Computer Vision
PWLR: Pairwise Witness Local Rejection for Boundary-Aware Out-of-Distribution Detection
Chengyao Jia and Ruixuan Wang
Out-of-distribution (OOD) detection remains challenging for image classifiers, especially when near-OOD samples lie close to in-distribution (ID) class boundaries. Recent
vision-
language detectors improve OOD detection through class semantics, local prompting, or LLM-generated outlier concepts, but seldom use
language as explicit boundary evidence between confusing ID classes. We propose Pairwise Witness Local Rejection (PWLR), which uses an MLLM offline to describe visible local cues that favor one ID class over a specific rival class. These cue phrases are then screened with ID-only data under a frozen
vision-
language backbone, so that only reliable local verifiers are kept. At inference, PWLR first retains a small set of globally plausible classes, then checks whether any of them is locally supported against its most relevant rivals, and finally combines this pairwise local evidence with the global class score through calibration. Experiments on ImageNet-100 far-OOD, cleaner/challenging OOD and near-OOD
benchmarks show that PWLR consistently improves strong
vision-
language baselines across multiple backbones. Source code will be released.
Read the full abstract ▾
Computation and Language
Using the Mimi codec for metalinguistic representations
Artem Saloev, Erin Pacquetet and Nicolas Ballier
In this paper, we focus on the dictionary of 2048
tokens used in Mimi semantic
token codebook, the neural codec of the Moshi
language model. We show that the ABX experiment carried out with Mimi fails to capture the mapping of the semantic
tokens to phone realisations. By realigning Mimi representations to the TIMIT corpus transcriptions, we show that the 2048
tokens IDs of the semantic codebook map to quadphone, triphone, biphone, phone and subphone realisations.
Read the full abstract ▾
Machine Learning
The Hardness of Estimating Cross-Entropy Risk for Language Models
Hanti Lin
Language models, once pretrained, are routinely assessed by the holdout method, which estimates their per-
token cross-
entropy risk—a quantity that may be finite or infinite. We prove possibility and impossibility
theorems that characterize the hardness of this estimation problem. The estimand depends on two objects: the unknown data distribution $p$ and the distribution $q$ induced by the
language model under study. Our ignorance of $p$ is empirical, whereas our ignorance of $q$, or at least of its tail, is mathematical; so the parameter space should range over pairs $(p,q)$—a product space—to fully capture our ignorance. Negative results: no
estimator is pointwise consistent, even when the parameter space is restricted to full-support models and to data distributions whose expected text length is below a fixed bound; worse, every
estimator fails on a dense set of pairs. Positive results: the holdout
estimator becomes pointwise consistent when the models are further restricted to
Transformers or, architecture-neutrally, to full-support models with a finite context window; and, where no such design is in place, it still consistently estimates the risk capped at any fixed threshold, which suffices for screening candidate models in practice. Lesson: designs such as the
Transformer architecture and finite context windows, although adopted for computational or engineering reasons, pay a statistical dividend: they suffice to make pointwise consistency possible—a dividend visible only in how they turn a negative result into positive ones.
Read the full abstract ▾
Artificial Intelligence
KV-Rescue: Recovering Reasoning Language Model KV Eviction Loss via Stepwise Interleaving
Minsoo Cheong, Woosang Lim, Vincent-Daniel Yun et al. (+1 more)
KV-cache eviction caps the
memory cost of long
reasoning traces but is inherently lossy because the model decodes from a partial view of its history. Under aggressive budgets, this not only lowers accuracy but can also cause runaway degeneration, where the model produces incoherent or repetitive
tokens until reaching the length limit. We characterize much of this loss as an information gapf caused by missing context, rather than a capability gap caused by limited model capacity. An evicted 7B model and a full-context 1.5B model make complementary errors, and an oracle choice between their answers recovers 79% of the accuracy gap to the full-KV 7B model. Based on this observation, we propose KV-Rescue, a training-free inference framework that bridges the information gap introduced by KV eviction using a lightweight full-context helper. KV-Rescue interleaves
reasoning steps from the two models into a shared trajectory. An online detector uses
entropy and compressibility to terminate the generation of incoherent or repetitive base-model candidates early. Across five math
benchmarks with Qwen2.5-Math 7B and 72B, KV-Rescue recovers an average of 87% of the accuracy lost to eviction at eviction budget B=64. A decode-cost analysis further shows that preventing runaway degeneration cuts base-model
token generation by 43% on average.
Read the full abstract ▾
All authors Minsoo Cheong, Woosang Lim, Vincent-Daniel Yun, Sungjoo Yoo
Computer Vision
Emergent 3D Instance Segmentation from Self-Supervised Point Transformers
Ted Lentsch, Santiago Montiel-Marín, Holger Caesar et al. (+1 more)
Unsupervised 3D instance
segmentation of outdoor
LiDAR scans has traditionally relied on handcrafted
geometric priors such as density-based clustering, motion cues, or projected 2D detections. In this work, we investigate whether a frozen, self-supervised point
transformer already contains the structural information required to isolate object instances without any handcrafted
geometric prior. Using this
transformer purely as a feature extractor, we probe its internal representations across the SemanticKITTI, nuScenes, and Waymo Perception
datasets. Our analysis yields four core insights: (1) the instance signal concentrates in the
attention queries and keys rather than in the values or final output features; (2) output features semantically collapse, merging adjacent same-class objects that the queries and keys keep distinct; (3) this instance signal is bimodal in depth, strongest at the shallowest and deepest encoder stages; and (4) this signal is driven predominantly by the rotary position encoding (RoPE), whose removal collapses its advantage. We put these findings into our method TokenGraph3D, a training-free segmenter that groups points via connected components on a key-similarity graph, using neither density-based clustering nor proximity priors. Under identical prior-free conditions, we substantially outperform output-feature baselines, making the emergent 3D instance structure visible.
Read the full abstract ▾
All authors Ted Lentsch, Santiago Montiel-Marín, Holger Caesar, Julian F. P. Kooij
Machine Learning
CrevasseSeg: A Label-Efficient UAV Crevasse Segmentation Framework
Steven Wallace, William D. Harcourt, Richard Hann et al. (+3 more)
Crevasse mapping from uncrewed aerial vehicle (
UAV) imagery matters for glaciological research and for field safety in glaciated terrain. Yet, pixel-level annotation of glacier surfaces is costly and requires domain experts. We introduce CrevasseSeg, a framework for binary
segmentation over the terminus of Borebreen, Svalbard, comprising 1,938 unlabelled
UAV orthomosaic tiles for self-supervised/unsupervised fine-tuning, 24 labelled tiles for validation and 176 labelled tiles for testing. Using CrevasseSeg, we
benchmark five self-supervised objectives – BYOL, a Jensen-Shannon Divergence (JSD) objective, Barlow-Twins, VICReg, and a combined BYOL-JSD objective – across three architectures: O-Net, O-Net++, and a DINOv3-initialised O-Net. Each configuration is evaluated under two frozen-feature readouts that differ only in the form of their decision boundary: a linear probe and a non-linear XGBoost classifier fit only on the 24 labelled validation images. Our central finding is a consistent inversion between the two readouts: DINOv3 features are the weakest under linear probing but the strongest under a non-linear readout. A UMAP analysis of the learned feature space shows that DINOv3 fragments pixels into many small clusters in which the classes are locally interleaved, whereas the convolutional architectures (O-Net and O-Net++) embed them onto a single class-sorted
manifold. Satellite-pretrained DINOv3 improves over natural-image initialisation across objectives, and our label-efficient DINOv3-ViT-L-Sat-O-Net-BYOL-JSD pipeline reaches 75.33 mDSC / 61.28 mIoU, outperforming standard machine learning baselines fit on the same 24 labelled images with the RGB pixel values used as features. We release CrevasseSeg to support label-efficient
segmentation research in remote sensing.
Read the full abstract ▾
All authors Steven Wallace, William D. Harcourt, Richard Hann, Aiden Durrant, Somayajulu Sripada, Georgios Leontidis
Computer Vision
ChainSpace: A Chained-Reasoning Paradigm for Spatial Intelligence
Xiaohan Zhang, Feng Gu, Xudong Rao et al. (+4 more)
Spatial intelligence requires foundation models to maintain coherent spatial state across interactions with the physical world. However, existing data-centric approaches typically treat spatial
reasoning as independent question-answer instances, enabling shortcut-based answering and providing limited supervision for persistent spatial understanding. To address this, we introduce ChainSpace, a chained-
reasoning paradigm that structures spatial
reasoning as a state-preserving multi-round process. In this paradigm, spatial questions are organized into logically constrained and jointly consistent chains, where later questions depend on spatial constraints established in earlier rounds. Following this principle, we instantiate ChainSpace-Bench, a manually annotated real-world multi-round
benchmark with a Chain-Aware Metric, and ChainSpace-Pipeline, a simulator-based chain-structured supervision generation framework for spatial intelligence training. Experiments show that ChainSpace-Bench exposes chain-level failures that are not captured by isolated question accuracy. Additionally, with a relatively small amount of simulator-generated chained data, models trained by ChainSpace-Pipeline achieve the best performance among open-source models on ChainSpace-Bench and transfer competitively to multiple external spatial intelligence
benchmarks. These results establish ChainSpace as an effective paradigm for more faithful evaluation and more data-efficient learning of spatial intelligence.
Read the full abstract ▾
All authors Xiaohan Zhang, Feng Gu, Xudong Rao, Xuhao Pan, Tao Wei, Zhou Pan, Kun Zhan
Machine Learning
Routing Divergence Is Not Evidence of Behavioral Influence in Same-Weight MoE Self-Distillation
Cedric Caruzzo, Donggeun Yoo and Tae Soo Kim
Two Mixture-of-Experts (MoE) forward passes can share every weight yet route the same
token through different experts. This creates a possible blind spot in same-weight self-
distillation, where a demonstration-conditioned teacher supervises a query-only student. We study this mismatch in its single-step form, with frozen weights rather than as a proxy for a full training trajectory. An exact blockwise decomposition separates a routing term, which changes gates at fixed content, from a dense-like content term. Across seven open-weight checkpoints and two domains, the routing term spans only $1.6\times$ as a fraction of block output, while its residual-stream exposure spans $3.2\times$. Exposure is ordered by the routed block's share of the residual. Scaling the always-on backbone in two confirmatory models moves exposure monotonically; common-mode controls support a mass-and-coherence mechanism rather than denominator dilution alone. Preregistered PubMedQA patches on three models show that the full routing term moves outputs by less than half the natural context effect and is largely reproduced by matched-norm noise, whereas the content term is strongly direction-specific. Scale and merged-expert probes show that the narrow block-level range is not universal, although exposure remains small at the tested boundaries. Router movement alone is therefore not evidence of behavioral influence: measure exposure first, and use a behavioral intervention when the decision matters.
Read the full abstract ▾
Computer Vision
RoofGS: Roofline-Guided End-to-End Acceleration of 3D Gaussian Splatting
Yang Luo, Yan Gong, Yongsheng Gao et al. (+1 more)
3D Gaussian Splatting (3DGS) enables real-time novel-view synthesis but remains limited on GPUs at high resolutions. Through a stage-wise Roofline characterization, we identify two distinct hardware bottlenecks: global
memory traffic dominates the front end, whereas instruction throughput limits rasterization. Guided by this analysis, we develop RoofGS, a rendering framework that applies bottleneck-specific optimizations rather than generic kernel acceleration. For the
memory-bound front end, we design a resolution-adaptive quantized depth sorting key that compresses each key to 32 bits. For the compute-bound rasterizer, we introduce a range-aware bit-level fast exponential approximation tailored to the bounded exponent range after opacity culling, with a derived per-pixel error bound. These two core techniques are complemented by additional optimizations (kernel fusion, compact attribute storage, culling, dual-pixel evaluation) that additionally reduce
memory traffic and improve instruction-level parallelism. Experiments show that RoofGS achieves a 10.1$\times$ end-to-end speedup over 3DGS at 4K on an RTX 4090, increasing throughput from 61 to 616 FPS, with only a 0.028 dB PSNR loss.
Read the full abstract ▾
All authors Yang Luo, Yan Gong, Yongsheng Gao, Jie Zhao
Robotics
Reliable Piezoresistive Strain Sensing Through Physical Limits and Uncertainty Monitoring
Carmen Ballester, Víctor Muñoz, Dorin Copaci et al. (+1 more)
Soft piezoresistive strain sensors are one of the most common sensing solutions for wearable and soft robotic applications due to their flexibility and compliance. However, their resistance response is nonlinear and hysteretic, and a sensor can be pushed past its calibrated workspace or misbehave inside it, carrying that error into a decision or control loop. Probabilistic regressors track confidence but ignore those limits. A predictive mean can look unremarkable even when the reading comes from a sensor outside its admissible range or already failing internally, so a confident-looking estimate is not the same as a trustworthy one. This paper proposes a reliability framework pairing a physics-informed probabilistic inverse model, built on physics-guided input features, with a risk factor fusing uncertainty with strain and strain-rate limits into a three-state monitor. Tests on a Nitinol wire and a silver-coated polyamide thread with a Gaussian Process raised fit scores to 0.90-0.95 (RMSE 0.26%-0.15%) and a 96% empirical coverage against the 95% target. The monitor caught 95% of out-of-range and 100% of abnormal conditions while staying reliable under nominal operation. A sensor that reports confidence alongside its estimate lets a system withhold action instead, since it needs no labeled failure examples, which are hard to collect for soft materials.
Read the full abstract ▾
All authors Carmen Ballester, Víctor Muñoz, Dorin Copaci, Dolores Blanco
Machine Learning · Cross-listed from stat.ML
Inferential Evaluation of Surrogate-Derived Models under Covariate Shift
Longtian Shi, Molei Liu and Doudou Zhou
In transfer-learning settings, a model derived from abundant surrogate labels may be deployed in a target population where gold-standard outcomes are unobserved. Evaluating its target performance is essential for determining whether decisions based on the model remain reliable, yet it is difficult when gold labels are scarce, and
covariate distributions differ across data sources. We study a three-sample setting with a small gold-labeled source, a larger surrogate-labeled source, and an unlabeled target. Under conditional transportability, we evaluate the surrogate-derived model against the latent gold-standard outcome in the target population. We propose cross-fitted
estimators that transport information from the two labeled sources through source-specific density ratios. We also combine outcome-regression augmentation with a kernel correction for estimating the model near a threshold, accounting for uncertainty from all three samples. We establish asymptotically linear inference for TPR and FPR, consistency and pointwise inference for the ROC curve, and asymptotically normal inference for AUC. Simulations assess bias, coverage, and sensitivity to bandwidth and relative sample sizes. A retrospective temporal validation on Chatbot Arena and a semi-synthetic ACS-Income study provide validation in real-world AI applications.
Read the full abstract ▾
Information Retrieval
Decomposing Staleness in Recommender Systems: A Dual-Filter Framework for Supersession and Decay
Di Bai, Feng Han, Zhenwei Tang et al. (+3 more)
Stale recommendations are a pervasive challenge and a leading source of user complaints on large-scale content platforms. Items lose relevance through two primary mechanisms: supersession, where emerging updates render prior coverage stale, and relevance decay, where an item's informational value naturally diminishes over its lifecycle. Traditional countermeasures serve as crude proxies: age cutoffs poorly reflect actual relevance loss, while engagement heuristics rely on lagging signals, broadly exposing users to stale content before the system adapts. We present SDF (Supersession-Decay Filtering), a staleness filtering system fully deployed in Google Discover, a personalized recommendation feed with hundreds of millions of daily and billions of monthly active users. SDF targets both mechanisms with complementary filters, each powered by a learned model: a relational staleness model that detects supersession between item pairs, and a predicted traffic ratio (PTR) model that forecasts relevance decay from the item's content, trained on lifetime visit traffic. Applied via disjunction upstream of the ranking stage, SDF prunes stale candidates, measurably reducing downstream serving costs. Online experiments demonstrate that these filters significantly reduce the prevalence of stale content while improving user engagement. Over a two-year production deployment, user-filed staleness reports (in-product user feedback) declined by 54.9% relative to the pre-deployment baseline, establishing SDF as a robust and scalable paradigm for resolving content staleness at industrial scale.
Read the full abstract ▾
All authors Di Bai, Feng Han, Zhenwei Tang, Jintao Liu, Luoshu Wang, Jialu Liu
Computational Geometry
On graphically local versions of metric embeddings
Vishesh Jain and Duan Tu
We consider the problem of graphically local metric
embedding, i.e.
embedding points from an arbitrary finite metric space into a target metric space while preserving, up to a small distortion, only a subset of the pairwise distances specified by a bounded degree graph $G$. We provide a general reduction showing that, in many cases, this is no easier than
embedding the points while approximately preserving all pairwise distances. As an illustration of our general reduction, we show that there exists a Euclidean metric space $X$ on $n$ points along with a graph $G = (X,E)$ of maximum degree $3$ such that any
embedding of $X$ into $\ell_2^m$ which only preserves distances specified by $E$ up to a relative error of $(1+\varepsilon)$ must satisfy $m = \Omega(\varepsilon^{-2}\log n)$. Our lower bound matches the upper bound on the dimension coming from the Johnson-Lindenstrauss lemma for approximately preserving all pairwise distances; previously, such a lower bound was known only for the class of noncontracting
embeddings [Schechtman-Shraibman, Discrete & Computational Geometry, 2009]. Moreover, the condition that the maximum degree of the graph is $3$ is best possible: for graphs $G$ of maximum degree $2$ (or more generally, treewidth at most $2$), any metric space embeds $G$-isometrically into any two-dimensional normed space.
Read the full abstract ▾
Cryptography and Security
Fast Simulation Algorithms for OLH using Binomial Modeling
Berkay Kemal Balioglu, Alireza Khodaie and M. Emre Gursoy
Optimized Local Hashing (OLH) is a widely used hash-based Local Differential
Privacy (LDP) protocol, and simulation-based experimentation is the standard approach for evaluating OLH and OLH-based applications in research. However, the existing OLH simulations have $O(nd)$ computational complexity, where $n$ is the user population size and $d$ is the domain size, and can lead to significant execution times as $n$ and $d$ grow. In this paper, we propose two fast simulation
algorithms for OLH (2-Binom and 3-Binom) grounded in Binomial modeling. Our key insight is that, for any domain value $v$, the total number of users whose perturbed reports support $v$ can be decomposed into a sum of two or three Binomial random variables. Using this insight, our
algorithms reduce the simulation complexity to $O(n + d)$ without hurting statistical equivalence. In particular, we theoretically prove that both
algorithms yield unbiased frequency estimations with variances identical to those of the original OLH simulations. Experiments on real-world
datasets confirm that both approaches reduce execution times from several minutes to milliseconds, yielding significant speedups with no change in utility.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cond-mat.mtrl-sci
ALKEMIE Agent: an autonomous platform for computational materials design
Hongfu Huang, Yuzhe Li, Ao Xu et al. (+14 more)
Despite the powerful multi-scale modeling methods and high-throughput infrastructures established in the materials community, real material computation workflows remain fragmented and heavily manual, requiring researchers to constantly bridge software tools, data analysis, and intermediate decisions. This growing gap between methodological capability and practical execution highlights the need for a new kind of autonomous computational framework, one that can coordinate tools, knowledge, and workflows in a more unified and adaptive way. Here, we introduce ALKEMIE
Agent, an agentic platform in which
retrieval-augmented generation, a materials-computation knowledge base, registered skills, database-supported provenance, AI-assisted structure modeling, bounded task execution, tool-calling iteration, and error-diagnostic assistance are integrated within a traceable control loop. The capabilities of ALKEMIE
Agent are demonstrated through applications including materials recommendation, structure modeling,
phonon calculations, machine-learned interatomic potential training, LAMMPS simulations, Ab Initio Monte Carlo (AIMC) sampling, and active-learning-based materials screening. Finally, we outline the future directions and challenges for the development of agentic platforms for computational materials design.
Read the full abstract ▾
All authors Hongfu Huang, Yuzhe Li, Ao Xu, Bo Liu, Changrui Wang, Kan Tang, Ning Yang, Shengxian Liu, Hanyu Liu, Pengpeng Zhang, Linggang Zhu, Fengkai Liu, Yichen Lu, Tong Zhao, Naihua Miao, Jian Zhou, Zhimei Sun
Artificial Intelligence
Broken Symmetry in LLM Refusal: Answer Release Is More Local Than Refusal Restoration
Yiqi Liu, Yang Wang, Songxin Wang et al. (+2 more)
When a
language model refuses to answer a
prompt, it is unclear whether the correct answer is erased from its internal representations, or merely suppressed at the output layer. We investigate this mechanism using a controlled withhold setting, which yields perfectly matched answering and refusal trajectories for bidirectional activation patching. We uncover a causal asymmetry in intervention locality under matched causal interventions, which we term broken
symmetry. Even when a model generates a clean refusal, the correct answer remains linearly recoverable from its hidden states. Furthermore, releasing this withheld answer is a highly local operation, requiring only a single-position patch. Conversely, the reverse operation is not equally local: reimposing suppression requires broader interventions across multiple positions, and assembling a coherent refusal sequence is more difficult still. We further demonstrate that while an average answer-to-refusal displacement vector marks the
geometric difference between these states, it fails to act as a reliable, reversible linear control toggle between behaviours. Taken together, our findings show that refusal does not function as a simple symmetric switch. For safety and
auditing, this implies that probe recoverability can overestimate true behavioural control, and locating refusal-relevant directions does not reliably grant the ability to steer a model from answering to coherent refusal.
Read the full abstract ▾
All authors Yiqi Liu, Yang Wang, Songxin Wang, Chenghao Xiao, Chenghua Lin
Machine Learning
Learning Stock Trading Policies via Barycenter-Based Adversarial Inverse Reinforcement Learning
Arishi Orra, Himanshu Choudhary and Manoj Thakur
Designing effective trading strategies using reinforcement learning remains challenging due to delayed and noisy rewards, poor exploration, and the difficulty of enforcing explicit risk constraints. In this work, we propose BRaG, a barycenter-based
adversarial inverse reinforcement learning framework for stock trading that learns trading behavior from multiple heterogeneous expert strategies. BRaG aggregates expert demonstrations using a performance-weighted Wasserstein barycenter, yielding a stable pseudo-expert representation that captures shared structure across diverse trading styles. This representation is used to pretrain a trading policy via
adversarial imitation learning, which alleviates unstable exploration during reinforcement learning. The pretrained policy is subsequently refined using reinforcement learning with true
market rewards. To ensure risk-aware decision-making, BRaG incorporates control barrier functions that constrain action execution and regularize policy learning to satisfy drawdown limits. We evaluate the proposed approach on four major global equity
markets, including the US, UK, Indian, and Taiwanese indices. Across all the
markets, the proposed approach achieves stronger performance than both classical trading rules and recent deep reinforcement learning methods, while exhibiting more stable risk characteristics.
Read the full abstract ▾
Machine Learning
Temporal Graph Prototype-conditioned Conformal Prediction for Fraud Detection
Xudong Chen, Shengbo Gong, Lu Cheng et al. (+1 more)
Conformal prediction (CP) provides distribution-free coverage guarantees and has emerged as a principled tool for uncertainty quantification. In edge-level fraud detection on temporal interaction graphs, where false positives and false negatives both carry substantial cost, such coverage guarantees are particularly appealing for risk-aware decision making. However, directly applying existing graph conformal predictors yields inefficient prediction sets due to two recurring properties of fraud data. Fraudulent interactions are often embedded in benign-dominated neighborhoods that dilute calibration signals, while extreme class imbalance leaves scarce labeled-fraud support in the calibration split and leads to overly conservative class-conditional thresholds. To address these issues, we propose ProtoCP, a conformal prediction framework for edge-level fraud detection on temporal graphs. ProtoCP improves calibration efficiency by focusing calibration on fraud-relevant subgraph context and producing more stable nonconformity scores under class imbalance and temporal drift. Specifically, it leverages learned prototypes to suppress benign-dominated noise in the calibration context and introduces a neighborhood-relative scoring mechanism with temporal score
diffusion for stable class-conditional calibration. Experiments on four fraud
benchmarks (YelpChi, S-FFSD, FTFD, and BankSim) show that ProtoCP achieves the target coverage with consistently smaller prediction sets than state-of-the-art baselines. Our codes are available at https://github.com/Picard1701ent/ProtoCP.git
Read the full abstract ▾
All authors Xudong Chen, Shengbo Gong, Lu Cheng, Wei Jin
Machine Learning
TinyCast: Probabilistic Zero-Shot Forecasting with Computed Periodicity
Armin Steinhauser
We introduce TinyCast, an
attention-free zero-shot forecaster that emits a predictive distribution from 146,505 parameters, on the premise that at this size the periodic structure of a context is worth computing rather than learning. A zero-parameter spectral detector supplies the dominant periods, the context is folded on their phase, and a dilated convolutional encoder and a block-autoregressive
quantile decoder model the rest. It is smaller than every zero-shot entry on the GIFT-Eval board whose parameter count can be established. On probabilistic accuracy it defines the size-accuracy frontier. Among zero-shot entries declaring no test-data leakage it is the only one below 1.4M parameters that emits a predictive distribution, and every entry scoring better carries at least that budget. On Chronos-ZS and fev-bench every neural model ahead of it carries at least 28 times its parameters. Because the mixing path is convolutions and
matrix multiplications only, it exports to static INT8 and forecasts end to end on an embedded device without per-signal fitting.
Read the full abstract ▾
Robotics
Tac4Loco: Learning Spatiotemporal Plantar Pressure Representations for Humanoid Locomotion
Ziyun Liu, Sikai Guo, Zheng Li et al. (+6 more)
Humanoid robots are expected to traverse complex terrains, where the plantar support may vary dramatically due to foot placement errors, ground properties, and transient dynamics. To achieve robust locomotion, the
robots are required to adapt to uneven terrain and uncertain foot–ground interactions. Existing locomotion policies rely primarily on proprioception or exteroceptive terrain perception, where the former provides only indirect evidence of plantar support, while the latter predicts contact conditions before touchdown but cannot observe the actual support in real-time. Although some studies incorporate plantar contacts as an auxiliary perception, they rely mainly on summary statistics, overlooking the spatial
topology of plantar pressure, which provides a more direct characterization of the realized contact state. To bridge this gap, we present Tac4Loco, a tactile-perceptive framework that incorporates multi-array plantar pressure as direct feedback for
humanoid locomotion. We formulate a
topology-preserving ordinal representation to map simulated and physical sensor signals into a shared observation space, with a dual-branch encoder for extracting their spatial and temporal representations. Subsequently, the learned spatiotemporal features are integrated with augmented proprioception including terrain estimation cues, and provided to an asymmetric actor-critic architecture for policy learning. Extensive simulation and real-world experiments demonstrate improved tracking performance and support adaptation on terrains with inclined, partial, asymmetric, and changing support. We further demonstrate its zero-shot deployment on unseen compliant and unstructured terrains, including a foam platform and a gravel road. All code and experimental configurations will be released as open-source to facilitate reproducibility.
Read the full abstract ▾
All authors Ziyun Liu, Sikai Guo, Zheng Li, Jiahang Cao, Haichao Liu, Pei Qu, Yinghong Zhang, Jinni Zhou, Jun Ma
Hardware Architecture
Concurrency Response of Plain Global Loads on the NVIDIA H100
Somashekar Manjunath and Rahul Ramachandra M
The bandwidth a
memory-bound GPU kernel sustains is set by how many bytes it keeps in flight. We use Little's Law here as throughput accounting, not as a measured hardware pool. CUDA fills that budget on Hopper through plain loads (ld.global) and asynchronous copies (cp.async), among other paths; we characterize their concurrency response with clean-room microbenchmarks on three H100 SXM5 dies. Our main result concerns the plain-load path: attained LDG bandwidth peaks at a small offered per-thread load (K ~ 2) and then declines, by about 35% from K=2 to K=8 at our primary configuration. The decline survives a fixed-work control matching total issued logical loads across K, ascending and reversed sweep orders, and replication on two dies with the same instrument (-35.0% and -35.2%). Separately profiled counters show DRAM bytes nearly constant over K=2->8 while L2-sector traffic rises, and a 40x nominal allocation-size sweep (512 MB to 20 GB, all above the ~50 MB L2; no address trace) leaves the decline essentially unchanged, disfavoring a simple allocation-size dependence. Because the L2 hit-rate nonetheless rises with K at every allocation, the aggregate request stream does change with K; we report K as offered software ILP and leave the hardware mechanism open. A preliminary survey adds a matched cp.async-versus-plain-load comparison (2.1-2.9x at high offered depth, two dies), a die-B same-CTA two-stream observation whose companion die-C check differs and is not pooled, and a cross-die primitive baseline.
Read the full abstract ▾
Computation and Language
Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report
TaoLive AIGC LLM Team: Yuhan Sun, Wenhao Lin, Yongdong Luo et al. (+6 more)
AI-powered digital avatar streamers must answer product questions, engage viewers, and execute marketing strategies in real time, demanding low latency, frequent strategy updates, and accurate yet effective responses. Evolvable Harnesses, whose Skills, Hooks,
prompts, and tools can be updated independently of model weights, enable rapid iteration but expose a trade-off: large models adapt zero-shot yet are too slow, whereas compact models meet latency targets but overfit to fixed Harness configurations. We propose Harness-Aware Training (HAT), which trains compact models to adapt to changing Harnesses. Its key component, Harness-State Augmentation (HSA), applies task-preserving transformations to Skill identifiers and content, tool schemas,
prompt structures, and Hook functions. Training proceeds in three stages: HSA-SFT learns
reasoning and tool use from strong-model trajectories across diverse environments; General On-Policy
Distillation restores generalization lost during SFT; and HSA-RL improves robustness to changing Harnesses through reinforcement learning in augmented environments. Across four evaluation sets, HAT achieves 94.8 on Live-Stream QA (base: 80.3; strongest general LLM: 93.0) and 94.6 on Harness-Variant QA (base: 75.4). Unlike Fixed-Harness SFT, which lowers IFEval by 7.7 points from the base model, HAT avoids this regression and reaches 83.5. On one NVIDIA H20 GPU, the optimized system delivers P50 and P95 latencies of 3.4 s and 8.1 s. Deployed in Taobao Live's digital-avatar service, it also yields positive online A/B test results for item-page views.
Read the full abstract ▾
All authors TaoLive AIGC LLM Team: Yuhan Sun, Wenhao Lin, Yongdong Luo, Yibo Hu, Meiguang Jin, Junfeng Ma, Weihang Pan, Jiaxin Zhao, Zulong Chen
Operating Systems
Global Simulation-Guided Dynamic Operator Scheduling for Efficient Multi-Tenant Model Serving
Weinan Liu, Zeyuan Ding, Dian Ding et al. (+5 more)
Container-granularity scheduling leaves abundant short-lived idle slices within containers unexploited. Reallocating containers is too heavyweight to utilize such fine-grained opportunities under SLA constraints, and operator-level scheduling requires
reasoning about dependencies,
memory safety, and cluster-wide execution dynamics in real time. In this paper, we present SliceScheduler, a dynamic operator-level scheduling system for multi-tenant model serving. The key idea is to expose cluster-wide operator execution state and enable what-if
reasoning over scheduling decisions. SliceScheduler consists of four key components. First, we introduce the Global Mapping Graph (GMG), a unified abstraction that captures operator dependencies, tensor shapes, resource mappings, and execution states, providing a real-time, cluster-wide view with explicit resource semantics. Second, we build a global simulator on top of GMG to predict operator-level execution and
memory evolution under candidate placements. Third, we design an incremental, simulation-based scheduling module that selects placements to exploit fragmented idle slices while avoiding
memory violations and preserving SLA. Finally, we develop an operator executor that materializes scheduling decisions on GPUs and coordinates computation and cross-accelerator transfers. We implement SliceScheduler as a PyTorch backend and evaluate it using production trace replay. Experimental results show that SliceScheduler improves
token throughput by 1.10–2.29$\times$ compared to existing approaches, while maintaining SLA violations within 9%. SliceScheduler demonstrates that operator-level scheduling is a practical and effective approach to improving GPU utilization for multi-tenant LLM serving.
Read the full abstract ▾
All authors Weinan Liu, Zeyuan Ding, Dian Ding, Chengcheng Wan, Lu Tang, Guangtao Xue, Jiwu Shu, Yiming Zhang
Cryptography and Security
Provenance, Not Behaviour: A Serialisation Artifact in Edge-IIoTset and a Leakage-Free Benchmark for Precision-Agriculture Intrusion Detection
Mostafa M. Galal
Edge-IIoTset is the reference
benchmark for machine-learning intrusion detection in the industrial Internet of Things, and results reported on it cluster above 99%. We show that much of that performance is not intrusion detection. The preprocessing recipe distributed with the
dataset instructs researchers to one-hot encode seven categorical columns. Four of them separate attack from normal traffic with an accuracy of 1.0000 on their own, through the spelling of the placeholder written for an absent protocol field: the string "0" in the normal-traffic branch of the
dataset build against "0.0" in the attack branch. The label is recoverable from a serialisation artifact encoding file provenance, with no network behaviour modelled, and separates every row of both curated subsets. Under 5-fold x 3-repeat cross-validation, five of six standard classifiers attain exactly 1.0000 +/- 0.0000 accuracy and the sixth attains 0.99998. Under a corrected protocol, naive Bayes falls by 0.3005 macro-F1 and the strongest model settles at 0.9503 +/- 0.0011. Label, ordinal and frequency encoding leak identically. Because the curated subsets also lack Modbus and per-device identity, we rebuild the
benchmark from the raw captures under uniform parsing, producing AgriEdge: 1,276,122 rows, five devices with full attribution, and no column separating the classes above 0.0288. A leave-one-device-out sweep locates the generalisation boundary at the perception/actuation layer, where random forest falls from 0.9988 to 0.5083 balanced accuracy. Non-IID
federated partitioning costs at most 0.0037 macro-F1, but a 20-round LoRaWAN training run costs 4.6 hours of uplink.
Read the full abstract ▾
Machine Learning · Cross-listed from quant-ph
Machine Learning Approaches to Decoding Topological Quantum Codes
Changwon Lee, Tak Hur, Jeongwoo Jae et al. (+1 more)
Decoding is an essential component of
quantum error correction (QEC), translating stabilizer measurement outcomes into corrective actions that suppress logical errors and preserve logical
quantum information. Building fault-tolerant architectures requires increasing the code distance, which in turn places growing demands on decoding accuracy, scalability, and practical deployability. While a wide range of decoding
algorithms have been proposed and demonstrated, achieving reliable, scalable, and real-time decoding remains a significant challenge. Machine-learning (ML) approaches are particularly well suited to this setting, as
quantum error decoding is fundamentally a problem of processing large volumes of classical data with complex spatiotemporal correlations. This chapter surveys ML-based methods for
quantum error decoding, with a focus on topological codes and an emphasis on architectural principles, practical performance, and real-time considerations. We first frame decoding as a learning problem and outline key paradigms, including discriminative, generative, and reinforcement-learning formulations. We then introduce the neural network building blocks that underpin most contemporary neural decoders and discuss how these components can be integrated to balance expressivity, scalability, and latency. Building on this architectural perspective, we review recent progress and
benchmarks in neural decoding for
memory experiments, and discuss real-time decoding, open challenges, and future directions toward scalable fault-tolerant
quantum computing.
Read the full abstract ▾
All authors Changwon Lee, Tak Hur, Jeongwoo Jae, Daniel K. Park
Systems and Control
Output Feedback Adaptive Performance Control
Panagiotis S. Trakas and Charalampos P. Bechlioulis
In this paper, we consider uncertain high-order nonlinear systems performing dynamic tracking tasks under hard actuator constraints, where only the output error is available for measurement, while the system states and the desired trajectory derivatives are unavailable for feedback. We propose a robust output-feedback controller that guarantees adaptive performance specifications in this framework. The proposed scheme employs a novel Prescribed Performance Observer (PPO) with dynamic gains, which enhances estimation accuracy while avoiding large fixed observer gains. In addition, we introduce an adaptive mechanism that dynamically adjusts the output performance specifications according to the actuator limitations, ensuring bounded closed-loop signals. We establish a separation principle showing that the output-feedback scheme recovers the performance of its state-feedback counterpart. Comparative simulations demonstrate accurate tracking and smoother applied control under actuator limitations, uncertainties, and measurement noise.
Read the full abstract ▾
Computer Vision
Beyond Independence: Learning Correlated Views for Variational Incomplete Multi-View Clustering
Zheming Xu, Aiyue Tang, Shidi Chen et al. (+4 more)
Incomplete multi-view clustering (IMVC) aims to uncover shared cluster structures from data with partially observed views. Although recent imputation-free methods based on variational inference demonstrate robustness to missing views, they commonly rely on a conditional independence assumption across views in the posterior aggregation stage, which fails to capture the inherently structured and potentially correlated nature of multi-view data. In this paper, we propose a variational framework that explicitly goes beyond this assumption by introducing a learnable cross-view correlation structure. Specifically, we explicitly model and learn correlations between views by utilizing the covariance structure of posterior estimation errors during aggregation. To facilitate robust and efficient learning, the correlation
matrix is parameterized through a normalized Cholesky decomposition, ensuring positive definiteness and enabling the entire model to be trained jointly through a unified variational objective. Extensive experiments on multiple IMVC
benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches across diverse missing-view settings while introducing only a negligible number of learnable parameters. These results highlight the effectiveness of adaptive correlation modeling in variational IMVC, demonstrating the need to go beyond the independence assumption in IMVC. The code is available at https://github.com/zmxu196/ACOVA.
Read the full abstract ▾
All authors Zheming Xu, Aiyue Tang, Shidi Chen, Xuechao Zou, Congyan Lang, Rogelio A. Mancisidor, Michael Kampffmeyer
Artificial Intelligence
Intent-Driven Situation Tracking for User-Centric Multi-Turn Agents
Meiling Tao, Yiling Tao and Peng Wang
User-centric multi-turn
agents must act on an evolving task situation shaped by changing user intents, accumulated tool-grounded facts, missing information, and execution constraints. Existing context-management methods improve the use of past interaction history, but rarely maintain an explicit situation state that separates grounded facts from task-state judgments. As a result,
agents often need to infer fine-grained attributes, task dependencies, and constraint satisfaction implicitly from dialogue traces. We propose Intent-Driven Situation States (IDSS), a training-free framework that maintains an explicit situation state alongside the dialogue. IDSS parses tool returns into provenance-aware entities and attributes, tracks user intents, required variables, constraints, and execution status, and propagates new facts to task constraints to update action executability. This allows
agents to avoid infeasible actions, advance dependent goals, and reuse relevant information without repeatedly searching raw history. Experiments on three interactive
benchmarks across eight LLMs show that IDSS improves task completion, preference elicitation, and interaction efficiency, with clear gains on tasks involving multi-entity coordination, evolving user constraints, and constraint-aware replanning. Ablations and error analyses show that these improvements come from the interaction between fact persistence, intent-centered state tracking, and constraint modeling. These results suggest that explicit situation tracking offers an effective alternative to history-centric context management for reliable user-centric multi-turn
agents.
Read the full abstract ▾
Information Theory · Cross-listed from quant-ph
Designing Quantum Error Correcting Codes to fit decoders via Reinforcement Learning
Omer S. Sella, Robert Pinsler and Thomas Heinis
We present a reinforcement learning (RL) approach to the co-design of stabilizer sets of
Quantum Error Correcting Codes (QECCs) and decoders. We show how to produce a generative model that produces Bivariate Bicycle (BB) codes based on the choice of decoder. Specifically, we fix a decoder architecture and use Proximal Policy Optimisation (PPO) to train an
agent over BB codes to maximise decoder performance under a depolarising channel noise model.
Read the full abstract ▾
Information Theory · Cross-listed from math.LO
S2a-reducibility and differentiation in Martin-Löf random reals
Georgii Sirotenko and Ivan Titov
Solovay reducibility is studied intensively as a tool to compare the approximability and the degree of randomness of left-c.e. reals. By definition, a real is left-c.e. if it has a left-c.e. approximation, that is, it is the limit of an effective nondecreasing sequence of rationals. If reals $\alpha$ and $\beta$ have left-c.e. approximations $a_0, a_1, \ldots$ and $b_0, b_1, \ldots$, respectively, such that the approximation ratios \[ \frac{\alpha-a_n}{\beta-b_n} \] are bounded from above by a constant, the real $\alpha$ is Solovay reducible to $\beta$. The latter is the case for any such $\alpha$ and $\beta$ and their left-c.e. approximations whenever $\beta$ is Martin-Löf random by the Kučera-Slaman
Theorem [DOI:10.1137/S0097539799357441]. This result was substantially strengthened by Barmpalias and Lewis-Pye [DOI:10.1016/j.jcss.2017.06.002], who demonstrated that, under the given assumptions, the approximation ratios are not only bounded but actually converge to a limit, which does not depend on the considered left-c.e. approximations. There is a quest for a suitable extension of Solovay reducibility to the class of all reals. Promising candidates include S2a-reducibility on the set of computably approximable reals by Zheng and Rettinger [DOI:10.1007/978-3-540-27798-9_39] and monotone Solovay reducibility by Titov [DOI:10.1007/978-3-031-95908-0_33]. For the latter, Titov [DOI:10.1017/jsl.2025.10157] demonstrated that the
theorems of Kučera and Slaman and of Barmpalias and Lewis-Pye extend to all reals. He conjectured further [DOI:10.1017/jsl.2025.10157,
Conjecture 3.2] that similar extensions hold for S2a-reducibility in terms of its functional characterization by Kumabe, Miyabe, and Suzuki [DOI:10.3233/COM-230486]. In this work, we refute this
conjecture by proving that the analogue of the Barmpalias-Lewis-Pye Limit
Theorem does not hold for S2a-reducibility.
Read the full abstract ▾