Networking
The OCUDU dApp Platform: An Open Runtime and E3 Interface for Real-Time AI-RAN
Timothy O'Shea, Matthew Pennybacker and Andriy Kharchenko
Machine learning has shown its largest gains in the band below 10 ms inside a 3GPP new
radio (NR) 5G distributed unit (DU): link adaptation, per-slot scheduling, channel estimation, and the receiver itself. No open platform has let independently built software run there. Prior dApp frameworks reached the band only as external observers of an export stream. This paper is a guided introduction to the OCUDU dApp platform, an open runtime and E3 interface under which signed AI-RAN applications execute inside a production DU under three timing contracts: resident on the GPU receive chain (Class A), inside the scheduler's 100 us admitted deadline (Class B), or as never-blocking observers whose results the scheduler consumes (Class C). The conventional path is never displaced, and every authority is typed, validated, and operator-bounded. The paper explains how the runtime, the embedded E3
agent, and the three public repositories fit together; shows a dApp's source, its signed package, and its lifecycle state machine; defines the contracts a module is written against; and shows how one management surface serves a Python script, an operator's console, and an LLM
agent. On a GB10 gNB with attached handsets, dApps of all three classes, including an out-of-tree neural equalizer, ran together on a live
cell without a single fallback, and equalizer variants were compared over the air by lifecycle operations alone. Every measured checkpoint is reported with its conditions and its gaps. Platform, SDK, and a zero-hardware quickstart are public under BSD-3-Clause-Clear as a preview release of the OCUDU AI-RAN Working Group 2, inviting feedback, new use cases, and independent vetting ahead of upstreaming into the OCUDU mainline.
Read the full abstract ▾
Robotics
ComVLA: Communication-Aware Split Inference for VLA Models in 6G-Connected Robotics
Boliang Liu, Wint Yi Poe, Jingyun Di et al. (+2 more)
Connected robotics is an emerging 6G application where mobile
robots follow natural-
language instructions to manipulate physical objects. The
Vision-
Language-Action (VLA) models that enable this are too large to run on the
robot; a common trend is to offload inference to the cloud. The wireless link, however, limits how much sensing data the edge can transmit per control step. Two recent lines address this constraint: semantic communication codecs compress sensor data but require channel-specific retraining, and VLA
token pruners select
tokens from image but ignore the channel. Our insight is that the dense semantic information contained in the
language already indicates which visual
tokens matter. We propose ComVLA, a framework that uses this
language guidance to adapt the VLA
token budget to the channel capacity. Transmitting 32
tokens instead of 512 on the LIBERO
benchmark, ComVLA cuts inference compute by 74% and inference latency by 22% versus the original OpenVLA-OFT baseline, at a cost of 1.5 pp in average task success (95.4% vs. 96.9%), and it stays within the capacity budget under Rayleigh and Rician fading. These results demonstrate that co-designing VLA inference and wireless communication is a practical direction for 6G-connected robotics.
Read the full abstract ▾
All authors Boliang Liu, Wint Yi Poe, Jingyun Di, Riccardo Trivisonno, Giuseppe Caire
Computer Vision · Cross-listed from astro-ph.IM
Neural Posterior Estimation for Tomographic Weak Lensing Mass Mapping
Tim White, Shreyas Chandrashekaran, Camille Avestruz et al. (+2 more)
Weak gravitational
lensing shear and convergence trace the distribution of baryonic and dark matter across space, making them a powerful probe of
cosmic structure. Inferring shear and convergence from images is a challenging inverse problem. The prevailing approach to this task estimates shear from weighted averages of
galaxy ellipticities, calibrates these estimates to account for systematic biases, and transforms them to reconstruct convergence, a multistage procedure that requires substantial computational resources and meticulous handling of statistical uncertainties. As an alternative, we propose a probabilistic approach to field-level weak
lensing inference in which we train a deep neural network to directly map a multiband image to a variational distribution over the underlying tomographic shear and convergence fields. This neural posterior estimation (NPE) procedure implicitly marginalizes over nuisance variables in the cosmological forward model and does not require evaluating the likelihood function. It is also amortized, so it enables rapid posterior inference for astronomical surveys once the neural network is trained. When evaluated on synthetic images from the LSST-DESC DC2 Simulated Sky Survey, NPE produces well-calibrated variational distributions for shear and convergence that are consistent with the ground truth. We describe how maps sampled from these variational distributions could be used in a subsequent simulation-based inference procedure to approximate the posterior distribution over cosmological parameters.
Read the full abstract ▾
All authors Tim White, Shreyas Chandrashekaran, Camille Avestruz, Jeffrey Regier, the LSST Dark Energy Science Collaboration
Computational Geometry · Cross-listed from math.MG
An explicit mono-monostatic polyhedron
Tancredi Schettini Gherardini
A convex body is mono-monostatic if, resting under
gravity on a horizontal plane, it has exactly one stable and one unstable
equilibrium position. Smooth mono-monostatic homogeneous bodies exist (the Gömböc of Domokos and Várkonyi), and Lángi proved that (homogeneous) mono-monostatic polyhedra exist; although no explicit example appears to have been published, to the author's knowledge. We construct explicitly two such mono-monostatic polytopes, the smaller one having $56946$ faces; importantly, we certify them: the polytope is presented as an intersection of half-spaces with rational data, and a certifying verification establishes, using exact rational arithmetic for every decisive comparison, that the body has
equilibrium signature $(S,H,U)=(1,0,1)$ with respect to its own exact centroid, with explicit nondegeneracy margins. We describe the
geometric obstructions that make naive discretisations of smooth mono-monostatic bodies fail, the adaptive construction that overcomes them, and the certification strategy. While the result itself is not strikingly novel, we emphasise the non-standard (but increasingly more common) methodology: the entire programme, i.e. experiments, constructions and the verifier itself, was implemented by AI
agents under human mathematical direction. We argue that exact certification of numerically discovered objects is the natural contract between such AI-assisted workflows and mathematical standards of rigour.
Read the full abstract ▾
Computer Vision
SAFIRE: Safety-Critical Benchmark for Fine-grained Fire and Smoke Understanding in Multimodal LLMs
Pengfei Li, Naufal Suryanto, Sicheng Zhang et al. (+2 more)
Multimodal Large
Language Models (MLLMs) show strong progress on
vision-
language tasks, yet their reliability in safety-critical settings remains underexplored. Fire-smoke understanding is central to public safety and disaster response, but most existing
benchmarks lack diverse real-world scenarios and context-aware evaluation. We introduce SAFIRE, a large-scale
benchmark for fire-smoke understanding in MLLMs, comprising 83K captioned images from 20 scenarios and 193K multiple-choice VQA (MCVQA) generated from a 9.7K-image subset, spanning 10 evaluation dimensions from basic perception to higher-order
reasoning. A GPT-5.4-assisted multi-stage verification pipeline with MLLM majority voting ensures annotation quality. Evaluating ten open-source MLLMs (8B-38B) yields an average accuracy of 61.9%, exposing major gaps in safety-critical
reasoning. We further show that adapting
vision encoders with only 7% of our domain-specific data boosts fire-scene classification accuracy from 20.1% to 64.5%, indicating that carefully curated data can yield substantial gains even when data volume is limited. All
datasets, models, and code are available at https://risys-lab.github.io/SAFIRE/.
Read the full abstract ▾
All authors Pengfei Li, Naufal Suryanto, Sicheng Zhang, Mohammad Alsharid, Muzammal Naseer
Computation and Language
A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM
Xiaoang Xu, Siyuan Liu, Shuo Wang et al. (+13 more)
Chain-of-Thought (CoT) improves the
reasoning ability of Large
Language Models (LLMs) but incurs substantial computation and context costs. Existing methods either lose intermediate information through hard
pruning or lack a principled criterion for continuous compression. We present A*-Thought-V2, a
geometric dynamics of LLM guided framework that models CoT as a hidden-state trajectory and replaces hard deletion with an explicit-implicit interleaved latent architecture. After projecting question, step, and solution representations into a 3D PCA space, it measures
alignment between each local transition and global question-to-solution direction. Aligned steps remain explicit text, whereas deviating steps are compressed into continuous latent
tokens. Directional angles capture both local semantics and
reasoning dynamics: small angles indicate direct execution and answer formation, while large angles more frequently involve checking, correction, and branch exploration; their temporal variation reveals exploration, convergence, and refinement stages. To train this architecture, we introduce stepwise
embedding forcing, which pools each redundant step into a single latent
embedding, and label forcing, which supervises that latent
token with a soft multi-modal vocabulary distribution instead of a hard one-hot label. Experiments on Qwen3.5-9B and Qwen3.6-27B across six in-domain and out-of-domain
benchmarks show that A*-Thought-V2 improves average accuracy by up to 2.6% while reducing response length by up to half, increasing Accuracy per Computation Unit by 2.29$\times$, and reducing preprocessing and training time by 94.6% and up to 80.3%, respectively. Representation analyses suggest that latent states form a compact region distinct from textual states, while higher
entropy at latent-
token positions reflects broader soft targets that encourage richer step-level feature learning.
Read the full abstract ▾
All authors Xiaoang Xu, Siyuan Liu, Shuo Wang, Junlan Feng, Fanyu Meng, Zhu Zhang, Jixun Wang, Xiaorong Wang, Zihan Zhou, Xin Li, Chaojun Xiao, Yiming Zhang, Huijia Wu, Liuyu Xiang, Peipei Li, Zhaofeng He
Machine Learning
Kalman Delta Networks: Uncertainty-aware Associative Memory
Ngoc Bui, Tinglin Huang and Rex Ying
Linear
attention enables efficient long-context inference by compressing
token history into a fixed-size recurrent
memory. This compression makes each update a trade-off between incorporating new information and preserving useful associations. Models such as DeltaNet, Gated DeltaNet, and KDA predict write strength from the current
token representation, without explicitly tracking uncertainty in the stored
memory. Yet this uncertainty matters: a new observation should have greater influence when the existing association is uncertain and less when it is already well supported. We introduce Kalman Delta Networks (KDNs), a family of linear-
attention models that explicitly track
memory uncertainty to guide each update. By formulating associative
memory as a linear-Gaussian state-space model, KDNs propagate both the
memory estimate and its uncertainty, using the Kalman gain to balance accumulated evidence against the reliability of new observations. This formulation also recovers standard delta-rule updates by replacing tracked covariance with a
token-predicted isotropic surrogate. To support hardware-efficient training and inference, we derive Diagonal KDN and Isotropic KDN, which retain one uncertainty value per key channel and per head, respectively. Their uncertainty updates admit associative scans with logarithmic parallel depth, requiring only $O(d_k)$ and $O(1)$ auxiliary state per head. Across controlled pretraining at 750M and 1.3B parameters, both variants consistently improve perplexity and mean downstream accuracy over the evaluated state-of-the-art linear-
attention baselines.
Read the full abstract ▾
Computer Vision
Jingxiang Sun, Chao Liao, Zhengxiong Luo et al. (+6 more)
Current text-to-image systems typically employ a "text encoder plus
diffusion decoder" paradigm, in which text semantics directly modulate continuous latent noise. Despite their success, these methods lack an explicit, interpretable intermediate representation that effectively bridges high-level linguistic semantics and low-level visual signals. In this paper, we propose
Vision-of-Thought (VoT), a framework that introduces a discrete visual-thinking layer between
vision-
language models (VLMs) and
diffusion transformers (DiTs). Instead of treating VLMs merely as text encoders, we use them as
multimodal planners that generate discrete VoT
tokens representing high-level visual plans, such as objects and layouts, before rendering pixels. We train a specialized VoT tokenizer in the VLM semantic space with a closed-loop objective that combines VLM
alignment, feature reconstruction, and vector-quantization losses. These objectives make the
tokens semantically readable by the VLM while preserving the visual information needed for generation. Experimental results demonstrate that VoT improves semantic
alignment and provides a structured interface for interpretable and controllable generation.
Read the full abstract ▾
All authors Jingxiang Sun, Chao Liao, Zhengxiong Luo, Chaorui Deng, Chen-lin Zhang, Junke Wang, Ceyuan Yang, Haoqi Fan, Weilin Huang
Machine Learning
Latent-MoE: Domain-Aware Mixture-of-Experts for PDEs with Multi-Regime Physics
Hanwen Wang and Paris Perdikaris
Physics-informed neural networks (PINNs) struggle on PDEs whose governing physics varies across the domain. We trace this to a structural property of standard coordinate networks: their neural tangent kernel (NTK) is translation-variant and lets training points of large coordinate magnitude disproportionately influence predictions elsewhere, producing long-range coupling and gradient conflict during training. We show analytically and empirically that mixture-of-experts (MoE) architectures with centered, compact-support routers yield a uniformly banded NTK whose kernel-regression weights decay exponentially with distance, localizing the learning. Building on this, we propose Latent-MoE, which interleaves domain-aware MoE blocks within a shared backbone. Unlike FB-PINNs or X-PINNs, which rigidly partition both the domain and the parameters so that the parameters on different subdomains are updated independently, Latent-MoE is designed to preserve the localization benefit of domain-aware routing while allowing capacity to flow across regions through the shared backbone. On standard homogeneous-physics
benchmarks Latent-MoE is competitive with established baselines; on
benchmarks with multi-stage time-variable physics, where global models and rigid domain decompositions both fall into spurious solutions, it improves over them by more than an order of magnitude, with markedly reduced gradient conflict during training.
Read the full abstract ▾
Systems and Control · Cross-listed from math.OC
Configuration-Constrained Tube MPC for Difference-of-Convex Nonlinear Systems
Filippo Badalamenti, Jose A. Borja-Conde, Filiberto Fele et al. (+2 more)
This paper develops a convex tube model predictive control formulation for constrained nonlinear systems. We consider dynamics described by a discrete-time state-space model with parametric and additive uncertainty that admits a difference-of-convex decomposition. Convex directional bounds of the nonlinear dynamics are combined with configuration-constrained polytopic tubes, whose predefined combinatorial structure yields an affine parameterization of their vertices. The resulting finite-dimensional sufficient conditions certify robust one-step tube propagation under parametric uncertainty and additive disturbances, while allowing the tube geometry and an associated vertex control law to be optimized jointly in a single convex program. An implicit terminal condition guarantees recursive feasibility and convergence of the predicted tube to a target robust control invariant set. Numerical results illustrate the closed-loop properties and the trade-off between
geometric flexibility and computational complexity.
Read the full abstract ▾
All authors Filippo Badalamenti, Jose A. Borja-Conde, Filiberto Fele, Teodoro Alamo, Daniel Limon
Computation and Language
You Can't Prefer Emotions You Don't Sample: Intensity Undershoot in DPO-Tuned LLMs
Hyunwoo Kim and Usama Khalid
Ask a
language model to respond "very excitedly," and its output is typically only mildly more energetic. We quantify this effect. We condition an instruction-tuned LLM on a continuous Valence-Arousal (VA) target, where valence measures how pleasant a state is and arousal how activated it is, measure the achieved affect with a frozen regressor, and sweep the requested target from -1 to +1. The response moves far less than asked: the gain, the slope of achieved against requested affect, is only 0.26 for valence and 0.13 for arousal on Llama-3.1-8B, where a faithful controller would score 1. The model systematically undershoots requested emotional intensity, which puts a number on the qualitative observation of Fazzi et al. (2025). Our experiments trace this to the preference-learning pipeline. Training targets from natural corpora such as EmoBank are neutral-heavy, and the sampled candidates themselves rarely reach extreme affect, so Direct Preference Optimization (DPO) is left with no extreme exemplar to prefer. If instead we cover the target space uniformly and sample a hotter, larger candidate pool, valence gain rises from 0.26 to 0.40 +/- 0.02 (3 seeds) and extrapolation error drops, at only a modest in-distribution cost (EmoBank-test VA distance 0.092 to 0.107). The same recipe reproduces on Qwen3-8B (gain_v 0.44, with in-distribution accuracy preserved). Arousal is harder and less reliable: its gain barely moves on average and swings across seeds (0.14 +/- 0.07, against valence's tight +/- 0.02), because raising arousal needs candidates the base model is reluctant to generate. The evidence indicates that faithful intensity is bottlenecked by the extremity of the candidate pool rather than by the conditioning format.
Read the full abstract ▾
Networking
Real-Time dApps for AI-RAN: Measured Interface Requirements for Inline PHY and Slot-Level Control
Timothy O'Shea, Matthew Pennybacker and Andriy Kharchenko
Distributed applications (dApps) bring AI to the microsecond-to-millisecond band beside the 5G distributed unit (DU), but every public dApp framework realizes them the same way: an external process that receives an indication and returns a control message. That boundary is right for sensing and advisory workloads. It cannot express a neural receiver that must finish inside a slot, and it cannot hold a scheduling decision the MAC is waiting on. This paper asks what a dApp interface must deliver, in latency and bandwidth, for the AI-RAN use cases now filed under that name to be realized as dApps at all. It treats the coupling between a dApp and the DU as a design axis with two legitimate ends, a C ABI inside the DU process and a protocol-standard E3AP association over SCTP, and places the three OCUDU dApp classes on it. An audited corpus of 39 runtime AI-RAN use cases, sized by 5G NR timing, shows that more than half cannot cross the observer boundary: inline PHY work because an indication has no return path into the same slot, and bounded control because of the tail under load. Measuring the mechanisms each framework actually uses, on a quiet host and with a live
cell on the air, shows that every carrier meets a 100 us control deadline on an idle host and that only the in-process paths still do once the DU is running. The asynchronous use cases remain feasible at every position, so the protocol-standard end is kept as a first-class option; what in-process placement adds for them is accountable staleness and an observation-to-decision path with no message on it. These measurements derive the released ABI, a stream for inline work, a validated call for bounded control, and a choice of lease, supervised ring, or portable E3 client for observation, and four dApps of all three classes are validated together on one over-the-air
cell.
Read the full abstract ▾
Artificial Intelligence
Understanding the Impact of Model Pruning on Long-Tail Forgetting and Explanation Reliability in Medical Imaging
Nazish Khalid, Tausifa Jan Saleem, Amal Saqib et al. (+2 more)
Model
pruning is widely used to compress deep neural networks, reducing
memory and computational requirements with minimal impact on aggregate performance. However, its effect on model behavior remains poorly understood, particularly for long-tailed medical
datasets where rare but clinically important conditions are underrepresented. Furthermore, it remains unclear whether pruned models preserve reliable explanations of their predictions. To address this gap, we present a systematic study of long-tail forgetting and explanation reliability under model
pruning. Across two long-tailed medical imaging
datasets, two CNN architectures, four
pruning methods, and sparsity levels up to 95%, we evaluate predictive performance, explanation stability, and explanation faithfulness. Our results show that predictive performance exhibits a strong frequency-dependent trend, with lower-frequency classes generally experiencing earlier and larger degradation than higher-frequency classes. In contrast, explanation stability and faithfulness are influenced primarily by the
pruning strategy, with gradient-informed methods preserving explanation reliability more effectively under aggressive compression. Qualitative and mechanistic analyses further indicate that explanation degradation is primarily associated with the collapse of class-discriminative gradients rather than the disappearance of feature activations. These findings suggest that model compression should be evaluated beyond aggregate performance. Incorporating class-aware and explanation-aware evaluation reveals failure modes that would otherwise remain hidden, while moderate sparsity levels provide a practical balance between compression, predictive performance, and explanation reliability.
Read the full abstract ▾
All authors Nazish Khalid, Tausifa Jan Saleem, Amal Saqib, Donald C. Wunsch II, Mohammad Yaqub
Computation and Language
Climate-ModernBERT: Revisiting Corpus Composition for Domain-Adaptive Continued Pretraining
Yongan Yu, Shantam Raj, Jingwei Ni et al. (+3 more)
Natural
Language Processing (NLP) in the
climate domain requires models to process heterogeneous text sources, including scientific literature, policy disclosures, and synthetic reports. However, how to effectively combine diverse domain corpora during continued pretraining (CPT) remains underexplored. We introduce
Climate-ModernBERT, a family of
climate-adapted encoder models obtained through continued pretraining of ModernBERT-Base on three
climate corpora: academic
climate text,
climate-filtered web data, and synthetic
climate documents. We systematically compare joint continued pretraining on corpus mixtures with parameter-space merging of independently specialized checkpoints. Across nine
climate NLP
benchmarks, our best model achieves 76.3 average F_1, improving significantly over a vanilla ModernBERT baseline by 2.8 points. Within the
climate NLP setting, the results show that academic
climate corpora provide the strongest adaptation signal among the evaluated sources, while parameter-space merging improves over joint multi-source training and better preserves complementary information from heterogeneous
climate corpora. We release all
Climate-ModernBERT variants and training checkpoints to support future research in
climate NLP and domain-adaptive pretraining.
Read the full abstract ▾
All authors Yongan Yu, Shantam Raj, Jingwei Ni, Ario Saeid Vaghefi, Dominik Stammbach, Markus Leippold
Computation and Language
Does Syntax Matter? A Graph-Augmented Variational Topic Model for Computational Social Sciences
Alessandro Meneghini
Topic modeling is widely used in computational social sciences to identify latent themes in large text corpora. Traditional approaches rely on Bag-of-Words representations and generative models such as LDA, while recent methods like BERTopic operate on dense document
embeddings. This paper introduces the Structural Contextual Probabilistic Topic Model (SCPTM), an architecture that incorporates syntactic dependency relations into topic inference. SCPTM represents a corpus as a heterogeneous graph of documents and words connected by lexical and syntactic edges, processed through a Graph
Attention Network within a Variational Autoencoder to produce probabilistic, mixed-membership topic distributions. We evaluate seven topic modeling techniques (including four SCPTM ablations) across four corpora differing in register and discourse structure. Our framework combines coherence (C_V, C_NPMI), topic diversity, clustering-label
alignment (NMI), and phrase-level diagnostics (complementarity and valence gap). Results show that SCPTM's neural architecture yields substantial gains in document-topic
alignment over generative baselines, but these gains are attributable to the variational encoder rather than to syntax. Syntax contributes to topic diversity, where graph-augmented variants outperform the no-graph baseline across all corpora, and to descriptor quality: dependency paths capture predicate-argument structures and stance in deliberative registers, while proving redundant in technical and institutional corpora. The valence gap is positive across all variants, but driven primarily by phrase grouping rather than syntactic filtering. We conclude that syntactic encoding matters conditionally: it benefits action-oriented, argumentative texts, but introduces noise in informational or administrative registers.
Read the full abstract ▾
Human-Computer Interaction
Quantifying the Engagement Trap: Impact of Short-form Video Recommender Systems on Users with ADHD
Vedad Misirlic, Gregor Mayr and Elisabeth Lex
Short-form
video platforms use recommender systems to maximize engagement through highly efficient personalized recommendations. However, the impact of these recommendations on users with ADHD compared to users without ADHD remains underexplored. Through this study, we introduce and operationalize the Engagement Trap, illustrating how recommender systems, while successfully optimizing for engagement, disproportionately disadvantage users with ADHD. This stratified study of 302 participants, recruited via the online platform Prolific, compares experiences between participants with and without ADHD. Our results show that while recommendations are perceived as relevant across groups, participants with ADHD report significantly higher levels of time blindness, post-usage regret, and emotional distress when consuming recommendations. Moreover, we collect feedback for several proof-of- concept, theoretical design interventions for neuro-inclusive design principles. These findings provide quantitative evidence of systemic differences in engagement-optimized recommender systems and highlight the unbalanced negative effects and interactions these systems create for participants with ADHD. We argue for neurodiversity-aware, human-centered design approaches that mitigate such algorithmic harms and support more equitable experiences.
Read the full abstract ▾
Computation and Language
LLM Agents as Computational Typologists
Changbing Yang, Christopher Hammerly, Freda Shi et al. (+1 more)
Linguistic typology relies on expert analysis of reference grammars across
languages, making large-scale crosslinguistic comparison labor-intensive and unscalable. We introduce AUTOTYPOLOGIST, an LLM
agent for evidence-grounded typological analysis over reference grammars. The
agent is capable of retrieving relevant grammar sections, analyzing interlinear glossed text (IGT), and iteratively
reasoning over typological hypotheses using a ReAct-style workflow. We evaluate the system on TYPOLOGICAL FEATURE CODING against expert annotations and TYPOLOGICAL HYPOTHESIS TESTING with typological universals using 25 open-source reference grammars. Operating under different information constraints in TYPOLOGICAL FEATURE CODING, the
agent can synthesize information from reference grammar prose but still faces challenges with only IGTs in the target
language. In TYPOLOGICAL HYPOTHESIS TESTING, the
agent can synthesize crosslinguistic evidence and identify both supporting cases and counterexamples. These findings suggest that LLM
agents can support scalable and inspectable typological analysis, while still requiring expert validation.
Read the full abstract ▾
All authors Changbing Yang, Christopher Hammerly, Freda Shi, Jian Zhu
Computation and Language
Signed Rescue Routing: Harm-Aware Cascades for Efficient LLM Inference
Zheyuan Wang, Siyu Li, Peiqiao Song et al. (+3 more)
Large
language model (LLM) cascades answer easy requests with a small model and escalate selected requests to a larger model. Most routers prioritize examples on which the small model appears uncertain or likely to be wrong. This proxy ignores a decisive fact: escalation is useful only when the large model corrects the small model, and it is harmful when the large model replaces a correct answer with an incorrect one. We introduce Signed Rescue Routing (SRR), a budgeted routing method that predicts these two events separately and ranks requests by their difference. We show that this signed conditional gain is the Bayes-optimal routing score under a fixed escalation budget. SRR requires only the small model's output statistics at deployment and adds a lightweight two-head router. We evaluate SRR with Qwen3-4B and Qwen3-8B on TBD examples from MMLU, HellaSwag, and ARC-Challenge. Across the accuracy-compute curve, SRR reaches an area of TBD, compared with TBD for a learned small-model error predictor and TBD for
entropy routing. These results show that predicting incremental value, rather than model uncertainty, is a simple and effective objective for efficient LLM cascades.
Read the full abstract ▾
All authors Zheyuan Wang, Siyu Li, Peiqiao Song, Sijia Chen, Qianqian Song, Qian Liu
Artificial Intelligence
What Does an LLM-Agent Leaderboard Rank Actually Compare?
Wei-Jung Huang
An LLM-
agent leaderboard invites a familiar inference: an
agent ranked above another is the better
agent. Public evaluation logs may not support that conclusion when systems differ in task mixture, label source, release detail, or cost rule. We study what leaderboard scores estimate and when they justify pairwise superiority conclusions. Our estimand-aware pairwise procedure states the comparison target and measurement source, checks common support, and evaluates the supported difference using a stated uncertainty rule and practical margin. Controlled checks evaluate the decision labels under known finite-sample conditions and show why uncertainty must be included when judging sensitivity to target reweighting. Across SWE-bench, AgentRewardBench, and tau2-bench, close rank differences are often unresolved; proxy labels and utility rules can also change which system is selected. DataAgentBench and Open
Agent show what remains estimable from coarser public records. A leaderboard score summarizes a released evaluation, whereas a fine-grained superiority claim additionally depends on the estimand and uncertainty rule used to interpret the difference.
Read the full abstract ▾
Artificial Intelligence
xDailyBench: Benchmarking LLMs on Professional Consultation for Real-Life Problems
Yongchang Peng, Qingshui Gu, Liya Zhu et al. (+31 more)
Large
language models (LLMs) are increasingly used for everyday assistance, yet existing
benchmarks only partially reflect the requests users naturally make in practice. Real-world requests are often open-ended, casually specified, and context-dependent, requiring models not only to follow explicit instructions but also to infer unstated needs from user background and situational context. We introduce xDailyBench, a
benchmark of 248 carefully curated tasks spanning 51 scenarios across personal life, white-collar work, learning and research, and cross-domain activities. The tasks are grounded in requests that users have actually completed or genuinely intended to accomplish with AI, and are evaluated with fine-grained binary rubrics covering both explicit and implicit requirements. We evaluate 11 frontier models under standardized agentic settings. The best models achieve a task-level score of 75.6%, while all models perform substantially worse on implicit than explicit requirements, with gaps no less than 9 percentage points. These results reveal implicit requirement inference as a persistent bottleneck for reliably satisfying real-world everyday user needs.
Read the full abstract ▾
All authors Yongchang Peng, Qingshui Gu, Liya Zhu, Ge Zhang, Duo Wang, Haodong Wang, Jingzhe Ding, Tianhao Yu, Letian Gao, Yongjie Zhong, Chaoxin Li, Zixin Su, Jinchao Tao, Xingyu Ma, Xin'ao Guo, Feng Tian, Shiyuan Dong, Xiaoyan He, Sen Liu, Xin Chen, Jiajun Li, Zejia Zhang, Xi Lin, Wen Zhang, Yi Zhu, Duju Zeng, Xiang Gao, Yunyang Wang, Jiahao Wang, Yujia Qin, Jiaheng Liu, Shen Yan, Xiaolong Chang, Wenhao Huang
Cryptography and Security
Grid Trouble in Paradise: Uncovering Vulnerable Distributed Energy Resources and Their Grid-Level Risks
Anna Raymaker, Samuel Talkington, Zeezoo Ryu et al. (+8 more)
Grid-connected
solar distributed energy resources (DERs), such as
solar inverters and monitoring platforms, have been deployed at unprecedented scale over the past few years, with global
solar capacity more than doubling since 2022. To support monitoring and control, many of these systems are Internet-connected and configured by installers or end users, yet the real-world scale of their Internet exposure and the implications for power grid operation remain poorly understood. In this paper, we present an Internet-scale evaluation of exposed and vulnerable
solar DER infrastructure, and assess the risk that compromised DERs can pose to energy grids. We develop a method for accurately identifying
solar DERs from Internet scanning data, and discover a diverse population of over 66,000 Internet-exposed
solar DERs. We detect that at least 10,000 of these DERs may have known CVEs, such as unauthenticated monitoring and control endpoints. To assess the risk that these vulnerable DERs pose to a power grid, we use an electric grid network for Oahu, Hawaii, established and used by the power system research community, and conduct a power system analysis. Our evaluation shows that by compromising exposed DERs, attackers can cause voltage and line flow violations across multiple locations in the Oahu network, resulting in a range of consequences from degraded power quality to damaged power system components to power outages. Ultimately, our work brings to light the emerging threat of grid-connected DERs, and provides directions for improving energy security.
Read the full abstract ▾
All authors Anna Raymaker, Samuel Talkington, Zeezoo Ryu, Richard Asiamah, Emad Abukhousa, Betelihem Ashebo, Animesh Chhotaray, Daniel K. Molzahn, Frank Li, Saman Zonouz, Raheem Beyah
Databases
TrajectoryDB: A New Database for Agent Trajectories
Yunjia Zheng and Juncheng Yang
AI
agents generate rich execution trajectories that capture their interactions with large
language models, tools, and external environments. These trajectories are increasingly valuable for downstream tasks such as
memory extraction, model fine-tuning, runtime optimization, and security and cost monitoring. Yet trajectory data today is fragmented across files, databases, and observability systems, with no persistent data management system designed around its unique structure and access patterns. We argue that trajectories should be treated as a distinct data type. A trajectory combines hierarchical execution structure, large volumes of text whose analysis often requires semantic
reasoning, and rich dependencies and lineage among events, intermediate states, and derived artifacts. These properties introduce new requirements throughout the data lifecycle. Ingestion must reconstruct and preserve execution structure and lineage; storage must efficiently organize large but highly redundant contexts while maintaining relationships among records; and query processing must jointly reason over structure, temporal order, semantics, and lineage. We therefore envision TrajectoryDB, a trajectory-native data management system that co-designs ingestion, storage, and query processing to efficiently manage and analyze
agent execution trajectories.
Read the full abstract ▾
Computer Vision
DroneGround: Open-Vocabulary Drone Payload Characterization Using Synthetic Data and Grounded Vision-Language Models
Ami Pandat, Rajasekhar Punna, Gopika Vinod et al. (+1 more)
Automated drone surveillance has become increasingly important for public safety, critical infrastructure protection,and restricted airspace monitoring. While existing
vision-based systems achieve strong performance for drone detection and tracking, reliable payload characterization remains highly challenging under long-range imaging conditions due to limited availability of annotated real-world
datasets, and substantial distribution shifts encountered during deployment. Existing approaches formulate payload characterization as a closed-set object detection problem, limiting their ability to recognize previously unseen payloads and generalize beyond the training distribution. To address these challenges, we generate a photorealistic synthetic drone-payload
dataset using Unreal Engine 5 and Cosys-AirSim and propose DroneGround: Grounded
Vision-
Language Payload Characterization, a two-stage framework for robust open-vocabulary payload analysis. DroneGround first employs a YOLO26s detector to localize drones and extract drone-centric image crops, followed by a LoRA-fine-tuned PaliGemma
vision-
language model that generates seman- tic descriptions of the detected drones and their attached payloads, enabling open-vocabulary payload characterization beyond predefined categories. An occlusion-based grounding module further provides interpretable payload localization by identifying image regions responsible for the generated descriptions. Extensive experiments on both synthetic and real-world drone imagery demonstrate that DroneGround substantially improves robustness under synthetic-to-real distribution shifts, outperforming a conventional closed-set payload detector by improving the F1-score from 82.5% to 96.3%, while achieving significantly better generalization to previously unseen payload categories (80.4%versus 42.7% F1).
Dataset and code will be released upon request.
Read the full abstract ▾
All authors Ami Pandat, Rajasekhar Punna, Gopika Vinod, Rohit Shukla
Software Engineering
Daria Voronkova, Ilya Trofimov, Anton Dmitriev et al. (+3 more)
As AI-code assistant tools become widespread, automatic assessment of the correctness of generated code becomes a significant challenge. Code LLMs are prone to
hallucinations, which may lead to code that does not solve the required problem, or even to code with severe security vulnerabilities. In this paper, we introduce CodeTD – the first approach to pre-execution assessment of code correctness based on topological data analysis (TDA) of Code LLMs'
attention maps. Our method quantifies
prompt-generation mismatch using topological patterns of
attention maps. We carry out experiments with common
benchmarks (HumanEval, MBPP, BigCodeBench, MultiPL-E), 5 programming
languages and 10 Code LLMs of size up to 34B parameters. The experimental results show that the proposed method outperforms recent baselines. Moreover, CodeTD is transferable between coding
benchmarks.
Read the full abstract ▾
All authors Daria Voronkova, Ilya Trofimov, Anton Dmitriev, Eduard Tulchinskii, Evgeny Burnaev, Serguei Barannikov
Systems and Control
Distributed Droop-Free Control of Grid-Forming Inverters with Dynamic Line and Load Modeling
Hiya Akhil Gada and Marija Ilic
Droop-free distributed control has emerged as a promising alternative to conventional linear droop control for coordinating inverter-based resources in AC microgrids. However, existing droop-free methods typically rely on quasi-steady state network models that neglect fast electromagnetic transients and assume a decoupled dependence of active and reactive power on frequency and voltage, respectively. In this paper, we propose a transient-aware droop-free distributed primary/secondary control framework for grid-forming (GFM) inverters. The control objective is to achieve proportional active and reactive power sharing, frequency regulation, and voltage regulation within prescribed bounds. The proposed approach incorporates dynamic models of network lines and loads into the control design, enabling accurate representation of transient behavior while capturing the coupled nature of power flow interactions. A gradient-based distributed control update is derived from an optimization formulation, in which voltage magnitude constraints are enforced through a projection operator. To validate the performance of the proposed control, real-time simulation studies are conducted on a four-inverter microgrid under load changes in both strong and weak grid conditions. The results demonstrate that the proposed method improves transient performance, particularly in weak grids, while preserving the same steady state operating conditions as existing QSS-based droop-free approaches.
Read the full abstract ▾
Hardware Architecture · Cross-listed from quant-ph
QROB: Quantifying Realization Overhead in Quantum Compilation via Reverse Construction
Jintao Li, Kaiqi Li, Rui Wang et al. (+7 more)
Quantum compilation reconciles a program's idealized interaction
topology with hardware locality constraints, yet evaluations at scale lack calibrated references for realization overhead. We present QROB, a scalable reverse-construction methodology that generates compilation instances backward from directly realizable configurations, retaining the inverse paths as feasible, compiler-independent references. QROB provides a common evaluation substrate for NISQ SWAP routing and fault-tolerant
lattice-surgery scheduling, while extending its reference-preserving principle to capacity-constrained
quantum memory-access scheduling. Across systems ranging from 9 to 156
qubits, evaluations highlight QROB's utility as both a diagnostic
benchmark and a data source. First, for compiler characterization, QROB reveals substantial realization gaps in existing tools, with NISQ compilers incurring up to 24.1x the reference SWAP cost and fault-tolerant compilers requiring up to 7.0x the reference makespan. Second, as a supervision source for data-driven compilation, a router trained on QROB references outperforms Qiskit SABRE on 84.8% of real-world application
circuits. Finally, on real hardware, QROB reference realizations achieve a median mirror-
circuit survival rate 1.65x that of full Qiskit O3 compilations across three 156-
qubit IBM Heron-r2 processors, demonstrating that closing algorithmic compilation gaps translates directly into physical fidelity gains.
Read the full abstract ▾
All authors Jintao Li, Kaiqi Li, Rui Wang, Yilun Zhao, Kaixuan Huang, Ying Wang, Jialin Zhang, Zheng-An Wang, Xiaoming Sun, Heng Fan
Numerical Analysis · Cross-listed from math.PR
Efficient computation of the asymptotics of extensive-rank HCIZ integrals
Antoine Maillard and Jean-Christophe Mourrat
We study the high-dimensional asymptotics of Harish-Chandra-Itzykson-Zuber (HCIZ) integrals in the extensive-rank regime. The limit of these integrals is governed by a one-dimensional boundary-value hydrodynamical problem originally derived by Matytsin (1994) and rigorously proved by Guionnet and Zeitouni (2002). Despite its wide-ranging applications, explicit solutions to this problem are known only in a few specific cases. In this work, we introduce an efficient numerical scheme based on a particle discretization and prove its convergence to the continuous boundary-value problem for generic boundary densities. We validate our approach against known analytical solutions and apply it to generic densities, uncovering interesting dynamical phenomena. The high-dimensional limit of HCIZ integrals appears in various contexts, from the large deviations of random
matrix spectra to the limiting free energy of disordered systems, high-dimensional statistics, and machine learning. As such, our contribution opens the way towards the numerical exploration of a wide range of high-dimensional models that were previously intractable.
Read the full abstract ▾
Information Theory
A Note on Binary Quadratic Systems and their relation to complexity theory
Gabriele Radici and Massimiliano Sala
Deciding whether a system of multivariate quadratic equations over $\mathbb F_2$ has a solution is a classical NP-complete problem, and remains so for square systems, with as many equations as variables. The hardness of this problem is one of the cornerstones of nowadays post-
quantum cryptography. Let $\MQ_0(n)$ and $\MQ_1(n)$ denote the sets of square quadratic systems in $n$ variables having respectively no solutions and exactly one solution. $\cup_{n\geq 2} \MQ_0(n)$ is a coNP-complete
language, while $\cup_{n\geq 2} \MQ_1(n)$ lies in DP. It is known that $\lim_{n\to \infty} |\MQ_1(n)|/|\MQ_0(n)|=1$. Here we prove the explicit finite-$n$ bounds \[ |\MQ_0(n)|<|\MQ_1(n)| \le \left(1+\frac{1}{2^n-1}\right)|\MQ_0(n)|, \] More generally, let $Q_d$ be the space of
polynomial functions $(\FF_2)^n\to\mathbb F_2$ of degree at most $d$, and let $\alpha_k$ count square systems in $(Q_d)^n$ having exactly $k$ solutions. Then \[ \alpha_0<\alpha_1 \le \left(1+\frac{1}{2^n-1}\right)\alpha_0\,, \qquad 2\le d\le n \,. \] The proof combines matroid and coding-theoretic methods. We interpret $(\FF_2)^n$ as the ground set of the evaluation matroid of $Q_d$, express $\alpha_0$ and $\alpha_1$ through characteristic
polynomials, and use a Whitney-type sign-reversing involution to show that the only terms that can push $\alpha_1-\alpha_0$ below $\alpha_1/2^n$ come from the elements of a matroid port. These are identified with minimal-support words of the Reed–Muller code $\RM(n-d-1,n)=\RM(d,n)^\perp$; the required estimate then follows from the MacWilliams identity, the minimum-distance bound $2^{d+1}$, and the even-weight structure of the code.
Read the full abstract ▾
Computation and Language
Bag of Tricks or Bag of Myths? Reducing Modeling Complexity with Task Knowledge in Explainable Suicide Risk Assessment
Shlok Shelat, Shrey Salvi, Souvik Roy et al. (+2 more)
Assessing suicide risk from social media text is a small-data, high-stakes setting requiring not only severity prediction but also supporting evidence and clinically relevant risk and protective factors. Yet common NLP techniques, including model scaling, synthetic data, loss reweighting, ensembling, and threshold tuning, are often applied without testing whether their gains hold up under severe class imbalance, coupled outputs, and limited author-level data. We study 1,635 clinician-annotated posts and audit 31 pre-specified techniques from 7 methodological families through roughly 300 controlled experiments on author-disjoint partitions. We found no prior audit of this playbook in this regime. The findings guide a task-grounded system for three outputs: 4-level suicide risk, evidence spans, and 24 clinical risk and protective factors. Only 5 of 31 comparisons produced reliable gains. We reformulate factor prediction as entailment between each post and its codebook definitions, using an architecturally diverse ensemble with class-balanced training and score rescaling. Risk predictions condition a 7-model evidence tagger ensemble; evidence restricts symbolic risk rules; and a difficult risk class is routed separately. The factor predictor remains independent because risk evidence provides no additional factor signal. We also correct a mismatch between validation scores used for threshold fitting and test-time ensemble scores through deployment-consistent calibration, yielding the largest improvement to the factor system. The final system achieves 0.8203 for risk, 0.7953 for evidence, and 0.7045 macro-F1 for factors, with a 0.7781 composite, ranking third among 53 teams. We call the underlying principle task-conditioned technique selection: retain techniques only when task-specific knowledge, structure, or empirical evidence justifies them.
Read the full abstract ▾
All authors Shlok Shelat, Shrey Salvi, Souvik Roy, Manas Gaur, Amit Sheth
Machine Learning · Cross-listed from eess.SP
Pre-Whitening and BCJR Posterior Distillation for Bi-LSTM Detection in Faster-than-Nyquist Signaling
Nurettin Safak, Osman Tokluoglu and Enver Cavus
Recurrent detectors such as bidirectional long short-term
memory (Bi-LSTM) networks are low-complexity alternatives to the optimal Bahl-Cocke-Jelinek-Raviv (BCJR) detector for faster-than-Nyquist (FTN) signaling. Motivated by convolutional detectors that build the intersymbol interference (ISI) structure into their architecture, we ask whether processing nested ISI windows in separate recurrent branches improves the bit error rate (BER) of a Bi-LSTM. Across roughly 260 controlled trainings it does not: at a matched parameter budget and a matched readout, the multi-window architecture never significantly beats a plain Bi-LSTM. Nested windowing is an invertible rearrangement that adds no information, extra branches only add bottlenecks, and a
distillation diagnostic shows the network is already near optimal for its window. The limitation is therefore the observation model, not the architecture. Keeping the architecture fixed, we pre-whiten the input, restoring the conditional independence that colored matched-filter noise violates, and distill the BCJR soft posterior into the network. With 3.4% more parameters this reaches 1.05 times the BCJR BER at a compression factor of 0.8 and 1.89 times at 0.7, improving to 1.47 times when the whitened window is widened. The 23.7% BER reduction at 0.8 requires an ill-conditioned ISI
matrix but is not monotone in the conditioning, and it holds across five independent noise realizations and a symbol-level McNemar test.
Read the full abstract ▾