broader class of submodular objectives that we call
matrix spectral functions. This also includes determinantal (DPP) objectives, as well as many others. We also introduce weakly
matrix monotone functions and show how they lead to weakly submodular
matrix spectral functions, yielding a broad family of practical objectives for data appraisal. We develop secular-equation-based updates that avoid repeated eigendecompositions during greedy optimization, reducing marginal-gain evaluation for $m$-dimensional
embeddings by an $O(m)$ factor relative to oracle queries. This yields an average empirical speedup of about 35,000x, making direct optimization of the Vendi Score feasible on ImageNet-1K-scale
datasets. Thus enabled, we compare how well several objectives predict the value of training subsets for held-out test performance under fixed-size, class-balanced, and fixed training-budget regimes, including the Vendi Score, DPPs, facility location, and three new
matrix spectral variants. Across multiple
datasets, facility location performs the best. Direct optimization also reveals that, while the Vendi Score is predictive over moderate score ranges, pushing the objective to higher values can make it a poor downstream performance proxy. We also find that uniformly at random fixed-size subsets, both unconstrained and class-balanced, are remarkably concentrated in both appraisal scores and held-out performance. Finally, we show that size, class balance, and training budget do not alone determine data value: even when controlling for these factors, performance ranges smoothly from good to bad.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing
Yuexin Li, Wenjie Qu, Linyu Wu et al. (+5 more)
Existing sentence-level watermarking methods enhance robustness to paraphrasing by anchoring watermarks in sentence semantics. However, their prefix-based designs remain vulnerable to structural perturbations, such as sentence splitting and merging, which commonly arise under strong paraphrasers like DIPPER and GPT-3.5. To mitigate this issue, we propose AliMark, a framework that reformulates sentence-level watermarking as a bit sequence encoding and
alignment problem between a potentially watermarked text and a secret bit sequence. Notably, our approach adopts a two-stage detection strategy: we generate multiple restructured text variants and adaptively align their extracted bit sequences with the secret bit sequence to minimize
alignment cost. This multi-candidate
alignment design naturally improves robustness to sentence merges and splits. Extensive experiments demonstrate that AliMark substantially outperforms state-of-the-art baselines under diverse paraphrasing attacks.
Read the full abstract ▾
All authors Yuexin Li, Wenjie Qu, Linyu Wu, Yulin Chen, Yufei He, Tri Cao, Bryan Hooi, Jiaheng Zhang
Machine Learning · Cross-listed from cs.AI
When Does Persona Prompting Actually Help? A Retrieval and Metric Analysis of Expert Role Injection in LLMs
Shuai Xiao, Su Liu, Weikai Zhou et al. (+4 more)
Persona prompting is widely used to steer large
language models, yet its practical value remains unclear. Prior work often evaluates persona prompting using aggregate scores, making it difficult to determine whether expert-role prompting consistently improves response quality or instead changes responses along different quality dimensions. We study this question through a controlled comparison of four prompting conditions across 1,140 open-ended questions spanning 38 expert roles and six domains: no role
prompt, a generic domain-expert
prompt,
embedding-based role
retrieval, and a hybrid
retrieval method combining
embedding search with LLM-based role selection. Aggregate results show only small overall differences between conditions. However, metric-level analysis reveals a consistent tradeoff that aggregate averages obscure: role prompting systematically increases expertise depth while reducing clarity. These effects are highly conditional rather than universal. Role prompting performs best on advisory questions and in domains such as medicine and psychology, where structured expert framing and risk communication are intrinsically valuable. In contrast, baseline prompting performs better on conceptual and explanatory questions in finance, legal, science, and technology domains, where concise plain-
language explanation is more important. We further show that hybrid
retrieval significantly improves over
embedding-only role selection, although better role
retrieval does not eliminate the broader expertise-depth versus clarity tradeoff. Overall, our findings suggest that persona prompting primarily reshapes response characteristics rather than broadly improving capability, and that multi-metric evaluation is necessary for understanding its effects.
Read the full abstract ▾
All authors Shuai Xiao, Su Liu, Weikai Zhou, Jialun Wu, Xinjie He, Zhiyuan Lin, Qiyang Xie
Machine Learning · Cross-listed from eess.IV
Constructing efficient channels for ideal observers using the conjugate gradient method
Weimin Zhou
Task-based assessment of image quality (IQ) is critically important for the design and optimization of medical imaging systems. Ideal observers, including the
Bayesian Ideal Observer (IO) and the ideal linear observer, i.e., the Hotelling observer (HO), provide objective figures of merit (FOMs) that quantify system performance on signal detection tasks. However, the application of ideal observers to high-dimensional image data is often computationally intractable. Channel mechanisms provide an effective framework for dimensionality reduction that can facilitate the computation of ideal observers. This work presents a conjugate gradient (CG)-based method to construct efficient channels for approximating the IO and HO performance.
Read the full abstract ▾
Machine Learning · Cross-listed from eess.SY
Real-Time Retargeting Using Controllability Boundary for Chandrayaan-3 Lunar Landing
Suraj Kumar, Debjyoti Chakrabarti, Aditya Rallapalli et al. (+2 more)
This paper presents the real-time retargeting guidance policy developed for the Chandrayaan-3 lunar landing mission. The baseline guidance generates approximate fuel-optimal descent trajectories, while a high-level policy enables safe retargeting to alternate sites when the nominal site becomes infeasible. The retargeting strategy leverages a convex representation of the controllability boundary, allowing rapid feasibility checks and real-time target updates. To the best of the authors knowledge, this represents the first application of a data-driven retargeting framework in an operational lunar landing mission. Pre-flight simulations and Chandrayaan-3 flight results validate the effectiveness of the proposed approach.
Read the full abstract ▾
All authors Suraj Kumar, Debjyoti Chakrabarti, Aditya Rallapalli, Bharat Kumar GVP, Ashok Kumar Kakula
Machine Learning
The Good, the Bad, and the Ugly of Markov Boundary for Tabular Prediction
Shu Wan, Abhinav Gorantla, Huan Liu et al. (+1 more)
Under standard graphical assumptions, the Markov boundary of a target variable is the smallest set of features that renders every other feature redundant. Once the boundary is observed, the target is conditionally independent of the rest of the table. This is a tempting object for tabular prediction, since it names exactly the columns a model should need. Yet modern regressors are still trained on the full feature set. We ask whether the Markov boundary is genuinely useful for prediction on SCM3K, a 3,450-task synthetic SCM
benchmark with feature counts from 40 to 1000 and six SCM families, evaluated with six regressors. The answer is more nuanced than the theory suggests. Restricting a regressor to the oracle boundary often improves prediction substantially, and the improvement grows as the feature space becomes larger and sparser. But the natural pipeline of recovering the boundary with causal discovery and training on the recovered mask does not deliver. Existing
estimators exhaust the compute budget before reaching the regime where the boundary helps most, and even where they run they rarely beat the full feature set. We trace this to three causes. Discovery optimizes structural recovery rather than prediction. False negatives and false positives carry sharply asymmetric predictive cost. The exact boundary is only one of many feature sets that beat all features. We then develop what these facts imply for prediction-aligned feature selection and for tabular models that learn to use causal structure.
Read the full abstract ▾
All authors Shu Wan, Abhinav Gorantla, Huan Liu, K. Selçuk Candan
Machine Learning
Information-Directed Offline-to-Online Reinforcement Learning
Keru Chen
Decision-making from offline
datasets typically warm-starts a policy or score model from fixed offline data and then refines it with limited online interaction. Offline data reduces uncertainty, but it does not remove the need for exploration; it changes what remains to be explored. We formalise this residual uncertainty by the conditional mutual information $I(\chi;\tau_{1:T}\mid\mathcal{D}_N)$ between a learning target $\chi$ and the online trajectories after conditioning on the offline
dataset. This view leads naturally to information-directed sampling (IDS), a family parameterised by $\eta\ge 0$ that selects actions by trading off instantaneous regret against information gain. We prove a generic offline-to-online
Bayesian regret bound for IDS through a ratio certificate: any information-ratio bound satisfied by a reference Thompson-sampling policy over the same randomised policy class is inherited by IDS. In a known-dynamics
Bayesian linear-reward model, the conditional mutual information has a log-determinant form, and vanilla IDS ($\eta=0$) satisfies $\widetilde O\!\left(Hd\min\left\{\sqrt T,\,T\sqrt{C^\dagger_{\beta,\mathrm{IDS}_0}(N,T)/N}\right\}\right),$ where the coverage coefficient is tied to the visitation distribution induced by vanilla IDS itself. We also identify a warm-start regime with a dominated but informative probe in which vanilla IDS selects the probe while Thompson sampling never does, giving a constant-factor
Bayesian regret separation. Controlled bandit experiments and D4RL offline-to-online RL experiments validate this mechanism: IDS is most beneficial when offline data is informative but leaves biased or low-probability residual uncertainty that targeted online actions can resolve, a regime shared by offline RL, offline black-box optimization, and
Bayesian optimization.
Read the full abstract ▾
Machine Learning
Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting
Haoxin Liu, Yichen Zhou, Rajat Sen et al. (+2 more)
Time-Series Foundation Models (TSFMs) excel at zero-shot unimodal
forecasting using numerical data, but unlike LLMs they cannot consume
multimodal, non-numerical context that often shape real-world trajectories. In this work, we bridge this gap and argue for a
multimodal time-series
forecasting approach that post-trains LLMs to act as context-guided revisors over strong numerical TSFM priors. We introduce PostTime, a post-training recipe combining Supervised Fine-Tuning (SFT) and Reinforcement Learning with Verifiable Rewards (RLVR), along with a methodology to generate automated
reasoning traces for forecast revisions. PostTime teaches an LLM to generate context-conditioned forecast interventions – decisions to revise, preserve, or ignore the TSFM prior based on the
multimodal context. We evaluate this approach on the TimesX
multimodal forecasting benchmark using a Gemma-3-4B LLM and TimesFM-2.5 TSFM, and show that it significantly outperforms standalone TSFMs, LLM-only baselines, and existing
multimodal forecasting approaches.
Read the full abstract ▾
All authors Haoxin Liu, Yichen Zhou, Rajat Sen, B. Aditya Prakash, Abhimanyu Das
Machine Learning
GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models
Xiaohang Tang, Keyue Jiang, Che Liu et al. (+4 more)
Reinforcement learning (RL) can be used to improve the policy (denoiser) of
diffusion large
language models (dLLMs), while being hindered by the intractability of the policy likelihood. A dominant and efficient family of methods replaces the likelihood in standard RL with its evidence lower bound (ELBO), estimated from randomly masked sequences. Despite being well aligned with pre-training, these approaches introduce bias through training–inference mismatch by using the ELBO as a likelihood surrogate, which can degrade performance. In this work, we propose Guided Denoiser Self-
Distillation (GDSD) to directly distill the denoiser of dLLMs from an advantage-guided self-teacher, derived from the closed-form optimum of reverse-KL regularized RL. GDSD matches the dLLM's denoiser logits to the teacher's via a normalization-free objective, which reduces RL to likelihood-free self-
distillation and thus bypasses the TIM biases. Recent ELBO-based methods emerge as instances of applying different
distillation divergences, but with diagnosable pathologies that GDSD avoids. On planning, math, and coding
benchmarks with LLaDA-8B and Dream-7B, GDSD consistently outperforms prior state-of-the-art ELBO-based methods with a more stable training reward dynamics, achieving test-accuracy improvements of up to $+19.6\%$. These results suggest that direct denoiser self-
distillation, without relying on an ELBO likelihood surrogate, can provide a more stable and effective RL procedure for dLLMs. Code is available at https://github.com/GaryBall/GDSD.
Read the full abstract ▾
All authors Xiaohang Tang, Keyue Jiang, Che Liu, Qifang Zhao, Xiaoxiao Xu, Sangwoong Yoon, Ilija Bogunovic
Machine Learning
On the Optimizer Dependence of Neural Scaling Laws
Vansh Ramani and Shourya Vir Jain
The scaling exponent $\alpha$ in neural scaling laws $L(N) \propto N^{-\alpha}$ is commonly treated as a fixed constant set by architecture and data. We present evidence that $\alpha$ depends systematically on the optimizer. In controlled random-feature regression experiments – the canonical theoretical framework for neural scaling – we measure $\alpha$ across five optimizer variants and six spectral conditions. Preconditioned optimizers consistently yield steeper scaling (larger $\alpha$), with the $\alpha$-shift increasing across most of the tested spectral range, peaking near $s = 1.5$, and remaining large at $s = 2.0$. At $s \approx 1.0$ (characteristic of natural
language), the full natural gradient achieves $\alpha \approx 0.31$ versus $\alpha \approx 0.12$ for gradient descent – a $2.6\times$ larger fitted exponent that, within the random-feature model, compounds with each model-size doubling. Whether and how this exponent shift transfers to large-scale LLM training – where recent evidence suggests the advantage may attenuate with scale – remains an important open question. Our results imply that scaling-law forecasts should account for optimizer choice, and we provide a spectral diagnostic predicting when advanced optimizers will pay off.
Read the full abstract ▾
Machine Learning
TRACER: Persistent Regularization for Robust Multimodal Finetuning
Hesam Asadollahzadeh, Feng Liu, Christopher Leckie et al. (+1 more)
Mainstream strategies for finetuning pretrained
multimodal models often degrade out-of-distribution (OOD) robustness, a phenomenon known as catastrophic forgetting. In this paper, we develop a theoretical framework for
multimodal contrastive finetuning, yielding closed-form solutions and a
geometric decomposition for each strategy. This framework shows that self-
distillation is more effective than other regularization approaches to retain the knowledge of the pretrained model. Our analysis reveals a largely overlooked limitation: standard Exponential Moving Average (EMA) teachers, widely used in robust finetuning, suffer from collapse. To solve this, we prove that a Weighted Moving Average (WMA) teacher maintains a persistent regularizing force over finite horizons and yields bias-free convergence in the task subspace while preserving orthogonal knowledge. These insights motivate **TRACER** (**T**rajectory-**R**obust **A**nchoring for **C**ontrastive **E**ncoder **R**egularization), which combines contrastive learning with WMA-guided multi-perspective
distillation. Extensive experiments on CLIP finetuning demonstrate consistent OOD accuracy and calibration gains across three backbone architectures, and comprehensive ablations confirm that TRACER is both principled and robust to hyperparameter choices. Code is available at [https://github.com/HesamAsad/TRACER](https://github.com/HesamAsad/TRACER).
Read the full abstract ▾
All authors Hesam Asadollahzadeh, Feng Liu, Christopher Leckie, Sarah M. Erfani
Machine Learning · Cross-listed from cs.CL
BrahmicTokenizer-131K: An Indic-Capable Drop-In Replacement for o200k_base
Rohan Shravan
We present BrahmicTokenizer-131K, a 131,072-vocabulary byte-level BPE tokenizer that closes the Brahmic compression gap at the 131K-vocabulary class while preserving the English, EU-
language, and code compression of OpenAI's o200k_base. We construct it through a two-stage retrofit: (1) a script-prune crop that reduces 200,019
tokens to 131,072 by removing nine out-of-scope writing systems, and (2) a
surgical retrofit of 2,372 corpus-dead vocabulary slots determined by linear-programming allocation across nine Brahmic Unicode blocks. The pre-tokenizer, decoder, and inherited merge rules are unchanged from o200k_base, making BrahmicTokenizer-131K a drop-in replacement at the tokenizer interface. On 27 million documents of public Indic pretraining text (2.84 billion words, 46.21 GB), BrahmicTokenizer-131K produces 26.7% fewer
tokens than Mistral-Nemo Tekken / Sarvam-m at the same vocabulary budget, with per-
language savings of 15.79% (Tamil) to 76.79% (Odia, a 4.31x compression ratio). The Odia advantage is mechanistically explained by Tekken/Sarvam-m containing zero Oriya-block
tokens; our surgery added 725. On non-Indic content, BrahmicTokenizer-131K matches o200k_base's English fertility (1.235 vs 1.232
tokens/word) and beats Tekken/Sarvam-m by 4.0-14.2% on HumanEval, MBPP, and GSM8K. Across our 14-tokenizer
benchmark, it is the only tokenizer simultaneously competitive on Brahmic, English, EU, code, and math at the 131K budget. Specialist tokenizers at other vocab classes (Sarvam-30B, Sarvam-1, MUTANT-Indic) achieve better Indic compression at the cost of non-Indic performance: Sarvam-1's English fertility is 15.9% worse and its code/math compression 26-33% worse than ours. We release the artifact under Apache 2.0 at https://huggingface.co/theschoolofai/BrahmicTokenizer-131K.
Read the full abstract ▾