Artificial Intelligence
Making Alternative Data Work: Context-Augmented LLMs for Financial Forecasting
Jihoon Kwon, Lawrence Liu, Daekyung Park et al. (+15 more)
When
forecasting a firm's future financial performance, alternative data - data collected from non-traditional sources such as consumer transactions, web traffic, and prediction
markets - can provide timely signals about firms' operating activities and broader
market conditions. These signals may reveal information that is not captured by traditional public sources and can therefore provide complementary information for
forecasting firms' future financial performance. However, firm-level alternative data often have limited historical coverage, are relevant only to specific prediction targets or subsets of firms, and are distributed across numerous heterogeneous channels, making them difficult to incorporate flexibly into conventional
forecasting approaches. Meanwhile, large
language models (LLMs) can interpret instructions, learn from in-context examples, and generate predictions by combining heterogeneous information without task-specific parameter updates. Motivated by this potential flexibility, we investigate whether an LLM can forecast firm performance by integrating alternative data with other financial information through in-context learning. We propose a two-
agent framework that first identifies the firms for which each alternative data channel is likely to be informative and then predicts revenue using firm- and channel-specific context. We evaluate the framework across four commercial alternative data channels. In our experiments, adding alternative data in context alongside other financial information improves the LLM's
forecasting relative to either source alone, and these forecasts are more accurate than those of standard
forecasting baselines. These findings suggest that LLMs provide a flexible and practical approach to integrating alternative data with heterogeneous financial information.
Read the full abstract ▾
All authors Jihoon Kwon, Lawrence Liu, Daekyung Park, Sumin Kim, Haverty Jack, Hoyoung Lee, Katherine Bjorkman, Josh McKenney, Peter Laurelli, Nicole Kagan, Zach Golkhou, Thorsten Neumann, Edward Tong, Pete Petersen, Yoon Kim, Alejandro Lopez-Lira, Yongjae Lee, Chanyeol Choi
Machine Learning · Cross-listed from stat.ML
Identifiability of Nonnegative Tensor Decompositions via Positive Scattering
Haoming Wang and Ming Yuan
Identifiability of tensor decompositions is often established through linear-algebraic conditions on the factor families. For nonnegative decompositions, however, positivity provides additional information that is not captured by dimension and independence alone: nonnegative terms cannot cancel, and their supports constrain competing decompositions. We introduce a positive scattering term that quantifies this additional source of identifiability and combine it with the dimension budget underlying the Lovitz–Petrov generalization of Kruskal's
theorem. For every subset of components, we obtain two sufficient conditions: a threshold of $2|S|-2$ guarantees minimality and nonnegative rank, while the stronger threshold $2|S|-1$ guarantees uniqueness among nonnegative decompositions of the same length. The key result is a positive splitting inequality for irreducible exchanges of nonnegative rank-one tensors, which combines the dimension constraint with support-induced
geometric rigidity. Although the scattering term is defined through an optimization over intermediate factor spaces, we show that its mode costs are exactly $0$, $1$, or $+\infty$, yielding an exact activation characterization in terms of graph connectivity. The resulting criterion can strictly certify sparse nonnegative tensor decompositions beyond the reach of Kruskal and Lovitz–Petrov conditions, including examples for which those conditions fail even after reshaping. In the
matrix case, the two criteria reduce respectively to full-rank factorization and two-sided separability.
Read the full abstract ▾
Computer Vision
MMGait: Benchmarking and Unifying Gait Recognition across Heterogeneous Modalities
Saihui Hou, Chenye Wang, Qingyuan Cai et al. (+2 more)
Gait recognition is commonly studied using RGB
videos or their derived silhouettes and poses. Yet human walking produces heterogeneous photometric,
geometric, and motion cues that cannot be systematically examined with RGB-centered
benchmarks. We present MMGait, a large-scale multi-sensor
benchmark that brings visible, infrared, depth,
LiDAR, and radar observations into sequence-level correspondence. It provides diverse modalities spanning appearance, contours, geometry, motion, and body structure. Under a shared impostor-augmented protocol, we evaluate single-modal recognition, cross-modal recognition via directed
retrieval, and multi-modal recognition using task-specific experts. Across settings, modality rankings vary with probe conditions, cross-modal
alignment remains difficult, and fusion often provides complementary gains. This analysis exposes a scalability problem: individual modalities, modality pairs, and fusion configurations are typically handled by separately trained experts. We formulate Omni-Modal Gait Recognition, which unifies single-modal, cross-modal, and multi-modal recognition within a shared identity space. OmniGait++ uses modality-specific front ends followed by a shared identity encoder to preserve modality-dependent cues while learning comparable identity descriptors. An anchor-guided fusion module aggregates modality subsets of varying size without frame-level synchronization. A jointly trained checkpoint covers all three recognition settings and accommodates modality subsets of different compositions and cardinalities. Experiments show OmniGait++ remains competitive with task-specific experts in many shared settings and extends to higher-cardinality fusion unavailable to fixed-pair models. The results establish MMGait as a common testbed for heterogeneous gait sensing and demonstrate the feasibility of unified recognition under varying modality availability.
Read the full abstract ▾
All authors Saihui Hou, Chenye Wang, Qingyuan Cai, Aoqi Li, Yongzhen Huang
Computational Geometry
Some results on Archdeacon's conjecture for rotation systems
Arahat Chikkatur and Ji Zeng
A rotation system on $n$ elements assigns to each element a cyclic order of the other $n-1$ elements. A four-element subset is non-planar if its induced rotation system cannot be realized by a crossing-free drawing of $K_4$. As a combinatorial strengthening of Hill's
conjecture on the crossing number of the complete graph, Archdeacon conjectured that every rotation system on $n$ elements has at least $H(n)=\frac{1}{4} \lfloor\frac {n}{2}\rfloor \lfloor\frac{n-1}{2}\rfloor \lfloor\frac{n-2}{2}\rfloor \lfloor\frac{n-3}{2}\rfloor$ non-planar four-element subsets. We computationally verify Archdeacon's
conjecture for $n\leq 10$ and show that every extremal rotation system in these orders is realizable by a simple drawing. With computer assistance, we prove that every rotation system on $n$ elements has at least $(8/9 - o(1)) H(n)$ non-planar four-element subsets. We also present a proof by hand for a weaker lower bound of $(2/3-o(1)) H(n)$. Finally, extending recent work of Felsner on antipodal pairs in drawings, we show that Archdeacon's
conjecture holds for antipodally shellable rotation systems.
Read the full abstract ▾
Cryptography and Security
From Intent to Execution Grant: An Execution-Boundary Conformance Profile for High-Risk AI Actions
Mengting Wu, Lin Wang, Yong Zhang et al. (+1 more)
AI
agents increasingly propose actions with external consequences, including financial transfers, infrastructure changes, software deployments, disclosures, and physical actuation. Authorization engines, policy
languages, runtime monitors, provenance mechanisms, and
agent guardrails provide important foundations, but do not necessarily define a common semantic contract for the final transition from a particular candidate action to execution authority. We specify EBL-Core, an execution-boundary conformance profile for deciding whether one canonical, fully materialized AI-generated candidate may receive action-scoped execution authority under explicit conditions. It binds a structured intent object, Root and Operational Policies, evidence obligations, typed evidence, context, time, and a verifiable Decision Derivation through an Execution Release Contract (ERC). An ERC is not an authority-bearing
token; a verified ALLOW ERC may support a separate Execution Grant governed by Redemption-time validation. EBL-Core specifies action binding, policy non-weakening, evidence handling, deterministic adjudication, derivation verification, and grant lifecycle behavior. An accompanying reference artifact provides schemas, adjudication, separate verification and Semantic Replay, and a linearizable in-
memory grant store. In the retained run, 34 static vectors and 15 lifecycle checks matched expected outcomes. Across 100 trials, 32 concurrent Redemption attempts yielded exactly one successful Redemption and protected test effect per trial; 100 Revoke-Redeem races ended in valid terminal outcomes. These bounded results demonstrate executability of the specified subset, not human-intent correctness, evidence truth, complete mediation, production readiness, mechanized correctness, or deployment-level security.
Read the full abstract ▾
All authors Mengting Wu, Lin Wang, Yong Zhang, Jiang Deng
Machine Learning · Cross-listed from stat.ML
CHOIR: heterogeneity-aware conformal prediction for crash injury severity across driver safety strata
Amir Rafe and Subasish Das
Transportation agencies increasingly predict crash-injury severity with statistical and machine-learning models, but these models do not state how often their output contains the recorded injury level or for which groups of drivers it fails, a gap that matters most for motorcyclists and unrestrained drivers. This study develops and evaluates a certification layer that gives any fitted severity model a finite-sample, distribution-free coverage guarantee within prespecified safety strata. The layer, CHOIR (Conformal Heterogeneity-aware Ordinal Inference with Risk control), combines groupwise and weighted conformal prediction with conformal risk control to return contiguous KABCO intervals, and adds a declared sensitivity analysis for medically assessed injury and bounds on fatal omission. It is evaluated on 4.04 million Texas crashes from 2017-2023, one sampled driver per crash, with seven base models from the ordered logit to a tabular foundation model, and on held-out counties and later years. Under one pooled threshold every model reaches 0.90 coverage overall but covers motorcyclists or unrestrained drivers at 0.868 or lower, and class-balanced gradient boosting covers unrestrained drivers at only 0.374. Calibration within four safety strata places all 28 model-by-stratum estimates between 0.898 and 0.907, at the cost of sets spanning 3.6 to 4.6 of five categories for these groups, and the certified ordered logit is within 0.03 categories of the narrowest model. Injury-model coverage should therefore be certified within safety groups rather than on average, calibration rather than model complexity determines validity, and a statewide threshold should not be applied to small rural counties without local calibration data.
Read the full abstract ▾
Hardware Architecture
CHERI-D Reincarnate: efficient multicore CHERI temporal memory safety through allocation reincarnation (draft version)
Yuecheng Wang, Jonathan Woodruff and Simon W. Moore
We propose CHERI-D Reincarnate (Reinc), an architectural extension to CHERI for scalable and efficient temporal
memory safety. Prior work CHERI-D has a finite-width generation ID stored at a fixed location, requiring an object to be quarantined when its ID is exhausted. Reinc further provides use-after-free mitigation while permitting immediate freed
memory reuse for objects through allocation reincarnation: rather than quarantining an allocation slot upon ID exhaustion, Reinc dynamically assigns a new ID to that slot when its current ID is exhausted. Exhausted IDs are quarantined and later reclaimed, while the underlying
memory remains available for immediate reuse. By quarantining IDs rather than
memory, Reinc enables continuous reuse of
memory in the common case, substantially reducing both
memory-sweep frequency and quarantine
memory overhead. Reinc further introduces coherent ID caching while retaining a fully decentralized ID organization. Temporal metadata remains colocated with the
memory it protects, preserving locality while avoiding centralized metadata structures. To support multicore execution, Reinc connects physical coherence events to the virtually addressed ObjID buffer using lightweight reverse-map and filter-based mechanisms. We implement Reinc as a hardware-software co-design spanning CHERI-Toooba (superscalar FPGA softcore), QEMU, LLVM/Clang and CheriBSD. Across our evaluated workloads, Reinc substantially reduces
memory-sweep frequency and
memory quarantine while incurring low performance and hardware overhead.
Read the full abstract ▾
Numerical Analysis · Cross-listed from math.RA
Quasilinear multiplication in the Cayley-Dickson tower
Harrison Lemley
Direct evaluation of the defining product of the Cayley-Dickson
algebra $A_n$ of rank $N:=2^n$ over a unital commutative ring $R$ in which $2$ is invertible requires a quadratic number of arithmetic operations. This paper gives a uniform bilinear
algorithm for multiplication in this
algebra costing $O(N \log N)$ arithmetic operations in $R$ and $O(N)$ auxiliary storage when the doubling parameters of $A_n$ are units whose square roots lie in a fixed commutative coefficient
algebra $S$ finitely generated as an $R$-module and admitting an $R$-linear map $\pi\colon S \to R$ with $\pi(1) = 1$. In particular, over $\mathbb{R}$ and every finite field $\mathbb{F}_{q}$ of odd characteristic, a quadratic field extension contains a square root of every possible doubling parameter, so the
algorithm applies to every Cayley-Dickson tower over these fields, and the tensor rank of multiplication in $A_n$ over them is at most $(9n-21)2^n+28$ when $n\ge2$. When the top doubling parameter is a non-square, as in the standard real tower, the bound is $(9n-15)2^{n-1}+10$. To the author's knowledge, the
algorithm presented in this paper is the first uniform subquadratic
algorithm for multiplication in $A_n$. When $R=\mathbb{R}$ with every doubling parameter equal to $-1$, the real quasilinear schedule uses fewer total arithmetic operations than both direct multiplication and a uniform
algorithm of Cariow-Cariowa for $n\ge4$. An implementation for the standard real tower is available in the MIT-licensed C11 library fastCD, with a NumPy-backed Python interface. In single-core
benchmarks against direct multiplication and the uniform Cariow-Cariowa method, the quasilinear implementation had the lowest mean time of the three at every tested dimension $N\ge32$, for both single and batched products, and was over $17$ times faster than direct multiplication at $N=1024$.
Read the full abstract ▾
Numerical Analysis
Convergence of finite element approximations for the one-dimensional stochastic Burgers equation with additive trace-class noise
Binjie Li, Xiaoping Xie and Qin Zhou
This paper investigates finite element approximations of the one-dimensional viscous
stochastic Burgers equation with additive trace-class noise. For the $P_2$ finite element spatial semi-discretization, we derive strong error estimates that are optimal with respect to regularity in \(L^p([0,T] \times \Omega;H_{D}^{\alpha,q})\) for \(p,q\in[2,\infty)\) and \(\alpha\in[-1,0]\), as well as an almost regularity-optimal estimate in \(L^p(\Omega;C([0,T];L^\infty(\mathcal{O})))\). Furthermore, we derive weak error estimates for moments of both terminal $L^q$-norms and space-time $L^p(0,T;L^q(\mathcal{O}))$-norms, with weak convergence rates (nearly) twice the corresponding strong ones. For the fully discrete scheme, which combines the \(P_2\) finite element method in space with a drift-implicit Euler–Maruyama scheme in time, we establish a strong temporal convergence rate of order \(\tau^{1/2-\varepsilon}\) in a discrete analogue of \(L^p(\Omega;C([0,T];L^\infty(\mathcal{O})))\), under the condition \(\tau \leqslant h^2\). Numerical experiments are presented to illustrate the theoretical convergence rates.
Read the full abstract ▾
Computer Vision
OmniKVQuant: KV Cache Quantization for Omni-LLMs
Suho Yoo, Hyunjong Ok, Jongmin Choi et al. (+2 more)
As Omni-modal large
language models (Omni-LLMs) take in audio,
video and text together, their KV cache
memory cost grows. KV cache quantization is the de facto approach in text-only LLMs, but its application to Omni-LLMs remains unexplored. In this paper, we analyze how TurboQuant, a representative rotation-based KV cache quantization method, behaves on
multimodal caches and identify two critical issues: temporal key drift and heterogeneous value geometry. To address these, we propose OmniKVQuant, a training-free framework that (i) sets the key quantization range over each short window of the input stream; and (ii) rotates values separately per modality. On Qwen2.5-Omni and Qwen3-Omni, OmniKVQuant enables 2-bit KV caches while substantially preserving performance across seven audio-visual
benchmarks. We further provide a fused Triton decode kernel that unpacks the 2-bit cache during
attention, so no dense FP16 cache is ever built. Code: https://github.com/kaistmm/OmniKVQuant
Read the full abstract ▾
All authors Suho Yoo, Hyunjong Ok, Jongmin Choi, Jihoo Jung, Joon Son Chung
Machine Learning
A Dataset and Model for Imputing Water Surface Elevation on a Large and Extremely Sparse Spatiotemporal Graph
Ruben Cartuyvels, Karim Douch, Gabriele Bertoli et al. (+4 more)
Continuous monitoring of water surface elevation across river networks is critical for flood
forecasting, water resource management, and understanding the global water cycle. Yet, the scarcity of in situ gauges across much of the globe constrains the development of reliable modeling frameworks. Satellite altimetry has the potential to alleviate this problem but its use is currently hindered by sparse temporal coverage. To this end, we introduce AmazonSWE, a
dataset for training and evaluating large-scale spatiotemporal graph imputation methods that integrates processed satellite altimetry measurements from a range of sources, including the recent wide-swath SWOT sensor. The
dataset covers over 19K river sections and 10 years (2016-2026) in the Amazon river basin, with in situ gauges held out for evaluation. Besides contributing a novel real-world use case with the potential for societal impact, AmazonSWE introduces significant technical challenges: with fewer than 1% of sections observed per day, the
dataset is far sparser than existing imputation
benchmarks, and its directed acyclic river
topology is both structurally different from and larger than graphs in existing
datasets. We show that prior spatiotemporal graph imputation methods are not adapted to this
topology, scale and sparsity, and propose a simple bidirectional selective state space model that outperforms them by sampling connected subgraphs and flattening space and time into a single
token sequence with
topology-aware positional encodings. Compared to the state-of-the-art published method for SWOT-based WSE densification, which integrates statistics with physical modeling, our model reduces RMSE against in situ gauges by 18-39%, while producing predictions for every river section rather than only those with sufficient nearby satellite coverage.
Read the full abstract ▾
All authors Ruben Cartuyvels, Karim Douch, Gabriele Bertoli, Mounia El Baz, Artemis Vrettou, Sébastien Lefèvre, Diego Fernandez Prieto
Robotics
Quasi-static analysis of passive stability in a novel underactuated multi-finger hand
Léonie Plancoulaine, Sylvain Guégan, Franck Plestan et al. (+1 more)
Underactuated robotic hands achieve adaptive and robust grasping with a reduced number of actuators, but predicting the stable
equilibrium pose of the grasped object remains a significant challenge. This paper introduces a quasi-static analytical approach to assess passive stability in underactuated multi-finger hands. A novel three-finger hand architecture integrating a differential spring-loaded slider mechanism is introduced, enabling versatile and adaptive grasping. The study focuses on how the differential mechanism influences the overall grasp behavior and analyzes the effect of object size on the stable
equilibrium configurations for two canonical grasp types: cylindrical and spherical.
Read the full abstract ▾
All authors Léonie Plancoulaine, Sylvain Guégan, Franck Plestan, Damien Chablat
Logic in Computer Science
Medvedev Logic is Not Decidable. It is {\pi}01 -complete. Who Would Have Guessed?
Pawel Pawlowski
This project began as an attempt to prove that Medvedev logic is decidable with the help of generative AI systems. The author (as well as the generative AI systems, or at least they claim to be since I have asked them) was surprised by its eventual conclusion. We prove that Medvedev logic ML, the intermediate logic of finite problems, is Pi-01-complete under computable many-one reductions. Consequently, ML is not recursively enumerable, a fortiori undecidable, and admits no recursively enumerable sound and complete proof calculus. The proof connects the periodic domino problem with intuitionistic formulas through a shared intermediate structure that we call a Wang-Medvedev pair. Such a pair consists of a finite partially ordered set of roles together with demands. Demands define the interaction between roles. A realization labels nonempty subsets of a finite set with these roles, respecting the order and satisfying the demands. We associate a pair with each finite Wang system and show that it has a realization iff the system tiles a finite
torus. We then construct an intuitionistic formula that fails on some finite Medvedev frame iff the same pair is realizable. Realizability thus provides the link between periodic tilings and the countermodels.
Read the full abstract ▾
Computer Vision
Learn the Solid, Not the File: Canonical Inputs for Neural Networks on CAD Boundary Representations
Heinrich Jiang, Hager Yasser Mohamed, Alexander Hitt et al. (+3 more)
Boundary representation (B-rep) is the standard format used by modern CAD systems for parametric 3D models. It turns out, the exact same solid can be represented by different B-reps: for example, two engineers using different operations, a geometry kernel rebuilding the file, and an export setting repartitioning faces will lead to different B-reps even though the underlying solid remains the same. We show that existing B-rep encoders are not robust to variation in the B-rep with the same solid on perturbations applied to standard
benchmarks, naturally occurring variations inherent to CAD software, and differences in how designers model the same part via a human
dataset we created in FreeCAD. The performance of popular B-rep encoders often collapses catastrophically. We propose the canonical region graph, an input representation whose nodes, features and coordinate frame are derived from the solid itself and show theoretical invariance guarantees on repartitioning and rigid motions. It matches the strongest baseline on standard
benchmarks, and is stable under every perturbation we test.
Read the full abstract ▾
All authors Heinrich Jiang, Hager Yasser Mohamed, Alexander Hitt, Valeriia Lomakina, Henning Jiang, Jennifer Jang
Information Retrieval
TimelyRAG: Semantic-Temporal Hybrid Retrieval for Time-Critical Question Answering in Overlapping-Evolving Documents
Youngeun Nam, Joeun Kim, Hwanjun Song et al. (+3 more)
Although large
language models (LLMs) and
retrieval-augmented generation (RAG) have advanced open-domain question answering (QA), they remain unreliable when documents evolve through amendments. Existing time-sensitive
retrieval methods address only the disjoint-evolving environment, where each update is an independent snapshot. However, laws, policies, and regulations often operate in overlapping-evolving environments, where amendments override earlier clauses while preserving most content, creating strong semantic overlap across versions. We propose TimelyRAG, a retriever-agnostic framework that incorporates temporal distance into ranking to align queries with version-appropriate documents. We also introduce TimelyQABench, the first
benchmark for regulation-heavy domains with overlapping-evolving challenges. Experiments show consistent gains, up to +28.6% in nDCG@10, highlighting the importance of temporal
reasoning for reliable QA over evolving documents. All resources are available at https://github.com/kaist-dmlab/TimelyRAG.
Read the full abstract ▾
All authors Youngeun Nam, Joeun Kim, Hwanjun Song, Susik Yoon, Jae-Gil Lee, Byung Suk Lee
Artificial Intelligence
Enabling Knowledge Graph Understanding at Scale with the EXplore Your Graphs ENgine (EXYGEN)
Harshdeep Singh, Yurui Zhu, Giovanni Colavizza et al. (+1 more)
We present EXYGEN (EXplore Your Graphs ENgine), a framework for knowledge graph (KG) understanding that enables conversational access to KGs at scale. We address two questions in sequence. First, how effectively can LLMs perform text-to-SPARQL generation given only automatically derived structured metadata and small graph samples, rather than task-specific fine-tuning? We integrate VoID descriptions and ShEx schemas into a
retrieval-augmented generation (RAG) pipeline and ablate KG-derived context on the SciQA
benchmark. Our best configuration – combining ShEx schemas, retrieved triples, and example question-query pairs – reaches an exact match of 0.419 on execution results without any LLM fine-tuning. We further find that lexical metrics such as F1 poorly predict query correctness, and that larger general-purpose LLMs can outperform smaller code-specialized ones once given sufficient context. Second, we ask how to generate the structured metadata that this method relies on from very large KGs, where KG metadata generation becomes computationally intractable. We introduce a predicate-coverage-aware parallel graph sampling strategy that preserves structural diversity while remaining computationally tractable. On OpenCitations Meta and GESIS, it retains high predicate coverage with minimal triple loss and reduces runtime by over 80x; on ORKG, sampling is not just faster but the only tractable path to obtain complete metadata. Together, these results show that structured schema context and lightweight prompting can substantially reduce reliance on fine-tuning for scalable conversational access to KGs, though closing the remaining gap to fully fine-tuned approaches will likely require reducing dependence on curated question-query exemplars – whether through synthetic generation or an execution-feedback-driven approach – and validating these findings beyond a single
benchmark.
Read the full abstract ▾
All authors Harshdeep Singh, Yurui Zhu, Giovanni Colavizza, Matteo Romanello
Systems and Control
Critic-Free Policy Iteration for Continuous-Time Zero-Sum Games: A Policy-Space Riccati Approach
Jiacheng Wu, Yang Zhu and Hongye Su
This paper develops a critic-free policy iteration (PI) method for continuous-time linear zero-sum games. The central idea is to characterize the saddle-point policies directly in the joint policy space, rather than treating the quadratic value
matrix as an iterative variable. A policy game Riccati equation (PGRE) is introduced whose unknowns are policy gains only. Its solutions are shown to be in one-to-one correspondence with the symmetric solutions of the game algebraic Riccati equation. Based on a stabilizing anchor, PI is performed directly in the actor space. The actor-space Jacobian is nonsingular at every stabilizing policy, and the resulting policy sequence coincides with that of simultaneous PI. For unknown dynamics, a data-driven
algorithm uses a single batch of data and nullspace projection of endpoint increments to eliminate the value
matrix, yielding an actor-only regression. A necessary and sufficient rank condition for unique policy recovery is established and shown to be iteration-invariant, demonstrating that critic identifiability is unnecessary. A power systems frequency-regulation example verifies convergence and policy recovery, while scalability tests demonstrate substantial reductions in computational and
memory requirements.
Read the full abstract ▾
Distributed Computing
Entwine: Coordinating Tiled Computation and Fine-Grained Communication across GPUs
Kai Ma, Quanfeng Lv, Jingguo Ge et al. (+2 more)
Modern high-performance GPU computations partition tensors into tiles to exploit data reuse and parallelism. Individual tile computations complete earlier than the full tensor computation, creating opportunities to overlap computation and communication. However, a mismatch between computation and communication progress can limit these opportunities. Communication stalls when no data is ready, and may lag when data arrives in bursts. Communication can also slow computation by consuming shared resources, offsetting the benefits of overlap. We present Entwine, which coordinates tile computation order, fine-grained communication, and SM resource allocation to minimize overall completion time. Entwine reorders tile computation to produce data for communication at a more regular pace. Entwine couples this schedule with fine-grained SM-based communication to process tile results with low latency and low overhead. Since the communication kernel also consumes SM resources, Entwine coordinates their allocation to balance communication progress against computation slowdown. Across representative tensor-parallel LLM workloads, Entwine achieves a geomean speedup of 1.232x (up to 1.433x) over cuBLAS+NCCL, and outperforms state-of-the-art overlap baselines by 3.1-9.8% in geomean. We will open-source our implementation upon publication.
Read the full abstract ▾
All authors Kai Ma, Quanfeng Lv, Jingguo Ge, Bowei Dai, Kefan Ruan
Robotics
Memory as Plans: World-Action Modeling with Memory-Grounded Planning
Sizhe Zhao, Haozhe Xie, Weiyu Zhao et al. (+5 more)
Mainstream robotic policies often adopt a Markovian formulation, but many complex real-world manipulation tasks are inherently non-Markovian, requiring long-horizon
memory beyond the current observation. Existing
memory mechanisms often rely on
language summaries, growing visual windows, or their combinations, and may therefore lose fine-grained visual evidence or face a trade-off between history coverage and execution efficiency. We introduce MaP-WAM, a
Memory-as-Plans framework that decomposes
memory-dependent world-action modeling into
memory-grounded planning and plan-conditioned execution, and uses long-term
multimodal episodic context as planning-time evidence rather than repeatedly conditioning the executor on the full history. MaP-WAM represents
memory as completed segment records containing
language instructions and sparse visual context, and converts this episodic
memory into compact plans comprising the next segment-level
language plan and corresponding visual guidance. A World-Action-Progress (WAP) model executes each plan over an unknown duration by jointly predicting action chunks and corresponding execution progress at inference time, calibrating predicted progress through plan-observation
alignment for adaptive segment transitions and closed-loop context updates. MaP-WAM keeps the executor context length fixed, while structured
attention further enables key-value caching in both planning and execution. MaP-WAM achieves state-of-the-art performance on RMBench with an 83.3% success rate and attains 78.0% success on real-
robot tasks, while maintaining approximately constant executor inference latency as task history grows.
Read the full abstract ▾
All authors Sizhe Zhao, Haozhe Xie, Weiyu Zhao, Chenchu Zhang, Huan Wang, Chenyang Wang, Qinglin Liu, Shengping Zhang
Software Engineering
PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews
Miguel Zabaleta and Baihan Lin
Large
language models (LLMs) and AI-enabled software increasingly participate in systematic-review decisions, yet the information needed to audit these workflows is reported inconsistently. We analyze SciLitBench, a corpus of 888 review-automation papers with 14,726 annotations, to characterize changes in methods, review-stage use, evaluation and reported limitations. Automation has shifted toward LLM- and software-facing workflows, including stages that can alter the evidence base. Since 2023, 38.0% of software/product papers reported no evaluation, compared with 9.3% of LLM papers. Reporting coverage increased with LLM workflow complexity, yet 52% of positive-only LLM evaluations still reported an unmet reliability or performance requirement. From these patterns, we introduce PRISMA-LLM, an empirically grounded framework separating implementation disclosure from consequence-sensitive evaluation and limitation reporting.
Read the full abstract ▾
Robotics
CAP: Continuously Adaptive Perception-Blind Humanoid Locomotion via Learned Denoising
Hongjin Chen, Zijun Xu, Shihao Ma et al. (+8 more)
Humanoid locomotion across complex terrain demands forward-looking exteroception to anticipate obstacles, yet this signal is unreliable in real-world deployment, failing partially and intermittently. Existing perceptive policies often assume that depth observations remain clean and in-distribution, while recent attempts to unify perceptive and blind control typically route or switch between separate sub-policies, leaving recoverable information in partially corrupted depth unexploited. We instead propose CAP, a single-stage
humanoid locomotion policy that recovers this signal with a perceptive world-model encoder trained as a learned denoiser to reconstruct clean depth from a corrupted input, together with a co-active proprioceptive variational encoder that supplies depth-free body-state information. A coupled training recipe pairs a depth-noise curriculum on the world-model input with world-model feature dropout on the policy-facing latent, exposing the policy to failures across the entire perception-quality spectrum. In simulation, CAP matches or improves upon perceptive baselines when depth remains informative, and degrades more smoothly than a binary-switching baseline as perception worsens. On the Unitree G1, controlled trials and indoor-outdoor deployments demonstrate perception-robust locomotion under intermittent occlusion, real-sensor corruption, and outdoor depth artifacts.
Read the full abstract ▾
All authors Hongjin Chen, Zijun Xu, Shihao Ma, Yi Zhao, Xilai Liu, Ke Ma, Wei Zhang, Chunyang Xie, Pengfei Li, Jieru Zhao, Wenchao Ding
Cryptography and Security
Accountability in Certificate Transparency and Variants
Timo Treitz and Robert Künnemann
Certificate Transparency (CT) aims to reduce the trust required in Certificate Authorities (CAs) within the TLS certificate ecosystem. It is supported by all major browsers. The protocol obliges all CAs to record the certificates they issue in a public log, which itself is monitored for compliance and consistency by third parties. Given this complex set of checks between the four roles-CA, loggers, monitor but also the end user's client-it is very hard to provide a precise account of how CT eliminates trust assumptions in exchange for complex infrastructure. Analyses both in the Dolev-Yao paradigm and the computational paradigm only regard a very simplified model and feature definitions adapted specifically to CAs, essentially capturing design features rather than the target property. The present paper posits accountability as the main goal of CT and presents a thorough analysis in the Dolev-Yao model. We start with the vanilla PKI and, step by step, move to CT, finally analyzing proposed extensions for SCT
Auditing and Gossiping. We show that plain CT relies on an honest log, but provides accountability under this assumption. Furthermore, we show that the SCT
Auditing extension can eliminate this assumption, while the Gossiping extension cannot.
Read the full abstract ▾
Computer Vision
A Comparative Evaluation of Pre-trained Convolutional Neural Networks for Melanoma Detection
Wagner Moreno Schmitz, Marco Antonio de Castro Barbosa, Thiago Magalhães Amaral et al. (+2 more)
Early diagnosis of melanoma is critical for improving patient survival rates. However, accurately distinguishing melanoma from other skin lesions remains a significant clinical challenge due to the high visual similarity among lesion types and variability in image acquisition conditions. Artificial intelligence, particularly machine learning, has emerged as a promising tool to support dermatological diagnosis by automating feature extraction from medical images. Among the available approaches, convolutional neural networks (CNNs) have demonstrated strong performance in image classification tasks, making them well-suited for analyzing both dermatoscopic and histopathological images, given their ability to capture hierarchical visual patterns relevant to lesion characterization. Nevertheless, despite numerous pre-trained CNN architectures having been proposed, selecting the most appropriate one for a given imaging modality remains an open challenge. In this study, we evaluate pre-trained convolutional neural networks (CNNs) for skin lesion classification using dermatoscopic and histopathological image
datasets. Experiments were conducted on the HAM10000, ISIC 2018, and CR-AI4SkIN
datasets, evaluating the ResNet50, VGG16, VGG19, MobileNet, and InceptionV3 architectures under the same training protocol. The experimental evaluation showed that the models achieved accuracies ranging from 71% (InceptionV3 on ISIC 2018) to 84% (ResNet50 on HAM10000) on dermatoscopic images. For histopathological images, accuracies ranged from 72% (VGG19) to 83% (ResNet50) on the CR-AI4SkIN
dataset. The results demonstrate that model performance differs between dermatoscopic and histopathological image modalities, showing that architectures exhibiting similar performance on dermatoscopic images exhibit different performance on histopathological data.
Read the full abstract ▾
All authors Wagner Moreno Schmitz, Marco Antonio de Castro Barbosa, Thiago Magalhães Amaral, Dalcimar Casanova, Jefferson Tales Oliva
Robotics
Using Automated Vehicles Operational Data to Confirm Safety and Anticipate Threats
Riccardo Donà, Espedito Rusciano, Germana Trentadue et al. (+2 more)
European Union (EU) policymakers adopted revolutionary data collection provisions for Automated Driving Systems (ADS) in the recently approved regulation that allows driverless vehicles to be operated on public roads. The framework is inspired by best practices developed at the United Nations Economic Commission for Europe(UNECE) level: the In-Service Monitoring and Reporting (ISMR); and by similar operational data collection regulatory approaches in
nuclear energy production and transportation fields. The collection of real-world data will enable the competent safety authorities to gather the information needed to confirm the homologation safety target. Safety-relevant driving scenarios discovered during the real-world operation of a given ADS can also be stored in a scenario catalogue to investigate how other ADS types might have addressed such a traffic conflict. Moreover, lessons learnt deriving from the data collected can be shared among original equipment manufacturers (OEMs) and safety authorities. Ultimately, the ISMR is recognised as a necessary tool to properly tackle the challenges associated with ADS safety assessment given the number of unknowns that might remain undisclosed by leveraging the traditional homologation validation scheme only.
Read the full abstract ▾
All authors Riccardo Donà, Espedito Rusciano, Germana Trentadue, Anastasios Tsakalidis, Maria Cristina Galassi
Computer Vision
World in World: Explore the World with World Models
Chenxi Song, Yanming Yang and Chi Zhang
Autoregressive
video world models enable interactive, long-horizon exploration, but flexible control remains challenging. Exploring a source
video from new viewpoints requires the generated rollout to remain synchronised with the recorded event, place observed content in the requested view, plausibly complete newly exposed regions, and recover previously generated appearance on revisits. Existing methods typically address these requirements through task-specific modules or additional training. We present World in World, a training-free inference-time interface that converts heterogeneous control evidence into camera- and time-labelled clean visual states, which are read through the native self
attention of a frozen causal
video model. The evidence comprises source-
video observations, target-view scene projections, geometry renderings that guide completion of newly exposed subject regions, and retrieved generated states beyond the rolling cache. Each evidence source carries
token-level support and its own availability schedule. A correspondence router combines persistent point identities with geometry to establish
token correspondences, guiding supported queries towards matching source-
video tokens. Evidence-wise
attention CFG (EWA) then independently regulates each auxiliary channel's additional contribution using
attention responses from the same denoising forward pass. The shared interface supports camera-controlled rerendering, long-horizon revisiting, and human-motion transfer with the same frozen backbone. We evaluate World in World on camera-controlled
video rerendering under diverse viewpoint changes, assessing perceptual quality, temporal consistency, and camera-following accuracy.
Read the full abstract ▾
Computation and Language
Complex-Text Robustness Evaluation and Failure Diagnosis for Low-Resource Multilingual Text-to-Speech
Tianlun Zuo, Ziyu Zhang, Tingzhi Mao et al. (+2 more)
Low-resource
multilingual text-to-
speech (TTS) systems have expanded
language coverage, but their robustness under complex text inputs remains insufficiently diagnosed. Existing evaluations mainly focus on naturalness, speaker similarity, and content consistency using regular test sentences, while providing limited insight into how
multilingual TTS systems fail when handling challenging inputs such as numbers, dates, named entities, long sentences, code-switched expressions, and punctuation-related structures. This paper proposes a complex-text robustness diagnosis framework for low-resource
multilingual TTS. We evaluate robustness from three dimensions: content consistency,
language consistency, and generation stability. A
multilingual robustness testing scheme is designed for Thai, Vietnamese, Swahili, and Indonesian, covering ordinary sentences and multiple types of complex text inputs. We further introduce automatic diagnostic metrics, including character error rate,
language identification accuracy, and duration abnormal rate. To support input-level risk analysis before
speech generation, we propose a lightweight Text Risk Score (TRS), which estimates synthesis risk from interpretable text features without manual annotation or model training. Experiments on three representative
multilingual TTS systems, including OmniVoice, VoxCPM2, and MMS-TTS, show that complex text inputs expose systematic failure patterns that are not fully reflected by ordinary short-sentence evaluation. Different systems exhibit distinct vulnerabilities in number normalization, named entity handling, long-text generation, and code-switched input processing. Furthermore, TRS shows a positive correlation with content errors and duration abnormalities, demonstrating its usefulness as a low-cost pre-synthesis indicator for complex-text risk diagnosis in low-resource
multilingual TTS.
Read the full abstract ▾
All authors Tianlun Zuo, Ziyu Zhang, Tingzhi Mao, Zhonghua Fu, Lei Xie
Artificial Intelligence
Characterizing Job Power Elasticity for Power-Flexible AI Training
Philip Colangelo, Charles Dawson, Shayan Sengupta et al. (+2 more)
Large
language model (LLM) training is among the fastest-growing sources of electricity demand in modern data centers, and power availability is a primary bottleneck to continued AI infrastructure growth. Making the power consumption of these workloads flexible could unlock additional power for AI growth, limit increases in electricity prices, and improve the utilization of existing grid infrastructure. However, to realize this flexibility, we must first understand how the performance of training workloads changes when GPU power is reduced. This paper presents the first systematic characterization of job power elasticity (the sensitivity of throughput to power reductions) in LLM training. To quantify elasticity, we introduce the Power Flexibility Index (PFI), a normalized metric that quantifies the performance cost of power reductions and provides a control primitive for SLA-aware power flexibility. We collect data from 131 LLM training runs on H200 (plus 24 H200 validation runs and 34 matched H100 runs), including both dense and mixture-of-experts models, pretraining and fine-tuning tasks, and up to 32 GPUs. We find that LLM training jobs exhibit substantial but variable power elasticity, and we identify telemetry signals that predict PFI at runtime. Finally, we demonstrate that PFI-aware power allocation maximizes total
tokens/second throughput under power constraints. Under a 30% power reduction, PFI-aware power allocation recovers ~1.5k
tokens/s per job, 63% of the performance gap between an equal-weight allocation and an oracle with perfect information. Our results establish power elasticity as a measurable property of training jobs and provide a foundation for power-aware, grid-responsive AI infrastructure.
Read the full abstract ▾
All authors Philip Colangelo, Charles Dawson, Shayan Sengupta, Ayse Coskun, Varun Sivaram
Machine Learning
Particle GFlowNets: Rethinking Generative Marginalization Models
Tiago da Silva, Diego Mesquita and Salem Lahlou
Generative Marginalization Models (MaMs) have been recently introduced as efficient neural sampling models for any-order autoregressive modelling of discrete distributions. By learning both the marginal and conditional probabilities of a persistent-block Gibbs sampler, MaMs enable fast posterior evaluation with a single neural network forward pass. While prior work has considered MaMs to be distinct from Generative Flow Networks (GFlowNets), a well-established paradigm for inference in discrete
stochastic models, we show that they are equivalent. Then, we also extend MaMs' sampling strategy to non-autoregressive generative processes. In particular, we describe an automatic criterion for full-state rejuvenation of the Gibbs sampler, derived from the Gelman-Rubin statistic, which plays a key role in speeding up learning convergence. Our experiments show that our method, called Particle GFlowNets, markedly accelerates training in large combinatorial spaces.
Read the full abstract ▾
Cryptography and Security
On Identifying Sound Conditions for Frontrunning Resistance
Sebastian Holler, Anna Piscitelli, Jannik Albrecht et al. (+3 more)
Blockchains enable decentralized applications through smart contracts—interactive programs executed through consensus. However, the inherently asynchronous nature of blockchain transaction ordering introduces a class of vulnerabilities known as frontrunning attacks, which have caused millions of dollars in losses in major blockchains, such as Ethereum. Frontrunning attacks arise because users interact with smart contracts through transactions, which are added to the blockchain by designated nodes called miners. Miners can exploit their ability to reorder, delay, or insert transactions to gain an advantage over honest users, effectively frontrunning them. Yet, to date, the field lacks a rigorous definition of what it even means for a contract to resist such attacks. Worse, we show that existing dynamic detection approaches are fundamentally inadequate: in a large-scale study comprising 287 smart contract audits, 55% of the 393 reported vulnerabilities identified by leading smart contract auditors fall outside the scope of state-of-the-art detection criteria. To address this gap, we propose the first formal definition of frontrunning vulnerability for smart contracts. Our definition captures a key insight: resistance to frontrunning is not an intrinsic property of a contract alone, but depends critically on how honest users interact with it. Grounded in this observation, we develop a sound
algorithm for synthesizing secure interaction conditions, alongside a prototype implementation that we apply to audited real-world contracts—revealing previously undiscovered vulnerabilities in two Ethereum contracts.
Read the full abstract ▾
All authors Sebastian Holler, Anna Piscitelli, Jannik Albrecht, Stephan Dübler, Ghassan Karame, Clara Schneidewind
Artificial Intelligence
Prompt Revision as a Source of Cultural Bias in Text-to-Image Systems
Aleksandra Urman, Elsa Lichtenegger, Salima Jaoua et al. (+7 more)
Commercial text-to-image systems silently revise user
prompts before generating images, a step users typically cannot disable or even see. Yet, existing audits of cultural bias examine only the final images and treat generation as a single pipeline, so they cannot tell where the bias originates. We introduce WORLDVIEW, a
multilingual benchmark of 8,960
prompts across 15
languages and 31
language-context pairings. Using it, we audit the revision layer in three systems (DALL-E-3, Imagen-4, GPT-Image-1.5) through a three-step analysis of how heavily it marks each cultural context, whether it flattens that context into a narrow vocabulary, and whether that vocabulary is stereotypical. Relative to a no-context English baseline, the US is the least-marked context, while non-Western and non-Anglophone contexts are marked far more heavily, flattened into narrow vocabularies applied across topically diverse
prompts, and reduced to recognizable cultural stereotypes. Comparing images from original versus revised
prompts on models without a revision layer, we identify the layer itself as a previously undocumented, causal source of this stereotyping. To locate cultural bias, and fix it, we must audit the system as deployed, not the model alone.
Read the full abstract ▾
All authors Aleksandra Urman, Elsa Lichtenegger, Salima Jaoua, Azza Bouleimen, Robin Forsberg, Corinna Hertweck, Stefania Ionescu, Nicolò Pagan, Ancsa Hannak, Joachim Baumann