Databases
The Case for Single-Version Concurrency Control in the Cloud
Lam-Duy Nguyen, Gabriel Haas, Muhammad El-Hindi et al. (+2 more)
Multi-version concurrency control (MVCC) has been the dominant concurrency protocol in modern database management systems (DBMSs). However, cloud-native HTAP architectures shift many of MVCC's traditional advantages from the primary transaction engine to the deployment architecture. Now, transactional and analytical processing are decoupled into loosely synchronized engines, while cloud deployment primitives provide the workload isolation required for this design. In this paper, we challenge the status quo, arguing that single-version concurrency control (SVCC) is better suited to cloud transaction processing than MVCC. Through a systematic analysis of MVCC's limitations, we show that SVCC avoids these shortcomings through a more lightweight and efficient design. Beyond arguing for a lighter transaction processing, we use this SVCC effort as a blueprint to advocate for a broader rethinking of cloud-native architectures and to outline a research roadmap to shape next-generation DBMSs.
Read the full abstract ▾
All authors Lam-Duy Nguyen, Gabriel Haas, Muhammad El-Hindi, Viktor Leis, Philip A. Bernstein
Systems and Control · Cross-listed from quant-ph
Quantum ordinal optimization under a fixed comparison budget
Hongyu Wu
Ordinal optimization selects designs that are good enough rather than optimal when evaluation is expensive and the budget is small. The
alignment probability measures the chance that the selected set contains at least a prescribed number of truly good designs. We formulate
quantum ordinal optimization as a class of problems that maximize this probability under a fixed oracle budget. We study exact, coherent pairwise comparisons with one selected design as a first instance, with the budget counted in comparison queries. For every classical comparison budget smaller than the number of designs, we prove that a knockout among uniformly sampled designs attains the optimum. The sample is drawn without replacement and contains one more design than the number of comparisons. For a uniformly random order, the selected design's rank has a
polynomial probability law. At the same comparison budget, the maximum
quantum degree is at most twice the classical maximum, a factor attained whenever there are more than twice as many designs as comparisons, so a
quantum algorithm can realize rank laws that no classical
algorithm with the same budget can. We determine the exact
quantum optimum with one comparison for every number of designs and every good-enough set. For selecting the best of n designs, the optimal success probability with one
quantum comparison is approximately 3.30/n for large n, compared with 2/n for one classical comparison. When the best design is sought, one
quantum comparison gives a higher
alignment probability than two classical comparisons whenever there are more than nine designs.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Inference on the Value of Policy Improvement in Adaptive Experiments
Justin Whitehouse, Emma Brunskill and Vasilis Syrgkanis
In this paper, we develop an asymptotically normal
estimator for the value of policy improvement (VPI) under adaptively collected data. This value, which is defined as the gap between the value of the best treatment policy in a class and that of a baseline policy, gauges whether or not it is worth deploying a personalized treatment policy. Building an
estimator for the VPI is naturally more difficult than estimating the value of a fixed policy. This is because, in addition to contending with the correlated data and decaying propensities associated with adaptive experiments, any
estimator must also handle the non-regularity, or lack of pathwise differentiability, of the underlying estimand when the optimal policy is non-unique. Our proposed
estimator works by sequentially fitting a weighted empirical welfare maximizing policy on historical data and then evaluating it using inverse propensity weighting on future samples. We neither assume that the optimal policy is unique nor make a margin assumption on the underlying heterogeneous treatment effects. A key difficulty in analyzing our
estimator is showing that the regret incurred through policy learning is asymptotically smaller than the standard error of the
estimator. We accomplish this by showing faster regret rates for policy learning under decaying propensities, which may be of independent interest. We not only evaluate the coverage of our
estimator on a mix of synthetic and semi-synthetic data, but also employ it to estimate the VPI in an adaptive experiment evaluating the efficacy of job assistance programs in Jordan due to Caria et al. Although our estimates are generally more conservative than their hierarchical
Bayesian analysis, which assumes that the optimal policy is unique, we still corroborate the benefits of personalization amongst Syrian refugees.
Read the full abstract ▾
Artificial Intelligence
Agent Sociodrama: Social-Dynamics-Guided Persona Recasting for LLM Agent Teams
Yirui Qi, Xiaoming Zhang and Jaehong Yoon
Large
language model (LLM)
agents are increasingly deployed as teams, yet they fail in characteristically social ways: information holders stay silent, dominant speakers anchor groups on wrong answers, and norm violations go unsanctioned. We present
Agent Sociodrama, a framework for modeling and validating evolving social dynamics in LLM
agent teams. Under fixed personas,
agents' emotional states and directed, asymmetric relationships are updated every round by a unified external LLM judge and shape their subsequent interactions. Across six LLM backbones and five social scenarios, we assess social fidelity through classical social-theory patterns and agreement with human judgments. The resulting trajectories exhibit structured social patterns and model-specific differences. We then introduce Trajectory-Guided Persona Recasting (TPR), which diagnoses group-dynamic failures from interaction transcripts and social trajectories and recasts
agent personas before rerunning the task. Across four collaborative
benchmarks, TPR improves performance from both heterogeneous and randomly initialized
agent persona compositions, yielding up to 83.3%p of accuracy improvement over the initial casting. On representative distributed-information cooperation and mixed-motive bargaining tasks, we outperform SOTOPIA and AgentVerse in three of four comparisons, by up to 37.5%p in Pareto rate. These results show that validated social trajectories provide actionable signals for repairing LLM
agent teams.
Read the full abstract ▾
Computer Vision
Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping
Songze Li, Haoming Gu, Ziyang Gong et al. (+11 more)
Vision-
language navigation requires
agents to follow natural-
language instructions to reach target locations, making high-quality
language supervision essential. Since human annotation is costly, prior work has explored scalable data synthesis methods. However, existing methods typically either use separate models for navigation and instruction generation or couple the two tasks through task-specific components; most also annotate the full trajectory corpus with a fixed model before updating, which can cause generated supervision to lag behind the evolving policy. Therefore, we introduce RSI-Nav, a data-centric recursive self-improvement framework for navigation via policy-synchronized
language-action dual bootstrapping, which unifies
vision-
language-to-action instruction following and
vision-action-to-
language instruction generation within a shared model. Specifically, after supervised fine-tuning establishes fundamental capabilities, RSI-Nav progressively processes unlabeled trajectories in small shards. The current model generates instructions for these trajectories, executes them to evaluate goal completion and path efficiency, retains qualified samples, and immediately updates itself before processing the next shard. This shard-wise update keeps newly generated supervision aligned with the evolving policy. We also incorporate spatial understanding data, since stronger spatial
reasoning benefits navigation. Extensive experiments show that RSI-Nav reaches 68.6% SR on R2R-CE and 72.4% SR on RxR-CE, while providing stronger instruction-generation utility and modestly improved spatial understanding after recursive
evolution.
Read the full abstract ▾
All authors Songze Li, Haoming Gu, Ziyang Gong, Zhitong Wang, Gengze Zhou, Zun Wang, Yuhan Zhu, Tianxiang Jiang, Juanzi Li, Qi Wu, Weinan Zhang, Yu Qiao, Wenwei Zhang, Yi Wang
Machine Learning
Heterogeneous Structured Pruning Under Resource Constraints for Hardware-Efficient Large Language Models
Cameron Barker, Andreas Paraskeva, Jan N. van Rijn et al. (+2 more)
Training-free
pruning removes weights from pretrained large
language models to reduce their deployment cost. However, existing approaches typically consider only the total number of retained weights. Consequently, their
pruning decisions do not account for how target hardware stores and processes those weights. These methods select a sparsity structure in advance and apply it uniformly to all projections, rather than accounting for how each structure trades
pruning error against latency and
memory across sublayers. We propose Heterogeneous Structured
Pruning (HSP), a hardware-aware
pruning framework that combines two components: (i) a heterogeneous search space of dense, unstructured, 2:4, block-sparse, and head / channel (H/C)
pruning options and (ii) structure-regularising constraints based on latency and
memory models. Our contribution generalises existing importance-based methods: a global solver selects one option per sublayer to minimise proxy
pruning loss under a resource budget, thereby assigning each projection a structure and density. We evaluate HSP on OPT and LLaMA models for an NVIDIA Jetson Orin Nano Super edge device, where it improves the quality-resource frontiers over training-free baselines. A project page and updated links for the related code is maintained at: cameronbarker.me/publications/hsp.
Read the full abstract ▾
All authors Cameron Barker, Andreas Paraskeva, Jan N. van Rijn, Elliot J. Crowley, Henry Gouk
Sound
FlowGRPO for Vocal Separation: From Reward Analysis to Reward Design
Lishi Zuo, Chong-Xin Gan, Zezhong Jin et al. (+3 more)
The Flow Matching objective supervises the velocity field at intermediate states, whereas waveform metrics are evaluated after decoding and may be non-differentiable. To align Flow Matching models with waveform-level and perceptual quality objectives during post-training, FlowGRPO optimizes their trajectories using endpoint rewards. In this work, we focus on music separation and use multi-resolution short-time
Fourier transform (MRSTFT), scale-invariant signal-to-distortion ratio (SI-SDR), and Virtual
Speech Quality Objective Listener (ViSQOL) as reward components. Before policy optimization, we analyze the relationship between data quality factors and the within-group gap between the maximum and mean rollout rewards for each component. This analysis motivates a revised ViSQOL reward that matches channel-wise root-mean-square (RMS) levels and evaluates the interval from the first to the last active frame, retaining inactive frames within that interval. We also apply a sample-quality filter based on predefined waveform checks. Together, the revised reward and quality filter enable FlowGRPO to improve the pretrained vocal separator in both separation performance and perceptual quality.
Read the full abstract ▾
All authors Lishi Zuo, Chong-Xin Gan, Zezhong Jin, Youzhi Tu, Man-Wai Mak, KongAik Lee
Machine Learning
Who Sets the Pace of Judge Hacking? Judge Capability versus the Policy-Judge Gap
Haosen Wang
Under GRPO against a frozen, reference-free LLM judge, RL exploits the judge's false positives. Does the policy-judge capability gap or the judge itself set how fast and how far? We train 0.5B and 1.5B Qwen2.5 policies on GSM8K against four judges at least as large, and the 1.5B policy also against one smaller judge. In a post-hoc analysis, judge acceptance rose, but no
cell of 12 gained more than 0.04 in seed-mean held-out greedy accuracy. A gold-reward control with the same recipe raised the 1.5B policy's accuracy by +0.054 (for the 0.5B policy, gold reward gave no detectable gain either). The depth of judge hacking tracks the judge: the plateau correlates with judge AUC (Spearman -0.69 over 12
cells), and within a family the larger judge is fooled less deeply. For the pace, two pre-specified pairs contradict the gap account: the
cell with the larger gap was fooled 3.5x sooner at the pre-specified threshold. With 12
cells, however, we cannot formally separate judge AUC from the gap for either endpoint. A blind test of step-0 predictors on three held-out judges was inconclusive. At 7-8B, judges from three families plateaued between 0.37 and 0.85.
Read the full abstract ▾
Data Structures and Algorithms
Exact and Asymptotic Analysis of Greedy Online Facility Assignment on Cycle Metrics
Md. Tanzeem Rahat, Md. Rawha Siddiqi Riad and Md. Manzurul Hasan
We identify the free-facility gaps of greedy online assignment on a cycle with the discrete additive coalescent and use this connection to determine the exact expected assignment cost. The cycle has circumference $n$, with one unit-capacity facility at each integer point and $n$ independent uniform arrivals. Each request is assigned immediately to a nearest free facility. The conditional one-step cost is the sum of squared gap lengths divided by $4n$. A uniform cyclic-order argument identifies the unordered gap process with additive coalescence. The classical Cayley-tree representation then reduces the accumulated cost to a two-vertex distance functional, yielding \[ G_n=\frac n4\sum_{d=0}^{n-1}\prod_{j=1}^{d}\left(1-\frac jn\right) \sim\frac14\sqrt{\frac\pi2}\,n^{3/2}. \] The formula requires a linear number of scalar recurrence steps to evaluate. We also obtain an asymptotic upper bound of $\pi\sqrt3/2$ on the ratio of expected greedy cost to expected offline optimum under this arrival model. An exact rational Bellman calculation shows that greedy is optimal for three facilities but exceeds the optimal online expected cost by $1/512$ for four facilities. Independent exact recurrences and finite tree enumeration provide reproducible checks of the analysis.
Read the full abstract ▾
Numerical Analysis
GPU-Accelerated Nested Schur-Complement Solvers for Atmospheric Flow Simulations Using Horizontally-Explicit, Vertically-Implicit Schemes and Discontinuous Galerkin Methods
Marco Artiano, Andrés Rueda-Ramírez, Oswald Knoth et al. (+2 more)
Horizontally explicit, vertically implicit (HEVI) time integration removes the acoustic time-step restriction imposed by fine vertical grids in nonhydrostatic atmospheric models, but requires fast solvers for the resulting vertical linear systems, especially on GPUs. We present GPU-accelerated nested Schur-complement solvers for these systems for a split-form discontinuous Galerkin spectral element method on Legendre-Gauss-Lobatto (LGL) nodes applied to the compressible Euler equations with
gravity. In time, we use a Rosenbrock-W method, a linearly implicit Runge-Kutta scheme that retains its order and stability with approximate Jacobians. This allows a sparse vertical Jacobian that captures vertical acoustic waves and
gravity on curvilinear meshes with orography and decouples into independent column systems. The solvers are nested: a global Schur complement (static condensation) exploits the LGL sparsity to condense each column onto a few element-edge unknowns, and a local Schur complement eliminates all variables but the vertical momentum within each element, exploiting that the pressure depends only on the potential-temperature density. We propose and analyze two condensation strategies, which lead to banded and block-tridiagonal reduced systems. The resulting HEVI schemes conserve total mass and potential-temperature density to round-off. The solvers are implemented for CPUs and GPUs in TrixiAtmo.jl, the atmospheric extension of Trixi.jl. We verify high-order convergence with linear inertia-
gravity waves in a 2D channel and demonstrate robustness on the sphere with the baroclinic instability, a mountain-induced baroclinic instability, and the DCMIP-2025 gap-flow and
vortex-shedding cases. For the baroclinic instability without orography, the scheme achieves 18.8 and 2.9 simulated years per day at 100 and 50 km resolution on one NVIDIA GH200 GPU in double precision.
Read the full abstract ▾
All authors Marco Artiano, Andrés Rueda-Ramírez, Oswald Knoth, Hendrik Ranocha, Gregor Gassner
Computation and Language
RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution
Fan Zhang, Hao Wu, Jinyang Wu et al. (+7 more)
Recent focus in agentic reinforcement learning (RL) seeks to improve credit assignment in long-horizon tasks. One promising direction combines reinforcement learning with verifiable rewards (RLVR) and on-policy self-
distillation (OPSD), integrating trajectory-level advantages with dense
token-level supervision. This line of work often conditions a teacher model on privileged context, such as agentic skills, to score
tokens generated by the student policy. Despite their progress, they largely overlook the on-policy
evolution of agentic skills and the reliability of teacher supervision. Towards this end, we introduce Recursive Self-Improving Policy Optimization (RSIPO), a self-evolving agentic RL framework that enables agentic skills and the policy model to co-evolve throughout the training process. Specifically, RSIPO enables the policy itself to extract skills from completed trajectories and explicitly optimizes its skill-generation capability through trajectory replay. It further employs empirical Bayes shrinkage to dynamically calibrate the student's trust in teacher scores, accounting for the fact that skill-enhanced teacher guidance can sometimes be less reliable. Experiments with Qwen-family models on embodied interaction and search-based agentic tasks demonstrate that RSIPO outperforms all the compared baseline approaches. With Qwen2.5-7B as the base model, RSIPO achieves an average success rate of 98.6% on ALFWorld, yielding absolute improvements of 2.5% and 17.4% over the second-best baseline and standard GRPO, respectively.
Read the full abstract ▾
All authors Fan Zhang, Hao Wu, Jinyang Wu, Hongyu Qu, Zheng Lian, Xiao Luo, Yefeng Zheng, Bo Zhang, Haoxuan Li, Pheng-Ann Heng
Robotics
Hand2Robot: Object-Centric 4D Hand Reconstruction from Human Demonstrations for Robotics
Zetao Du, Weiqing Wang, Hanbing Zhang et al. (+4 more)
Human demonstrations can capture task-relevant manipulation without using the target
robot, but the recorded hand motions cannot directly serve as
robot action supervision. Hand reconstruction and motion retargeting provide a direct route to such supervision, yet recovering hand motion alone does not ensure physically consistent hand-object interactions. To address this issue, we introduce Hand2
Robot, an object-centric 4D hand reconstruction framework for
robot policy post-training. Given
videos of humans performing the target task, Hand2
Robot extracts interaction clips, reconstructs object geometry, and generates
robot action supervision through hand-object interaction optimization and motion retargeting. For object tracking, we combine observation confidence with temporal motion constraints to select a globally consistent object pose trajectory from per-frame pose candidates. For hand refinement, we use object geometry and motion as a reference and combine staged 2D
alignment with object-local contact constraints to refine hand trajectories and finger joint configurations. Experiments on DexYCB and HO3D-v3 show improved object pose accuracy and hand-object interaction quality. Experiments on three real-
robot dexterous manipulation tasks further show that reconstructed and retargeted human demonstrations can effectively supplement limited
robot data for target-task policy post-training.
Read the full abstract ▾
All authors Zetao Du, Weiqing Wang, Hanbing Zhang, Yimiao Zhou, Ye Shi, Liang Wang, Jingya Wang
Information Theory
On the Average List Size of VT Codes under Two Insertions or Two Deletions
Anisha Banerjee, Roni Con, Antonia Wachter-Zeh et al. (+1 more)
Levenshtein's classical
theorem shows that any code that can uniquely decode from \(t\) deletions can also uniquely decode from \(t\) insertions. This
symmetry, however, does not generally hold in the list-decoding regime. Several prior results on the capacity and radii of list-decoding from insertions and deletions suggest that insertions are easier to handle than deletions. In an effort to better understand this asymmetry between insertions and deletions under list-decoding, we study an analogous version of McEliece's average list size problem. More precisely, given a binary code \(\mathcal{C}\) of length \(n\) that uniquely corrects \(t'\) insertions (or deletions), we are interested in the average number of codewords returned by a \(t\)-insertion (or deletion) list decoder, where \(t' < t\). Focusing on the case of \(t'=1\) and \(t=2\), we find that under two insertions, this quantity is at most \((n+12)/4\) for any VT code of length \(n\), whereas under two deletions it is at least \(n/2 - 10\) when averaged over all length-\(n\) VT codes. The nearly factor-of-two gap between these upper and lower bounds serves to confirm the relative ease of list-decoding of insertions compared to deletions from an average-case perspective.
Read the full abstract ▾
All authors Anisha Banerjee, Roni Con, Antonia Wachter-Zeh, Eitan Yaakobi
Robotics
SurgiCLAW: An Interpretable Atomic-Skill Agent for Precision Robotic Micromanipulation
Angen Ye, junjie xie, Yujia Song et al. (+2 more)
Recent
multimodal large
language models (MLLMs) and
vision–
language–action models have provided
robots with new capabilities for long-horizon task understanding and planning. In surgical robotics, however, end-to-end prediction of low-level actions remains limited by insufficient precision, opaque decisions, and scarce data. This paper presents SurgiCLAW, a hierarchical skill-based framework for precision surgical manipulation. SurgiCLAW confines an MLLM to intraoperative visual understanding, structured explanation, and atomic surgical-skill selection, while delegating physical execution to verifiable deterministic control programs. For
brain–machine-interface implantation, a representative high-precision surgical task, we construct a state-to-skill invocation
dataset and expand it through visual and state perturbations. The model first learns structured skill invocation through supervised fine-tuning and is then optimized using three rewards for action correctness, operation prerequisites, and format validity, improving action selection, operational safety, and output parseability. We evaluate subtask success, offline model comparison, real-
robot performance, and ablations. On a fixed test set, SurgiCLAW achieves 94.6% skill-selection accuracy and 93.0% macro-averaged F1 (Macro-F1). Across 50 closed-loop real-
robot implantation trials, it achieves an 88.0% task success rate.
Read the full abstract ▾
All authors Angen Ye, junjie xie, Yujia Song, Junkai Huang, Dapeng Zhang
Software Engineering
A Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software Evolution
Alan Wu, Wei Tao and Yiwen Guo
Large
language model
agents are emerging as an important new class of users of desktop applications. However, existing desktop interfaces were designed for human end users or application developers, leaving
agents to interpret visual controls or discover and compose low-level software operations. This mismatch can hinder even capable
agents, yet it remains unclear what interface properties make desktop software easier for
agents to use. To study this question, we treat software
evolution as a natural source of interface variation and introduce DeskIF-Bench, a
benchmark of 255 artifact-verified tasks across six desktop applications. By holding the task,
agent, and verifier fixed while varying the software release, we measure how interface changes affect
agent performance. Across two models and six applications, the newest release consistently outperforms the oldest. Trajectory analysis identifies three relevant interface properties: discoverability, granularity, and observability. Guided by these properties, we develop ANIS, a framework that synthesizes
agent-native interfaces from the capabilities of installed applications. On an expanded evaluation of 368 tasks across eight applications, atomic interfaces improve success over native SDK use by 3.8 and 3.5 percentage points with DeepSeek V4 Flash and Claude Haiku 4.5, respectively, while reducing online
token usage by approximately 73%. Goal-level commands further raise success to 74.5% and 67.4%, respectively.
Read the full abstract ▾
Computer Vision
SlotAVS: Object-Centric Audio-Visual Segmentation via Bi-Modal Slot Attention
Arnav Sharma, Anand Mishra and Renu Rameshan
Audio-Visual Segmentation (AVS) requires predicting pixel-wise masks of sounding objects by grounding acoustic signals in visual space. In multi-source scenes, concurrent sound sources often remain entangled within shared visual representations, leading to merged masks or unstable specialization when using standard
alignment-focused
transformer architectures. To address this, we present SlotAVS, an object-centric framework driven by competitive bi-modal slot
attention. While robust foundation models provide rich semantic priors, SlotAVS shifts the paradigm from global cross-modal fusion to explicit competitive binding. By initializing discrete object slots from temporal audio sequences and enforcing strict slot-wise competition over spatial visual
tokens, our method structurally mitigates the blending of distinct acoustic entities. Further, to stabilize instance-level learning, we introduce a Hungarian matching strategy that optimally aligns slots with ground-truth objects using spatial and boundary overlap. Coupled with a numerically stable, confidence-aware mask fusion mechanism, SlotAVS robustly aggregates multi-source predictions. Extensive experiments on the AVSBench
dataset demonstrate the efficacy of our approach, achieving 88.6% mIoU on the Single-Source (S4) split and 71.7% mIoU on the Multi-Source (MS3) split. These results show that explicit competitive binding is critical for complex audio-visual scene understanding and effectively leveraging foundation-model priors without relying solely on their capacity.
Read the full abstract ▾
Robotics
Competitive Task Allocation with Temporal Proposal Windows and Improved Artificial Potential Fields for Dual-Arm Industrial Manipulation
Surya Prakash S.K, Bhuvan Narula, Jagannath Prasad Sahoo et al. (+3 more)
Modern industrial automation demands autonomous collaborative systems capable of coordinated manipulation in workspaces with heterogeneous object arrangements. Existing systems rely on predetermined trajectories and rigid allocation strategies, causing suboptimal workspace utilization and collision risks. This paper presents a distance-based competitive task allocation framework for dual-arm systems, integrating real-time
vision perception with collision-free motion planning. A temporal window mechanism enables each arm to evaluate object detections over five consecutive
vision frames before committing to optimal distance-based selection, featuring dynamic reallocation and spatial conflict resolution at 0.01m threshold accuracy. An improved Artificial Potential Field (iAPF) framework provides coordinated dual-arm movements through exponential goal attraction, inter-arm repulsion, home-seeking, and velocity damping forces. Simulation results validate superiority over
market-based, round-robin, and fixed allocation strategies in distance efficiency, collision risk, and workspace coverage. Hardware experiments using two 6-DOF Kinova Gen3 Lite manipulators demonstrate approximately 47% average velocity improvement over fixed allocation in homogeneous scenarios with zero collisions, while mixed object scenarios confirm universal handling with approximately 11% time overhead offset by superior safety margins. The framework integrates YOLOv8 OBB detection at 30 FPS with 10 Hz control loops, demonstrating practical deployment capability for industrial assembly and sorting operations.
Read the full abstract ▾
All authors Surya Prakash S.K, Bhuvan Narula, Jagannath Prasad Sahoo, Jayakumar VK, Praful Hambarde, Amit Shukla
Computation and Language
Robust Marathi Sentiment Analysis using Domain-Adaptive Pre-training and Data Augmentation Approaches
Tanvi Somani, Aryan Babare, Samyak Bora et al. (+2 more)
For
languages with limited resources, Sentiment Analysis remains a challenging problem due to limited annotated data and strong domain variability across textual sources. Marathi, despite being widely spoken, lacks extensive multi-domain sentiment analysis studies. Recent efforts by L3Cube have introduced multi-domain
datasets in Marathi, enabling a better study of domain-aware sentiment classification. This study uses the pretrained MahaBERT model to improve sentiment classification for Marathi across different domains. Models are trained on individual domain
datasets and domain-adaptive pretraining is applied using masked
language modeling to help the model better understand domain-specific
language. In addition, back-translation is used as a method of data augmentation to increase the diversity of training data. Results show that these methods lead to consistent improvements in accuracy across all domains. The improvements range from a minimum of about 0.12% to a maximum of about 1.74%, depending on the
dataset. These results demonstrate that domain-adaptive pretraining and data augmentation are effective strategies for improving sentiment analysis models. This helps achieve more robust performance across different domains and makes the approach more suitable for low-resource
languages like Marathi.
Read the full abstract ▾
All authors Tanvi Somani, Aryan Babare, Samyak Bora, Raviraj Joshi, Abhinay Dhamankar
Machine Learning
Hyperbolic Time Series Forecasting with Learnable Decomposition and Manifold Dynamics
Sarang Rajendra Patil, Vishal Fenn and Mengjia Xu
Multiscale structure is central to time series forecasting: temporal signals contain slowly varying trends, intermediate seasonal patterns, and high-frequency residuals. Traditional forecasters model this multiscale structure in Euclidean space, without representing the ordering it induces among components. We identify that cascaded decomposition orders components by their characteristic frequencies, forming a natural frequency hierarchy. This hierarchy aligns with the exponential volume growth of
hyperbolic space, which provides increasing representational capacity with radius and naturally accommodates nested hierarchies. We propose HyperForecast, the first long-term time series forecasting (LTSF) framework operating in
hyperbolic space. HyperForecast embeds decomposed temporal segments on the Poincaré ball where radial distance captures this nested structure, from low-frequency components near the origin to high-frequency components near the boundary. We model geodesic velocity through two
manifold-dynamics variants: (a) autoregressive forecasting via Poincaré residual dynamics, and (b) non-autoregressive forecasting that predicts all future segments in parallel. HyperForecast consistently outperforms existing and state-of-the-art baselines on 9 of 11 long-term forecasting
benchmarks, achieving up to 58% lower mean squared error at long horizons. Further analysis reveals that the learned radial
embeddings recover the frequency hierarchy and that
hyperbolic geometry contributes substantially to forecasting performance.
Read the full abstract ▾
Computation and Language
Enhancing Zero-Shot Domain Transfer in Low-Resource Sentiment Analysis: A Case Study in Marathi
Tanvi Somani, Aryan Babare, Samyak Bora et al. (+1 more)
Sentiment analysis is a key task in Natural
Language Processing that determines the polarity of opinions in text. For low-resource
languages like Marathi–where limited data prevents the direct use of standard statistical methods–models are often trained on single-domain
datasets. While this yields strong in-domain performance, it leads to poor generalization to unseen domains. Recent studies highlight the need for domain-robust systems that can handle diverse real-world content through multi-domain modeling. This study investigates how multi-domain training improves sentiment classification for unseen Marathi domains. Models are trained using single-domain, two-domain, and three-domain
dataset combinations. Results show that two-domain training improves accuracy on unseen domains by about 8% compared to single-domain training. Adding a third domain provides further improvement, though the gain is smaller, averaging around 2% for some domains. These results suggest that training with data from multiple domains helps build more robust sentiment analysis models for low-resource
languages, though the benefits reduce as more domains are added.
Read the full abstract ▾
All authors Tanvi Somani, Aryan Babare, Samyak Bora, Raviraj Joshi
Robotics
Kinematic Reward, Measured Effort: Hardware-Validated RL Morphology Optimization of a Planar 2R Manipulator
Gunesh Gupta, Arvind Kumar Mishra and Sohom Chakrabarty
Yoshikawa's Manipulability Index is generally used as a classical measure to define an optimal morphology of a manipulator. However, any such optimization is almost always studied as a purely kinematic quantity in simulation and is rarely validated on hardware. We present a reinforcement-learning framework with RSL-RL PPO that optimizes the morphology of a 2R SCARA-type manipulator arm with Yoshikawa's kinematic manipulability index as a core reward, and the analytically derived closed-form optimum for the circular task is used to verify that our method recovers it. Then the same method is applied to custom elliptical and rectangular paths having no analytical optimum. The RL-optimized morphologies are then transferred to a 2R hardware manipulator to validate its effect in reduction of joint load in the hardware. Compared to the worst morphology, the optimum morphology delivered by our method reduces second joint load by 38.4 +/- 0.6% for the ellipse path and 41.3 +/- 0.3% for the rectangle, and first joint load by 15%.
Read the full abstract ▾
Distributed Computing
Native Dual Pools or Shared Paging? Memory Organization for Concurrent Hybrid LLM Serving
Dongwook Kang
Hybrid
attention-SSM serving combines growing
attention KV with fixed-size recurrent and convolution state whose allocation units, reuse boundaries, and lifetimes differ. We implement four
memory organizations in a modified vLLM runtime: a coarse shared-page baseline (S0), checkpoint-internal recurrent paging (S1), paging with convolution-slot packing (S2), and native dual pools (D0). Nine evaluation questions cover storage costs and serving behavior. The cumulative S0-S1-S2 refinement improves completed-output throughput and tail completion time at the main operating point. D0-S2 performance varies with
memory budget, offered load, and admission headroom. Shared-prefix workloads yield larger stepwise gains; gains also persist in a no-sharing control with equal recorded input-work totals. State traces identify recurrent-checkpoint availability as the limit on joint reuse in the tested S2 runs. Extending producer-side checkpoint lifetime increases reusable depth at a fixed page budget. A fresh-seed SHARE/ISOLATE comparison estimates a positive retention interaction, with a primary confidence interval that includes zero. Retained-state continuation correctness remains unresolved. These findings motivate evaluating physical state representation together with request admission and checkpoint lifetime when designing
memory management for concurrent hybrid-model serving.
Read the full abstract ▾
Computer Vision
Frozen History: When Temporal Losses Stop Accumulation in Learned Real-Time Supersampling
Hao Yu and Guoying Zhao
Learned real-time supersampling accumulates jittered low-resolution samples along motion vectors. Many methods use a temporal consistency loss to reduce flicker. We show that with accurate registration, this loss can suppress accumulation: on static content, the network copies its warped history at almost no temporal cost. Camera jitter in motion vectors raises this cost and can hide the effect. We identify four registration errors that training can conceal: jitter-carrying motion vectors, one motion field for both resolution
lattices, jittered depth, and an unregistered skip path. A model-free oracle shows that correct registration makes freezing two orders of magnitude cheaper on static pixels. Controlled training shows that registration reverses the temporal weight's effect on PSNR. Under exact registration, increasing the weight reduces pixel variance at the expense of accuracy and perceived quality, with a 0.7 to 0.9 dB loss on static frames at weight 0.25. This reversal recurs across three network families and two scales; the loss also reduces accuracy on unjittered STSS data. With a small temporal weight and a normalised sample accumulator, a plain registered network improves the best published QRISP PSNR by 0.34 to 0.62 dB at $\times$2, $\times$3 and $\times$4 upscaling to 1080p. At $\times$2, its static pixel standard deviation is one quarter that of DLSS 2. Without retraining, it outperforms classical temporal upsampling by at least 4.4 dB on Arm's jittered Bistro capture. Our most accurate $\times$4 model runs in 2.03 ms per 1080p frame on an H200. Code: https://github.com/CV-AC/Frozen_history
Read the full abstract ▾
Artificial Intelligence
Google Earth AI Geospatial Reasoning Agent: Capabilities and a Systematic Evaluation
Noam Slonim, Aviv Slobodkin, Gil Fidel et al. (+34 more)
Google Earth AI is a family of geospatial AI models, together with an
agent that orchestrates them. We present this
agent, Google Earth AI's Geospatial
Reasoning agent (GRA), a Gemini-powered research system that combines geospatial data sources, foundation models, and tools to answer questions about our
planet. GRA organizes these into modular domain skills and pairs them with upfront geospatial planning to decompose complex queries into multi-stage workflows. Evaluating such systems is hard: real-world problems admit multiple valid workflows, require data discovery across large catalogs, and rely on evolving ground truth. We introduce two
benchmarks and release their development splits. GeoExpertQueries poses complex analytical problems grounded in practitioner use cases and refined by geospatial experts; each is paired with a consensus golden workflow from three independent experts and scored by a human-validated, tool-agnostic autorater. GeoKTools consists of templated queries with deterministic reference solvers that systematically vary the number of required tool types. We also use two external
benchmarks, CBGB and UnivEARTH; the latter we find to be saturated. To isolate the contribution of GRA's tools and its agentic orchestration, we compare four configurations, each with Gemini 3.1 Pro and 3.8 Flash: a standalone LLM, the LLM with basic tools, the LLM with GRA's skills and tools but without its upfront planning and execution guidance, and GRA itself. With at most basic tools, an advanced model recovers much of the answer on templated queries but satisfies only a small fraction of the expert workflows on open-ended problems; GRA performs well on both. The largest step comes from GRA's skills and tools; on open-ended problems, its planning and execution guidance add a further gain with Gemini 3.8 Flash, letting Flash match or exceed Pro at lower cost.
Read the full abstract ▾
All authors Noam Slonim, Aviv Slobodkin, Gil Fidel, Gal Moshitch, Mimi Sun, Lily Mihalkova, Joydeep Paul, Per Bjornsson, Sydney Lin, Jamie McPike, Samapriya Roy, Utkarsh Patel, Gia Jung, Zachary Luna, Allison Berman, William Cai, Xiao Wu, Mohit Agarwal, Mandar Sharma, Aliza Hoffman, Mark Young, Rama Pasumarthi, Roy Lee, Ruth Alcantara, Luke Barrington, Aaron Bell, Reuven Sayag, Avinatan Hassidim, Yossi Matias, Tyler McHenry, Ronald Ho, Christopher Haire, Oliver Guinan, Niv Efron, Tim Thelin, Gautam Prasad, Shravya Shetty
Robotics
Model-Based Trailer-Sway Suppression for Autonomous Passenger Vehicles
Alec McFadyen, Pablo Covarrubias De La Torre and Connor McGovern
Trailer sway is a persistent contributor to severe crashes among light passenger vehicles towing trailers, yet it remains largely unaddressed by the autonomous vehicle systems now entering this new era of automation. Improper cargo placement rearward of the trailer axle reduces, and can invert, the tongue load transmitted through the hitch. The resulting loss of vertical load at the tow vehicle's rear axle diminishes the lateral tire force available there and degrades yaw stability of the coupled system, admitting a divergent lateral oscillation of the trailer known as trailer sway. Under adverse combinations of speed and loading, this oscillation can progress to jackknifing, in which the articulation angle diverges rapidly and directional control is lost. This work develops a linear state-space model of the yaw-plane dynamics of a light vehicle-trailer combination, parameterized to expose tongue load as an explicit stability-determining quantity. From this model a linear quadratic regulator is synthesized to suppress articulation-angle divergence. Because consumer trailers carry no sensors, the two trailer states the controller needs, trailer yaw rate and articulation angle, are estimated by a Kalman filter from measurements taken only on the tow vehicle. The controller is then implemented and evaluated in a MuJoCo multibody simulation across a range of longitudinal speeds and tongue-load conditions, including the negative-tongue-load regime. Results show a significant decrease in trailer oscillation when controlling a given vehicle's steering with an LQR using tow-vehicle IMU and
LiDAR data. These findings indicate that LQR controlled anti-sway systems are a viable control method for future autonomous vehicles.
Read the full abstract ▾
Computer Vision
SpikeOcc: Towards Resilient Multimodal 3D Occupancy Perception via Spiking Experts
Yiding Sun, Zijie Xu, Hongqiang Lin et al. (+7 more)
Multimodal 3D occupancy prediction underpins safe autonomous driving through comprehensive scene understanding. However, existing methods have largely pursued higher accuracy through sophisticated fusion, leaving resilience to missing sensors underexplored. In this paper, we investigate spiking neural networks (SNNs) as a means of building more resilient
multimodal perception. Still, the discrete nature of spiking
neurons makes optimization challenging. To overcome this difficulty, SpikeOcc is introduced with two complementary components, a Spiking Mixture-of-Experts (SMoE) and Sensor Availability Learning (SAL). Specifically, SMoE organizes RGB,
LiDAR, and joint fusion into specialized pathways, enabling full-width unimodal representations while retaining the original
multimodal features via a bounded residual. Beyond sensor dropout, SAL employs a staged curriculum with explicit routing supervision, progressively improving robustness under severe sensing conditions. Remarkably, SAL also yields notable gains for conventional models, highlighting its broader potential for resilient
multimodal learning. Extensive experiments demonstrate that SpikeOcc maintains competitive full-sensor accuracy while markedly raising the performance floor under sensor outages. SpikeOcc illustrates the promise of neuromorphic computing, pointing toward more reliable and energy-efficient autonomous driving.
Read the full abstract ▾
All authors Yiding Sun, Zijie Xu, Hongqiang Lin, Jiajun Cao, Dongxu Zhang, Kai Tang, Jihua Zhu, Wenxuan Liu, Zhaofei Yu, Tiejun Huang
Computer Vision
RSAJEV: Training-Free Abstaining Prototype Memory for Eliminating Silent Hallucination in JEV-Based Remote Sensing Classification
Man Chen, Antai Chen, Shuai Xu et al. (+5 more)
Scene classification of remote sensing imagery with
multimodal large
language models (MLLMs) is formulated as a single-forward-pass decision problem: candidate class names are lettered options in the
prompt, a registered answer slot is conditioned on the
prompt, and classification is read out by scoring letter
tokens with the
language-modeling head. We show that although this letter binding is highly effective within its training vocabulary (97.71% OA on UCM), it behaves erratically out of vocabulary: zero-adaptation accuracy across four cross-
dataset directions fluctuates between 7.35% and 96.40%, and under out-of-vocabulary weights its confidence fails inversely on open-set evaluation, assigning higher confidence to unseen than to seen classes (AUROC 0.38), a failure we term silent
hallucination. We retain the slot representation and replace the readout with RSAJEV, a training-free abstaining prototype
memory that performs
retrieval-based prototype matching: K reference images per class are cached as prototypes via their slot representations under the same
prompt, and classification becomes nearest-neighbor
retrieval over the prototypes, refined by a shrinkage-Mahalanobis
geometric correction. This readout is mechanistically isomorphic to
retrieval-augmented generation (RAG) but operates on discriminative decisions; it is the first
retrieval-based readout for MLLM slot representations. The
retrieval readout reaches 89.43% on the UCM cross-
dataset gate with 16 references per class and zero gradient updates, and 96.90% on AID. Its ID-ness scores attain 0.91-0.99 AUROC on open-set evaluation over two
datasets, exceeding symbolic confidence (0.38-0.96) in all four open-set settings, restoring a calibratable abstention channel and supporting class addition/removal at zero extra inference cost via offline rescoring of the cached
matrix.
Read the full abstract ▾
All authors Man Chen, Antai Chen, Shuai Xu, Chengjie Gu, Huaping Zhou, Kelei Sun, Tao Wu, Yongjie Huang
Robotics
Multimodal Sensor-Gated Mid-Air Launch and Vision-Based Recovery of a Child UAV on a Hovering Mothership Drone
Aashish Sahu and R. Prasanth Kumar
Launching a micro unmanned aerial vehicle (
UAV) from a hovering carrier and recovering it in flight requires reliable confirmation that the child is securely seated before the carrier is allowed to descend. This is challenging because
vision provides relative guidance but does not directly indicate load transfer, and a downward-facing camera can lose its fiducial near touchdown. This letter presents a mothership-child quadrotor system in which mission transitions are gated by complementary nonvisual sensing. An upward-facing single-beam
LiDAR on the recovery deck provides a binary occupancy state using hysteresis and a debounce interval derived from the child's occluding footprint and crossing speed; real-time kinematic (RTK) positioning conditions the carrier hover; and carrier thrust provides a proprioceptive indication of load transfer. In ten outdoor missions using an F450-class mothership and a Q250-class child with camera-guided recovery, nine completed successfully while RTK-fixed positioning was maintained through release and capture. A complementary MuJoCo study of fully autonomous fiducial-based recovery achieved touchdown 0.077 m from the deck center, while marker detection was lost within the final approximately 0.2 m above the docked configuration. In simulation, carrier thrust changed by -17.0 N at release and +17.3 N at capture, agreeing within 6% with the child's 18.0 N hover thrust. The results support a sensing architecture in which
vision guides the approach, while range and proprioceptive information corroborate the final docking decision.
Read the full abstract ▾
Robotics
Distributed area coverage path planning subject to the inclusion of a headland path
Mogens Plessen
A deterministic method for the problem of distributed area coverage path planning subject to the inclusion of a headland path is presented. Given a, in general, non-convex area to be covered that may, in general, include obstacle areas, multiple
robots, at least one
robot depot, and constraints on each machinery such as a working width, work capacity limits, travel capacity limits, nonholonomic dynamical constraints and, possibly, a
robot start and end depot assignment, distributed paths for each machinery are calculated that collectively enable full area coverage. Variations are discussed, in particular, a scenario where unconstrained depots assignment can attain a global optimal solution to the problem. The importance of inclusion of a headland path for area coverage, as well as the benefits in comparison to an alternative Boustrophedon-pattern based approach are highlighted.
Read the full abstract ▾
Artificial Intelligence
Visible but Not Avoided: State-Dependent Re-Proposal of Rejected Candidates in Catalog-Based LLM Optimization Loops
Jianlin Chen, Wenhui Chen and Chi Man Vong
LLM optimization loops often show the proposer the candidates it has already tried and rejected, but leave it to the proposer to avoid them. We ask whether avoidance measured in a static probe predicts avoidance in the states an optimizer's own trajectory produces. In catalog-based loops where three open LLMs improve a GUI
agent by naming one of 40 edits, a re-proposal is identified exactly by the edit's name. Clean base-state probes underpredict re-proposal in the proposers' own loops (macro-averaged loop-minus-probe rate 0.32 [0.27, 0.37]), and proposals of already evaluated harness-edit pairs consume 28-63% of valid proposer iterations. The two settings reject different edits: a probe's rejected edits are mostly ones the proposer did not choose, whereas a loop's are its own earlier choices, which remain preferred when the history is removed. Ordinary history lowers re-proposal for two proposers but raises it for the third, and the effects of failure evidence are model-specific. Stating the rejection status in one sentence lowers re-proposal in every model (-0.16 [-0.22, -0.09] relative to a neutral list of the same IDs). For catalog-based loops with exact edit identities, rejection avoidance should be measured on the rejected sets the loop produces.
Read the full abstract ▾