# Research Papers — 2026-02 · bundle page 16 of 210

> Full-text markdown of papers #751–800 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-02/page/16
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/15.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/17.md)

### Model Agreement via Anchoring

Authors: Eric Eaton, Surbhi Goel, Marcel Hussing, Michael Kearns, Aaron Roth, Sikata Bela Sengupta, Jessica Sorrell
Published: 2026-02-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.23360v1

Numerous lines of aim to control $\textit{model disagreement}$ -- the extent to which two machine learning models disagree in their predictions. We adopt a simple and standard notion of model disagreement in real-valued prediction problems, namely the expected squared difference in predictions between two models trained on independent samples, without any coordination of the training processes. We would like to be able to drive disagreement to zero with some natural parameter(s) of the training procedure using analyses that can be applied to existing training methodologies. We develop a simple general technique for proving bounds on independent model disagreement based on $\textit{anchoring}$ to the average of two models within the analysis. We then apply this technique to prove disagreement bounds for four commonly used machine learning algorithms: (1) stacked aggregation over an arbitrary model class (where disagreement is driven to 0 with the number of models $k$ being stacked) (2) gradient boosting (where disagreement is driven to 0 with the number of iterations $k$) (3) neural network training with architecture search (where disagreement is driven to 0 with the size $n$ of the architecture being optimized over) and (4) regression tree training over all regression trees of fixed depth (where disagreement is driven to 0 with the depth $d$ of the tree architecture). For clarity, we work out our initial bounds in the setting of one-dimensional regression with squared error loss -- but then show that all of our results generalize to multi-dimensional regression with any strongly convex loss.

---

### SeeThrough3D: Occlusion Aware 3D Control in Text-to-Image Generation

Authors: Vaibhav Agrawal, Rishubh Parihar, Pradhaan Bhat, Ravi Kiran Sarvadevabhatla, R. Venkatesh Babu
Published: 2026-02-26
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.23359v1

We identify occlusion reasoning as a fundamental yet overlooked aspect for 3D layout-conditioned generation. It is essential for synthesizing partially occluded objects with depth-consistent geometry and scale. While existing methods can generate realistic scenes that follow input layouts, they often fail to model precise inter-object occlusions. We propose SeeThrough3D, a model for 3D layout conditioned generation that explicitly models occlusions. We introduce an occlusion-aware 3D scene representation (OSCR), where objects are depicted as translucent 3D boxes placed within a virtual environment and rendered from desired camera viewpoint. The transparency encodes hidden object regions, enabling the model to reason about occlusions, while the rendered viewpoint provides explicit camera control during generation. We condition a pretrained flow based text-to-image image generation model by introducing a set of visual tokens derived from our rendered 3D representation. Furthermore, we apply masked self-attention to accurately bind each object bounding box to its corresponding textual description, enabling accurate generation of multiple objects without object attribute mixing. To train the model, we construct a synthetic dataset with diverse multi-object scenes with strong inter-object occlusions. SeeThrough3D generalizes effectively to unseen object categories and enables precise 3D layout control with realistic occlusions and consistent camera control.

---

### A Dataset is Worth 1 MB

Authors: Elad Kimchi Shoshani, Leeyam Gabay, Yedid Hoshen
Published: 2026-02-26
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.23358v1

A dataset server must often distribute the same large payload to many clients, incurring massive communication costs. Since clients frequently operate on diverse hardware and software frameworks, transmitting a pre-trained model is often infeasible; instead, agents require raw data to train their own task-specific models locally. While dataset distillation attempts to compress training signals, current methods struggle to scale to high-resolution data and rarely achieve sufficiently small files. In this paper, we propose Pseudo-Labels as Data (PLADA), a method that completely eliminates pixel transmission. We assume agents are preloaded with a large, generic, unlabeled reference dataset (e.g., ImageNet-1K, ImageNet-21K) and communicate a new task by transmitting only the class labels for specific images. To address the distribution mismatch between the reference and target datasets, we introduce a pruning mechanism that filters the reference dataset to retain only the labels of the most semantically relevant images for the target task. This selection process simultaneously maximizes training efficiency and minimizes transmission payload. Experiments on 10 diverse datasets demonstrate that our approach can transfer task knowledge with a payload of less than 1 MB while retaining high classification accuracy, offering a promising solution for efficient dataset serving.

---

### Sensor Generalization for Adaptive Sensing in Event-based Object Detection via Joint Distribution Training

Authors: Aheli Saha, René Schuster, Didier Stricker
Published: 2026-02-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23357v1

Bio-inspired event cameras have recently attracted significant research due to their asynchronous and low-latency capabilities. These features provide a high dynamic range and significantly reduce motion blur. However, because of the novelty in the nature of their output signals, there is a gap in the variability of available data and a lack of extensive analysis of the parameters characterizing their signals. This paper addresses these issues by providing readers with an in-depth understanding of how intrinsic parameters affect the performance of a model trained on event data, specifically for object detection. We also use our findings to expand the capabilities of the downstream model towards sensor-agnostic robustness.

---

### SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport

Authors: Simon Roschmann, Paul Krzakala, Sonia Mazelet, Quentin Bouniot, Zeynep Akata
Published: 2026-02-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.23353v3

The Platonic Representation Hypothesis posits that neural networks trained on different modalities converge toward a shared statistical model of the world. Recent work exploits this convergence by aligning frozen pretrained vision and language models with lightweight alignment layers, but typically relies on contrastive losses and millions of paired samples. In this work, we ask whether meaningful alignment can be achieved with substantially less supervision. We introduce a semi-supervised setting in which pretrained unimodal encoders are aligned using a small number of image-text pairs together with large amounts of unpaired data. To address this challenge, we propose SOTAlign, a two-stage framework that first recovers a coarse shared geometry from limited paired data using a linear teacher, and then refines the alignment on unpaired samples via an optimal-transport-based divergence that transfers relational structure without overconstraining the target space. SOTAlign effectively leverages unpaired images and text, learning robust joint embeddings across datasets and encoder pairs, and significantly outperforming supervised and semi-supervised baselines. Code is available at https://github.com/ExplainableML/SOTAlign.

---

### SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport

Authors: Simon Roschmann, Paul Krzakala, Sonia Mazelet, Quentin Bouniot, Zeynep Akata
Published: 2026-02-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.23353v2

The Platonic Representation Hypothesis posits that neural networks trained on different modalities converge toward a shared statistical model of the world. Recent work exploits this convergence by aligning frozen pretrained vision and language models with lightweight alignment layers, but typically relies on contrastive losses and millions of paired samples. In this work, we ask whether meaningful alignment can be achieved with substantially less supervision. We introduce a semi-supervised setting in which pretrained unimodal encoders are aligned using a small number of image-text pairs together with large amounts of unpaired data. To address this challenge, we propose SOTAlign, a two-stage framework that first recovers a coarse shared geometry from limited paired data using a linear teacher, and then refines the alignment on unpaired samples via an optimal-transport-based divergence that transfers relational structure without overconstraining the target space. SOTAlign effectively leverages unpaired images and text, learning robust joint embeddings across datasets and encoder pairs, and significantly outperforming supervised and semi-supervised baselines. Code is available at https://github.com/ExplainableML/SOTAlign.

---

### Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning

Authors: Amita Kamath, Jack Hessel, Khyathi Chandu, Jena D. Hwang, Kai-Wei Chang, Ranjay Krishna
Published: 2026-02-26
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2602.23351v1

The lack of reasoning capabilities in Vision-Language Models (VLMs) has remained at the forefront of research discourse. We posit that this behavior stems from a reporting bias in their training data. That is, how people communicate about visual content by default omits tacit information needed to supervise some types of reasoning; e.g., "at the game today!" is a more likely caption than "a photo of 37 people standing behind a field". We investigate the data underlying the popular VLMs OpenCLIP, LLaVA-1.5 and Molmo through the lens of theories from pragmatics, and find that reporting bias results in insufficient representation of four reasoning skills (spatial, temporal, negation, and counting), despite the corpora being of web-scale, and/or synthetically generated. With a set of curated benchmarks, we demonstrate that: (i) VLMs perform poorly on the aforementioned types of reasoning suppressed in the training data by reporting bias; (ii) contrary to popular belief, scaling data size, model size, and to multiple languages does not result in emergence of these skills by default; but, promisingly, (iii) incorporating annotations specifically collected to obtain tacit information is effective. Our findings highlight the need for more intentional training data curation methods, rather than counting on scale for emergence of reasoning capabilities.

---

### FlashOptim: Optimizers for Memory-Efficient Training

Authors: Jose Javier Gonzalez Ortiz, Abhay Gupta, Christopher Rinard, Davis Blalock
Published: 2026-02-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.23349v2

Standard mixed-precision training of neural networks requires many bytes of accelerator memory for each model parameter. These bytes reflect not just the parameter itself, but also its gradient and one or more optimizer state variables. With each of these values typically requiring 4 bytes, training even a 7 billion parameter model can be impractical for researchers with less than 100GB of accelerator memory. We introduce FlashOptim, a suite of optimizations that reduces per-parameter memory by over 50% while preserving model quality and API compatibility. Our approach introduces two key techniques. First, we improve master weight splitting by finding and exploiting a tight bound on its quantization error. Second, we design companding functions that greatly reduce the error in 8-bit optimizer state quantization. Together with 16-bit gradients, these techniques reduce AdamW memory from 16 bytes to 7 bytes per parameter, or 5 bytes with gradient release. They also cut model checkpoint sizes by more than half. Experiments with FlashOptim applied to SGD, AdamW, and Lion show no measurable quality degradation on any task from a collection of standard vision and language benchmarks, including Llama-3.1-8B finetuning.

---

### Mean Estimation from Coarse Data: Characterizations and Efficient Algorithms

Authors: Alkis Kalavasis, Anay Mehrotra, Manolis Zampetakis, Felix Zhou, Ziyu Zhu
Published: 2026-02-26
Categories: cs.LG, cs.DS, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2602.23341v1

Coarse data arise when learners observe only partial information about samples; namely, a set containing the sample rather than its exact value. This occurs naturally through measurement rounding, sensor limitations, and lag in economic systems. We study Gaussian mean estimation from coarse data, where each true sample $x$ is drawn from a $d$-dimensional Gaussian distribution with identity covariance, but is revealed only through the set of a partition containing $x$. When the coarse samples, roughly speaking, have ``low'' information, the mean cannot be uniquely recovered from observed samples (i.e., the problem is not identifiable). Recent work by Fotakis, Kalavasis, Kontonis, and Tzamos (FKKT21) established that sample-efficient mean estimation is possible when the unknown mean is identifiable and the partition consists of only convex sets. Moreover, they showed that without convexity, mean estimation becomes NP-hard. However, two fundamental questions remained open: (1) When is the mean identifiable under convex partitions? (2) Is computationally efficient estimation possible under identifiability and convex partitions? This work resolves both questions. (...)

---

### Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation?

Authors: Tilemachos Aravanis, Vladan Stojnić, Bill Psomas, Nikos Komodakis, Giorgos Tolias
Published: 2026-02-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23339v1

Open-vocabulary segmentation (OVS) extends the zero-shot recognition capabilities of vision-language models (VLMs) to pixel-level prediction, enabling segmentation of arbitrary categories specified by text prompts. Despite recent progress, OVS lags behind fully supervised approaches due to two challenges: the coarse image-level supervision used to train VLMs and the semantic ambiguity of natural language. We address these limitations by introducing a few-shot setting that augments textual prompts with a support set of pixel-annotated images. Building on this, we propose a retrieval-augmented test-time adapter that learns a lightweight, per-image classifier by fusing textual and visual support features. Unlike prior methods relying on late, hand-crafted fusion, our approach performs learned, per-query fusion, achieving stronger synergy between modalities. The method supports continually expanding support sets, and applies to fine-grained tasks such as personalized segmentation. Experiments show that we significantly narrow the gap between zero-shot and supervised segmentation while preserving open-vocabulary ability.

---

### Differentiable Zero-One Loss via Hypersimplex Projections

Authors: Camilo Gomez, Pengyang Wang, Liansheng Tang
Published: 2026-02-26
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.23336v1

Recent advances in machine learning have emphasized the integration of structured optimization components into end-to-end differentiable models, enabling richer inductive biases and tighter alignment with task-specific objectives. In this work, we introduce a novel differentiable approximation to the zero-one loss-long considered the gold standard for classification performance, yet incompatible with gradient-based optimization due to its non-differentiability. Our method constructs a smooth, order-preserving projection onto the n,k-dimensional hypersimplex through a constrained optimization framework, leading to a new operator we term Soft-Binary-Argmax. After deriving its mathematical properties, we show how its Jacobian can be efficiently computed and integrated into binary and multiclass learning systems. Empirically, our approach achieves significant improvements in generalization under large-batch training by imposing geometric consistency constraints on the output logits, thereby narrowing the performance gap traditionally observed in large-batch training.

---

### Understanding Usage and Engagement in AI-Powered Scientific Research Tools: The Asta Interaction Dataset

Authors: Dany Haddad, Dan Bareket, Joseph Chee Chang, Jay DeYoung, Jena D. Hwang, Uri Katz, Mark Polak, Sangho Suh, Harshit Surana, Aryeh Tiktinsky, Shriya Atmakuri, Jonathan Bragg et al.
Published: 2026-02-26
Categories: cs.HC, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2602.23335v1

AI-powered scientific research tools are rapidly being integrated into research workflows, yet the field lacks a clear lens into how researchers use these systems in real-world settings. We present and analyze the Asta Interaction Dataset, a large-scale resource comprising over 200,000 user queries and interaction logs from two deployed tools (a literature discovery interface and a scientific question-answering interface) within an LLM-powered retrieval-augmented generation platform. Using this dataset, we characterize query patterns, engagement behaviors, and how usage evolves with experience. We find that users submit longer and more complex queries than in traditional search, and treat the system as a collaborative research partner, delegating tasks such as drafting content and identifying research gaps. Users treat generated responses as persistent artifacts, revisiting and navigating among outputs and cited evidence in non-linear ways. With experience, users issue more targeted queries and engage more deeply with supporting citations, although keyword-style queries persist even among experienced users. We release the anonymized dataset and analysis with a new query intent taxonomy to inform future designs of real-world AI research assistants and to support realistic evaluation.

---

### Bitwise Systolic Array Architecture for Runtime-Reconfigurable Multi-precision Quantized Multiplication on Hardware Accelerators

Authors: Yuhao Liu, Salim Ullah, Akash Kumar
Published: 2026-02-26
Categories: cs.AR, cs.AI
arXiv: https://arxiv.org/abs/2602.23334v2

Neural network accelerators have been widely applied to edge devices for complex tasks like object tracking, image recognition, etc. Previous works have explored the quantization technologies in related lightweight accelerator designs to reduce hardware resource consumption. However, low precision leads to high accuracy loss in inference. Therefore, mixed-precision quantization becomes an alternative solution by applying different precision in different layers to trade off resource consumption and accuracy. Because regular designs for multiplication on hardware cannot support the precision reconfiguration for a multi-precision Quantized Neural Network (QNN) model in runtime, we propose a runtime reconfigurable multi-precision multi-channel bitwise systolic array design for QNN accelerators. We have implemented and evaluated our work on the Ultra96 FPGA platform. Results show that our work can achieve 1.3185 to 3.5671 times speedup in inferring mixed-precision models and has less critical path delay, supporting a higher clock frequency (250MHz).

---

### Utilizing LLMs for Industrial Process Automation

Authors: Salim Fares
Published: 2026-02-26
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2602.23331v1

A growing number of publications address the best practices to use Large Language Models (LLMs) for software engineering in recent years. However, most of this work focuses on widely-used general purpose programming languages like Python due to their widespread usage training data. The utility of LLMs for software within the industrial process automation domain, with highly-specialized languages that are typically only used in proprietary contexts, remains underexplored. This research aims to utilize and integrate LLMs in the industrial development process, solving real-life programming tasks (e.g., generating a movement routine for a robotic arm) and accelerating the development cycles of manufacturing systems.

---

### Toward Expert Investment Teams:A Multi-Agent LLM System with Fine-Grained Trading Tasks

Authors: Kunihiro Miyazaki, Takanobu Kawahara, Stephen Roberts, Stefan Zohren
Published: 2026-02-26
Categories: cs.AI, q-fin.TR
arXiv: https://arxiv.org/abs/2602.23330v1

The advancement of large language models (LLMs) has accelerated the development of autonomous financial trading systems. While mainstream approaches deploy multi-agent systems mimicking analyst and manager roles, they often rely on abstract instructions that overlook the intricacies of real-world workflows, which can lead to degraded inference performance and less transparent decision-making. Therefore, we propose a multi-agent LLM trading framework that explicitly decomposes investment analysis into fine-grained tasks, rather than providing coarse-grained instructions. We evaluate the proposed framework using Japanese stock data, including prices, financial statements, news, and macro information, under a leakage-controlled backtesting setting. Experimental results show that fine-grained task decomposition significantly improves risk-adjusted returns compared to conventional coarse-grained designs. Crucially, further analysis of intermediate agent outputs suggests that alignment between analytical outputs and downstream decision preferences is a critical driver of system performance. Moreover, we conduct standard portfolio optimization, exploiting low correlation with the stock index and the variance of each system's output. This approach achieves superior performance. These findings contribute to the design of agent structure and task configuration when applying LLM agents to trading systems in practical settings.

---

### LLM Novice Uplift on Dual-Use, In Silico Biology Tasks

Authors: Chen Bo Calvin Zhang, Christina Q. Knight, Nicholas Kruus, Jason Hausenloy, Pedro Medeiros, Nathaniel Li, Aiden Kim, Yury Orlovskiy, Coleman Breen, Bryce Cai, Jasper Götting, Andrew Bo Liu et al.
Published: 2026-02-26
Categories: cs.AI, cs.CL, cs.CR, cs.CY, cs.HC
arXiv: https://arxiv.org/abs/2602.23329v2

Large language models (LLMs) perform increasingly well on biology benchmarks, but it remains unclear whether they uplift novice users -- i.e., enable humans to perform better than with internet-only resources. This uncertainty is central to understanding both scientific acceleration and dual-use risk. We conducted a multi-model, multi-benchmark human uplift study comparing novices with LLM access versus internet-only access across eight biosecurity-relevant task sets. Participants worked on complex problems with ample time (up to 13 hours for the most involved tasks). We found that LLM access provided substantial uplift: novices with LLMs were 4.16 times more accurate than controls (95% CI (2.63, 6.87)). On four benchmarks with available expert baselines (internet-only), novices with LLMs outperformed experts on three of them. Perhaps surprisingly, standalone LLMs often exceeded LLM-assisted novices, indicating that users were not eliciting the strongest available contributions from the LLMs. Most participants (89.6%) reported little difficulty obtaining dual-use-relevant information despite safeguards. Overall, LLMs substantially uplift novices on biological tasks previously reserved for trained practitioners, underscoring the need for sustained, interactive uplift evaluations alongside traditional benchmarks.

---

### Deep ensemble graph neural networks for probabilistic cosmic-ray direction and energy reconstruction in autonomous radio arrays

Authors: Arsène Ferrière, Aurélien Benoit-Lévy, Olivier Martineau-Huynh, Matías Tueros
Published: 2026-02-26
Categories: astro-ph.IM, cs.LG
arXiv: https://arxiv.org/abs/2602.23321v1

Using advanced machine learning techniques, we developed a method for reconstructing precisely the arrival direction and energy of ultra-high-energy cosmic rays from the voltage traces they induced on ground-based radio detector arrays. In our approach, triggered antennas are represented as a graph structure, which serves as input for a graph neural network (GNN). By incorporating physical knowledge into both the GNN architecture and the input data, we improve the precision and reduce the required size of the training set with respect to a fully data-driven approach. This method achieves an angular resolution of 0.092° and an electromagnetic energy reconstruction resolution of 16.4% on simulated data with realistic noise conditions. We also employ uncertainty estimation methods to enhance the reliability of our predictions, quantifying the confidence of the GNN's outputs and providing confidence intervals for both direction and energy reconstruction. Finally, we investigate strategies to verify the model's consistency and robustness under real life variations, with the goal of identifying scenarios in which predictions remain reliable despite domain shifts between simulation and reality.

---

### ParamMem: Augmenting Language Agents with Parametric Reflective Memory

Authors: Tianjun Yao, Yongqiang Chen, Yujia Zheng, Pan Li, Zhiqiang Shen, Kun Zhang
Published: 2026-02-26
Categories: cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2602.23320v2

Self-reflection enables language agents to iteratively refine solutions, yet often produces repetitive outputs that limit reasoning performance. Recent studies have attempted to address this limitation through various approaches, among which increasing reflective diversity has shown promise. Our empirical analysis reveals a strong positive correlation between reflective diversity and task success, further motivating the need for diverse reflection signals. We introduce ParamMem, a parametric memory module that encodes cross-sample reflection patterns into model parameters, enabling diverse reflection generation through temperature-controlled sampling. Building on this module, we propose ParamAgent, a reflection-based agent framework that integrates parametric memory with episodic and cross-sample memory. Extensive experiments on code generation, mathematical reasoning, and multi-hop question answering demonstrate consistent improvements over state-of-the-art baselines. Further analysis reveals that ParamMem is sample-efficient, enables weak-to-strong transfer across model scales, and supports self-improvement without reliance on stronger external model, highlighting the potential of ParamMem as an effective component for enhancing language agents.

---

### Generalized Rapid Action Value Estimation in Memory-Constrained Environments

Authors: Aloïs Rautureau, Tristan Cazenave, Éric Piette
Published: 2026-02-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.23318v1

Generalized Rapid Action Value Estimation (GRAVE) has been shown to be a strong variant within the Monte-Carlo Tree Search (MCTS) family of algorithms for General Game Playing (GGP). However, its reliance on storing additional win/visit statistics at each node makes its use impractical in memory-constrained environments, thereby limiting its applicability in practice. In this paper, we introduce the GRAVE2, GRAVER and GRAVER2 algorithms, which extend GRAVE through two-level search, node recycling, and a combination of both techniques, respectively. We show that these enhancements enable a drastic reduction in the number of stored nodes while matching the playing strength of GRAVE.

---

### Invariant Transformation and Resampling based Epistemic-Uncertainty Reduction

Authors: Sha Hu
Published: 2026-02-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.23315v1

An artificial intelligence (AI) model can be viewed as a function that maps inputs to outputs in high-dimensional spaces. Once designed and well trained, the AI model is applied for inference. However, even optimized AI models can produce inference errors due to aleatoric and epistemic uncertainties. Interestingly, we observed that when inferring multiple samples based on invariant transformations of an input, inference errors can show partial independences due to epistemic uncertainty. Leveraging this insight, we propose a "resampling" based inferencing that applies to a trained AI model with multiple transformed versions of an input, and aggregates inference outputs to a more accurate result. This approach has the potential to improve inference accuracy and offers a strategy for balancing model size and performance.

---

### Evaluating Zero-Shot and One-Shot Adaptation of Small Language Models in Leader-Follower Interaction

Authors: Rafael R. Baptista, André de Lima Salgado, Ricardo V. Godoy, Marcelo Becker, Thiago Boaventura, Gustavo J. G. Lahr
Published: 2026-02-26
Categories: cs.HC, cs.AI, cs.LG, cs.RO, eess.SY
arXiv: https://arxiv.org/abs/2602.23312v3

Leader-follower interaction is an important paradigm in human-robot interaction (HRI). Yet, assigning roles in real time remains challenging for resource-constrained mobile and assistive robots. While large language models (LLMs) have shown promise for natural communication, their size and latency limit on-device deployment. Small language models (SLMs) offer a potential alternative, but their effectiveness for role classification in HRI has not been systematically evaluated. In this paper, we present a benchmark of SLMs for leader-follower communication, introducing a novel dataset derived from a published database and augmented with synthetic samples to capture interaction-specific dynamics. We investigate two adaptation strategies: prompt engineering and fine-tuning, studied under zero-shot and one-shot interaction modes, compared with an untrained baseline. Experiments with Qwen2.5-0.5B reveal that zero-shot fine-tuning achieves robust classification performance (86.66% accuracy) while maintaining low latency (22.2 ms per sample), significantly outperforming baseline and prompt-engineered approaches. However, results also indicate a performance degradation in one-shot modes, where increased context length challenges the model's architectural capacity. These findings demonstrate that fine-tuned SLMs provide an effective solution for direct role assignment, while highlighting critical trade-offs between dialogue complexity and classification reliability on the edge.

---

### ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding

Authors: Yiran Guan, Sifan Tu, Dingkang Liang, Linghao Zhu, Jianzhong Ju, Zhenbo Luo, Jian Luan, Yuliang Liu, Xiang Bai
Published: 2026-02-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23306v2

Omni-modal reasoning is essential for intelligent systems to understand and draw inferences from diverse data sources. While existing omni-modal large language models (OLLM) excel at perceiving diverse modalities, they lack the complex reasoning abilities of recent large reasoning models (LRM). However, enhancing the reasoning ability of OLLMs through additional training presents significant challenges, including the need for high-quality data, task-specific adaptation, and substantial computational costs. To address these limitations, we propose ThinkOmni, a training-free and data-free framework that lifts textual reasoning to omni-modal scenarios. ThinkOmni introduces two key components: 1) LRM-as-a-Guide, which leverages off-the-shelf LRMs to guide the OLLM decoding process; 2) Stepwise Contrastive Scaling, which adaptively balances perception and reasoning signals without manual hyperparameter tuning. Experiments on six multi-modal reasoning benchmarks demonstrate that ThinkOmni consistently delivers performance improvements, with main results achieving 70.2 on MathVista and 75.5 on MMAU. Overall, ThinkOmni offers a flexible and generalizable solution for omni-modal reasoning and provides new insights into the generalization and application of reasoning capabilities. Code is publicly available at https://github.com/1ranGuan/thinkomni

---

### A Proper Scoring Rule for Virtual Staining

Authors: Samuel Tonks, Steve Hood, Ryan Musso, Ceridwen Hopely, Steve Titus, Minh Doan, Iain Styles, Alexander Krull
Published: 2026-02-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.23305v1

Generative virtual staining (VS) models for high-throughput screening (HTS) can provide an estimated posterior distribution of possible biological feature values for each input and cell. However, when evaluating a VS model, the true posterior is unavailable. Existing evaluation protocols only check the accuracy of the marginal distribution over the dataset rather than the predicted posteriors. We introduce information gain (IG) as a cell-wise evaluation framework that enables direct assessment of predicted posteriors. IG is a strictly proper scoring rule and comes with a sound theoretical motivation allowing for interpretability, and for comparing results across models and features. We evaluate diffusion- and GAN-based models on an extensive HTS dataset using IG and other metrics and show that IG can reveal substantial performance differences other metrics cannot.

---

### Inferential Mechanics Part 1: Causal Mechanistic Theories of Machine Learning in Chemical Biology with Implications

Authors: Ilya Balabin, Thomas M. Kaiser
Published: 2026-02-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.23303v1

Machine learning techniques are now routinely encountered in research laboratories across the globe. Impressive progress has been made through ML and AI techniques with regards to large data set processing. This progress has increased the ability of the experimenter to digest data and make novel predictions regarding phenomena of interest. However, machine learning predictors generated from data sets taken from the natural sciences are often treated as black boxes which are used broadly and generally without detailed consideration of the causal structure of the data set of interest. Work has been attempted to bring causality into discussions of machine learning models of natural phenomena; however, a firm and unified theoretical treatment is lacking. This series of three papers explores the union of chemical theory, biological theory, probability theory and causality that will correct current causal flaws of machine learning in the natural sciences. This paper, Part 1 of the series, provides the formal framework of the foundational causal structure of phenomena in chemical biology and is extended to machine learning through the novel concept of focus, defined here as the ability of a machine learning algorithm to narrow down to a hidden underpinning mechanism in large data sets. Initial proof of these principles on a family of Akt inhibitors is also provided. The second paper containing Part 2 will provide a formal exploration of chemical similarity, and Part 3 will present extensive experimental evidence of how hidden causal structures weaken all machine learning in chemical biology. This series serves to establish for chemical biology a new kind of mathematical framework for modeling mechanisms in Nature without the need for the tools of reductionism: inferential mechanics.

---

### The logic of KM belief update is contained in the logic of AGM belief revision

Authors: Giacomo Bonanno
Published: 2026-02-26
Categories: cs.AI, cs.LO, math.LO
arXiv: https://arxiv.org/abs/2602.23302v2

For each axiom of KM belief update we provide a corresponding axiom in a modal logic containing three modal operators: a unimodal belief operator $B$, a bimodal conditional operator $>$ and the unimodal necessity operator $\square$. We then compare the resulting logic to the similar logic obtained from converting the AGM axioms of belief revision into modal axioms and show that the latter contains the former. Denoting the latter by $\mathcal L_{AGM}$ and the former by $\mathcal L_{KM}$ we show that every axiom of $\mathcal L_{KM}$ is a theorem of $\mathcal L_{AGM}$. Thus AGM belief revision can be seen as a special case of KM belief update. For the strong version of KM belief update we show that the difference between $\mathcal L_{KM}$ and $\mathcal L_{AGM}$ can be narrowed down to a single axiom, which deals exclusively with unsurprising information, that is, with formulas that were not initially disbelieved.

---

### A Mixture-of-Experts Model for Multimodal Emotion Recognition in Conversations

Authors: Soumya Dutta, Smruthi Balaji, Sriram Ganapathy
Published: 2026-02-26
Categories: cs.CL, eess.AS
arXiv: https://arxiv.org/abs/2602.23300v1

Emotion Recognition in Conversations (ERC) presents unique challenges, requiring models to capture the temporal flow of multi-turn dialogues and to effectively integrate cues from multiple modalities. We propose Mixture of Speech-Text Experts for Recognition of Emotions (MiSTER-E), a modular Mixture-of-Experts (MoE) framework designed to decouple two core challenges in ERC: modality-specific context modeling and multimodal information fusion. MiSTER-E leverages large language models (LLMs) fine-tuned for both speech and text to provide rich utterance-level embeddings, which are then enhanced through a convolutional-recurrent context modeling layer. The system integrates predictions from three experts-speech-only, text-only, and cross-modal-using a learned gating mechanism that dynamically weighs their outputs. To further encourage consistency and alignment across modalities, we introduce a supervised contrastive loss between paired speech-text representations and a KL-divergence-based regulariza-tion across expert predictions. Importantly, MiSTER-E does not rely on speaker identity at any stage. Experiments on three benchmark datasets-IEMOCAP, MELD, and MOSI-show that our proposal achieves 70.9%, 69.5%, and 87.9% weighted F1-scores respectively, outperforming several baseline speech-text ERC systems. We also provide various ablations to highlight the contributions made in the proposed approach.

---

### PRIMA: Pre-Training with Risk-Integrated Image--Metadata Alignment for Medical Diagnosis with LLM-Based Feature Aggregation

Authors: Yiqing Wang, Chunming He, Ziyun Yang, Maria Woodward, Ming-Chen Lu, Mercy Pawar, Leslie Niziol, Sina Farsiu
Published: 2026-02-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23297v3

Medical diagnosis requires the effective synthesis of visual manifestations and clinical metadata. However, existing methods often treat metadata as isolated tags, failing to exploit the rich semantic knowledge embedded in clinical descriptions. We propose PRIMA (Pre-training with Risk-integrated Image-Metadata Alignment), a framework that integrates domain-specific knowledge into multi-modal representation learning. We first curate a corpus of risk--disease correlations via Retrieval-Augmented Generation (RAG) to refine Clinical ModernBERT, embedding diagnostic priors into the text encoder. To bridge the modality gap, we introduce a dual-encoder pre-training strategy utilizing DINOv3 and our refined Clinical ModernBERT, optimized by a suite of four complementary loss functions. These losses are designed to capture multi-granular semantic alignment and handle the ambiguity of clinical correlations through soft labels. Finally, we leverage Qwen3 to fuse these aligned features for precise disease classification. Extensive experiments demonstrate that PRIMA effectively harmonizes pixel-level features with abstract clinical expertise. Across PAD-UFES-20 and AQUA, PRIMA achieves average F1-scores of 72.04\% and 85.22\%, outperforming strong image-only, metadata-fusion, and medical vision-language baselines. Notably, our framework achieves strong performance without requiring massive data collection or exhaustive computational resources. Our code is available at https://github.com/yqwang01/PRIMA.

---

### Conformalized Neural Networks for Federated Uncertainty Quantification under Dual Heterogeneity

Authors: Quang-Huy Nguyen, Jiaqi Wang, Wei-Shinn Ku
Published: 2026-02-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.23296v2

Federated learning (FL) faces challenges in uncertainty quantification (UQ). Without reliable UQ, FL systems risk deploying overconfident models at under-resourced agents, leading to silent local failures despite seemingly satisfactory global performance. Existing federated UQ approaches often address data heterogeneity or model heterogeneity in isolation, overlooking their joint effect on coverage reliability across agents. Conformal prediction is a widely used distribution-free UQ framework, yet its applications in heterogeneous FL settings remains underexplored. We provide FedWQ-CP, a simple yet effective approach that balances empirical coverage performance with efficiency at both global and agent levels under the dual heterogeneity. FedWQ-CP performs agent-server calibration in a single communication round. On each agent, conformity scores are computed on calibration data and a local quantile threshold is derived. Each agent then transmits only its quantile threshold and calibration sample size to the server. The server simply aggregates these thresholds through a weighted average to produce a global threshold. Experimental results on seven public datasets for both classification and regression demonstrate that FedWQ-CP empirically maintains agent-wise and global coverage while producing the smallest prediction sets or intervals.

---

### ManifoldGD: Training-Free Hierarchical Manifold Guidance for Diffusion-Based Dataset Distillation

Authors: Ayush Roy, Wei-Yang Alex Lee, Rudrasis Chakraborty, Vishnu Suresh Lokhande
Published: 2026-02-26
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.23295v1

In recent times, large datasets hinder efficient model training while also containing redundant concepts. Dataset distillation aims to synthesize compact datasets that preserve the knowledge of large-scale training sets while drastically reducing storage and computation. Recent advances in diffusion models have enabled training-free distillation by leveraging pre-trained generative priors; however, existing guidance strategies remain limited. Current score-based methods either perform unguided denoising or rely on simple mode-based guidance toward instance prototype centroids (IPC centroids), which often are rudimentary and suboptimal. We propose Manifold-Guided Distillation (ManifoldGD), a training-free diffusion-based framework that integrates manifold consistent guidance at every denoising timestep. Our method employs IPCs computed via a hierarchical, divisive clustering of VAE latent features, yielding a multi-scale coreset of IPCs that captures both coarse semantic modes and fine intra-class variability. Using a local neighborhood of the extracted IPC centroids, we create the latent manifold for each diffusion denoising timestep. At each denoising step, we project the mode-alignment vector onto the local tangent space of the estimated latent manifold, thus constraining the generation trajectory to remain manifold-faithful while preserving semantic consistency. This formulation improves representativeness, diversity, and image fidelity without requiring any model retraining. Empirical results demonstrate consistent gains over existing training-free and training-based baselines in terms of FID, l2 distance among real and synthetic dataset embeddings, and classification accuracy, establishing ManifoldGD as the first geometry-aware training-free data distillation framework.

---

### Towards Long-Form Spatio-Temporal Video Grounding

Authors: Xin Gu, Bing Fan, Jiali Yao, Zhipeng Zhang, Yan Huang, Cheng Han, Heng Fan, Libo Zhang
Published: 2026-02-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23294v2

In real scenarios, videos can span several minutes or even hours. However, existing research on spatio-temporal video grounding (STVG), given a textual query, mainly focuses on localizing targets in short videos of tens of seconds, typically less than one minute, which limits real-world applications. In this paper, we explore Long-Form STVG (LF-STVG), which aims to locate targets in long-term videos. Compared with short videos, long-term videos contain much longer temporal spans and more irrelevant information, making it difficult for existing STVG methods that process all frames at once. To address this challenge, we propose an AutoRegressive Transformer architecture for LF-STVG, termed ART-STVG. Unlike conventional STVG methods that require the entire video sequence to make predictions at once, ART-STVG treats the video as streaming input and processes frames sequentially, enabling efficient handling of long videos. To model spatio-temporal context, we design spatial and temporal memory banks and apply them to the decoders. Since memories from different moments are not always relevant to the current frame, we introduce simple yet effective memory selection strategies to provide more relevant information to the decoders, significantly improving performance. Furthermore, instead of parallel spatial and temporal localization, we propose a cascaded spatio-temporal design that connects the spatial decoder to the temporal decoder, allowing fine-grained spatial cues to assist complex temporal localization in long videos. Experiments on newly extended LF-STVG datasets show that ART-STVG significantly outperforms state-of-the-art methods, while achieving competitive performance on conventional short-form STVG. Our code is at: https://github.com/HengLan/ART-STVG.

---

### PGVMS: A Prompt-Guided Unified Framework for Virtual Multiplex IHC Staining with Pathological Semantic Learning

Authors: Fuqiang Chen, Ranran Zhang, Wanming Hu, Deboch Eyob Abera, Yue Peng, Boyun Zheng, Yiwen Sun, Jing Cai, Wenjian Qin
Published: 2026-02-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23292v1

Immunohistochemical (IHC) staining enables precise molecular profiling of protein expression, with over 200 clinically available antibody-based tests in modern pathology. However, comprehensive IHC analysis is frequently limited by insufficient tissue quantities in small biopsies. Therefore, virtual multiplex staining emerges as an innovative solution to digitally transform H&E images into multiple IHC representations, yet current methods still face three critical challenges: (1) inadequate semantic guidance for multi-staining, (2) inconsistent distribution of immunochemistry staining, and (3) spatial misalignment across different stain modalities. To overcome these limitations, we present a prompt-guided framework for virtual multiplex IHC staining using only uniplex training data (PGVMS). Our framework introduces three key innovations corresponding to each challenge: First, an adaptive prompt guidance mechanism employing a pathological visual language model dynamically adjusts staining prompts to resolve semantic guidance limitations (Challenge 1). Second, our protein-aware learning strategy (PALS) maintains precise protein expression patterns by direct quantification and constraint of protein distributions (Challenge 2). Third, the prototype-consistent learning strategy (PCLS) establishes cross-image semantic interaction to correct spatial misalignments (Challenge 3).

---

### LineGraph2Road: Structural Graph Reasoning on Line Graphs for Road Network Extraction

Authors: Zhengyang Wei, Renzhi Jing, Yiyi He, Jenny Suckale
Published: 2026-02-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23290v2

Extracting routable road networks from satellite imagery requires accurate topology recovery beyond pixel-level segmentation. Recent methods decompose the task into keypoint detection and connectivity prediction, but reliably inferring road connectivity under structural ambiguity remains challenging. Overpasses introduce non-planar crossings that can create false shortcuts, and occlusions break visual continuity, requiring long-range structural reasoning. We formulate road extraction as fully unobserved connectivity inference and construct a global but sparse Euclidean graph from detected keypoints to better leverage the long-term context. To improve link prediction, we transform this graph into its line graph and perform reasoning using a Graph Transformer. We propose an end-to-end pipeline that integrates vision-based segmentation, sparse graph construction, and structured inference. Our method explicitly models overpasses and uses topology-preserving vertex extraction to mitigate routing-critical errors. This approach achieves state-of-the-art performance on City-scale, SpaceNet, and Global-scale benchmarks in topology metrics including TOPO-F1 and APLS. In addition to quantitative gains, our method improves reconstruction of multi-level road structures crucial for real-world routing reliability. The code is available at: https://github.com/wzzzzzzy/LineGraph2Road.

---

### LineGraph2Road: Structural Graph Reasoning on Line Graphs for Road Network Extraction

Authors: Zhengyang Wei, Renzhi Jing, Yiyi He, Jenny Suckale
Published: 2026-02-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.23290v1

The accurate and automatic extraction of roads from satellite imagery is critical for applications in navigation and urban planning, significantly reducing the need for manual annotation. Many existing methods decompose this task into keypoint extraction and connectedness prediction, but often struggle to capture long-range dependencies and complex topologies. Here, we propose LineGraph2Road, a framework that improves connectedness prediction by formulating it as binary classification over edges in a constructed global but sparse Euclidean graph, where nodes are keypoints extracted from segmentation masks and edges connect node pairs within a predefined distance threshold, representing potential road segments. To better learn structural link representation, we transform the original graph into its corresponding line graph and apply a Graph Transformer on it for connectedness prediction. This formulation overcomes the limitations of endpoint-embedding fusion on set-isomorphic links, enabling rich link representations and effective relational reasoning over the global structure. Additionally, we introduce an overpass/underpass head to resolve multi-level crossings and a coupled NMS strategy to preserve critical connections. We evaluate LineGraph2Road on three benchmarks: City-scale, SpaceNet, and Global-scale, and show that it achieves state-of-the-art results on two key metrics, TOPO-F1 and APLS. It also captures fine visual details critical for real-world deployment. We will make our code publicly available.

---

### SPARTA: Scalable and Principled Benchmark of Tree-Structured Multi-hop QA over Text and Tables

Authors: Sungho Park, Jueun Kim, Wook-Shin Han
Published: 2026-02-26
Categories: cs.CL, cs.AI, cs.DB, cs.IR
arXiv: https://arxiv.org/abs/2602.23286v1

Real-world Table-Text question answering (QA) tasks require models that can reason across long text and source tables, traversing multiple hops and executing complex operations such as aggregation. Yet existing benchmarks are small, manually curated - and therefore error-prone - and contain shallow questions that seldom demand more than two hops or invoke aggregations, grouping, or other advanced analytical operations expressible in natural-language queries. We present SPARTA, an end-to-end construction framework that automatically generates large-scale Table-Text QA benchmarks with lightweight human validation, requiring only one quarter of the annotation time of HybridQA. The framework first constructs a reference fact database by enriching each source table with grounding tables whose tuples are atomic facts automatically extracted from the accompanying unstructured passages, then synthesizes nested queries whose number of nested predicates matches the desired hop count. To ensure that every SQL statement is executable and that its verbalization yields a fluent, human-sounding question, we propose two novel techniques: provenance-based refinement, which rewrites any syntactically valid query that returns a non-empty result, and realistic-structure enforcement, which confines generation to post-order traversals of the query graph. The resulting pipeline produces thousands of high-fidelity question-answer pairs covering aggregations, grouping, and deep multi-hop reasoning across text and tables. On SPARTA, state-of-the-art models that reach over 70 F1 on HybridQA or over 50 F1 on OTT-QA drop by more than 30 F1 points, exposing fundamental weaknesses in current cross-modal reasoning. Our benchmark, construction code, and baseline models are available at https://github.com/pshlego/SPARTA/tree/main.

---

### ODEBrain: Continuous-Time EEG Graph for Modeling Dynamic Brain Networks

Authors: Haohui Jia, Zheng Chen, Lingwei Zhu, Rikuto Kotoge, Jathurshan Pradeepkumar, Yasuko Matsubara, Jimeng Sun, Yasushi Sakurai, Takashi Matsubara
Published: 2026-02-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.23285v2

Modeling neural population dynamics is crucial for foundational neuroscientific research and various clinical applications. Conventional latent variable methods typically model continuous brain dynamics through discretizing time with recurrent architecture, which necessarily results in compounded cumulative prediction errors and failure of capturing instantaneous, nonlinear characteristics of EEGs. We propose ODEBRAIN, a Neural ODE latent dynamic forecasting framework to overcome these challenges by integrating spatio-temporal-frequency features into spectral graph nodes, followed by a Neural ODE modeling the continuous latent dynamics. Our design ensures that latent representations can capture stochastic variations of complex brain states at any given time point. Extensive experiments verify that ODEBRAIN can improve significantly over existing methods in forecasting EEG dynamics with enhanced robustness and generalization capabilities.

---

### Mollified Value Learning

Authors: Hrishikesh Viswanath, Juanwu Lu, S. Talha Bukhari, Mihir Chauhan, Damon Conover, Ziran Wang, Aniket Bera
Published: 2026-02-26
Categories: cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2602.23280v2

Offline goal-conditioned reinforcement learning (GCRL) learns goal-reaching behaviors from static datasets, but accurate value estimation remains challenging under limited state-action coverage. Existing physics-informed approaches address this by imposing pointwise distance-like geometric constraints derived from Hamilton--Jacobi--Bellman (HJB) optimality principles, often through first-order partial differential equations such as the Eikonal equation. However, enforcing local consistency through explicit differential structure can become unstable in complex, high-dimensional environments. Our key insight is to instead reinterpret distance-like constraints as an expectation over a local spatial measure. By aggregating constraints over this measure rather than evaluating them pointwise, the objective acts as a spatial mollifier, inducing distance-like value geometry without requiring expensive differential operators. We refer to this as Mollified Value Learning (MVL). Experiments across navigation and high-dimensional robotic manipulation tasks show that MVL learns structured, value representations, improving goal-reaching performance, when used with implicit value representation learning methods. Open-source codes are available at https://github.com/HrishikeshVish/MVL.

---

### Zeroth-Order Stackelberg Control in Combinatorial Congestion Games

Authors: Saeed Masiha, Sepehr Elahi, Negar Kiyavash, Patrick Thiran
Published: 2026-02-26
Categories: cs.GT, cs.LG
arXiv: https://arxiv.org/abs/2602.23277v1

We study Stackelberg (leader--follower) tuning of network parameters (tolls, capacities, incentives) in combinatorial congestion games, where selfish users choose discrete routes (or other combinatorial strategies) and settle at a congestion equilibrium. The leader minimizes a system-level objective (e.g., total travel time) evaluated at equilibrium, but this objective is typically nonsmooth because the set of used strategies can change abruptly. We propose ZO-Stackelberg, which couples a projection-free Frank--Wolfe equilibrium solver with a zeroth-order outer update, avoiding differentiation through equilibria. We prove convergence to generalized Goldstein stationary points of the true equilibrium objective, with explicit dependence on the equilibrium approximation error, and analyze subsampled oracles: if an exact minimizer is sampled with probability $κ_m$, then the Frank--Wolfe error decays as $\mathcal{O}(1/(κ_m T))$. We also propose stratified sampling as a practical way to avoid a vanishing $κ_m$ when the strategies that matter most for the Wardrop equilibrium concentrate in a few dominant combinatorial classes (e.g., short paths). Experiments on real-world networks demonstrate that our method achieves orders-of-magnitude speedups over a differentiation-based baseline while converging to follower equilibria.

---

### CXReasonAgent: Evidence-Grounded Diagnostic Reasoning Agent for Chest X-rays

Authors: Hyungyung Lee, Hangyul Yoon, Edward Choi
Published: 2026-02-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.23276v2

Chest X-ray plays a central role in thoracic diagnosis, and its interpretation inherently requires multi-step, evidence-grounded reasoning. However, large vision-language models (LVLMs) often generate plausible responses that are not faithfully grounded in diagnostic evidence and provide limited visual evidence for verification, while also requiring costly retraining to support new diagnostic tasks, limiting their reliability and adaptability in clinical settings. To address these limitations, we present CXReasonAgent, a diagnostic agent that integrates a large language model (LLM) with clinically grounded diagnostic tools to perform evidence-grounded diagnostic reasoning using image-derived diagnostic and visual evidence. To evaluate these capabilities, we introduce CXReasonDial, a multi-turn dialogue benchmark with 1,946 dialogues across 12 diagnostic tasks, and show that CXReasonAgent produces faithfully grounded responses, enabling more reliable and verifiable diagnostic reasoning than LVLMs. These findings highlight the importance of integrating clinically grounded diagnostic tools, particularly in safety-critical clinical settings. The demo is available \href{https://ttumyche.github.io/cxreasonagent/#demo}{here}.

---

### Evaluating Stochasticity in Deep Research Agents

Authors: Haotian Zhai, Elias Stengel-Eskin, Pratik Patil, Liu Leqi
Published: 2026-02-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.23271v1

Deep Research Agents (DRAs) are promising agentic systems that gather and synthesize information to support research across domains such as financial decision-making, medical analysis, and scientific discovery. Despite recent improvements in research quality (e.g., outcome accuracy when ground truth is available), DRA system design often overlooks a critical barrier to real-world deployment: stochasticity. Under identical queries, repeated executions of DRAs can exhibit substantial variability in terms of research outcome, findings, and citations. In this paper, we formalize the study of stochasticity in DRAs by modeling them as information acquisition Markov Decision Processes. We introduce an evaluation framework that quantifies variance in the system and identify three sources of it: information acquisition, information compression, and inference. Through controlled experiments, we investigate how stochasticity from these modules across different decision steps influences the variance of DRA outputs. Our results show that reducing stochasticity can improve research output quality, with inference and early-stage stochasticity contributing the most to DRA output variance. Based on these findings, we propose strategies for mitigating stochasticity while maintaining output quality via structured output and ensemble-based query generation. Our experiments on DeepSearchQA show that our proposed mitigation methods reduce average stochasticity by 22% while maintaining high research quality.

---

### Discourse-Aware Dual-Track Streaming Response for Low-Latency Spoken Dialogue Systems

Authors: Siyuan Liu, Jiahui Xu, Feng Jiang, Kuang Wang, Zefeng Zhao, Chu-Ren Huang, Jinghang Gu, Changqing Yin, Haizhou Li
Published: 2026-02-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.23266v1

Achieving human-like responsiveness is a critical yet challenging goal for cascaded spoken dialogue systems. Conventional ASR-LLM-TTS pipelines follow a strictly sequential paradigm, requiring complete transcription and full reasoning before speech synthesis can begin, which results in high response latency. We propose the Discourse-Aware Dual-Track Streaming Response (DDTSR) framework, a low-latency architecture that enables listen-while-thinking and speak-while-thinking. DDTSR is built upon three key mechanisms: (1) connective-guided small-large model synergy, where an auxiliary small model generates minimal-committal discourse connectives while a large model performs knowledge-intensive reasoning in parallel; (2) streaming-based cross-modal collaboration, which dynamically overlaps ASR, LLM inference, and TTS to advance the earliest speakable moment; and (3) curriculum-learning-based discourse continuity enhancement, which maintains coherence and logical consistency between early responses and subsequent reasoning outputs. Experiments on two spoken dialogue benchmarks demonstrate that DDTSR reduces response latency by 19%-51% while preserving discourse quality. Further analysis shows that DDTSR functions as a plug-and-play module compatible with diverse LLM backbones, and remains robust across varying utterance lengths, indicating strong practicality and scalability for real-time spoken interaction.

---

### Decomposing Private Image Generation via Coarse-to-Fine Wavelet Modeling

Authors: Jasmine Bayrooti, Weiwei Kong, Natalia Ponomareva, Carlos Esteves, Ameesh Makadia, Amanda Prorok
Published: 2026-02-26
Categories: cs.CV, cs.CR
arXiv: https://arxiv.org/abs/2602.23262v1

Generative models trained on sensitive image datasets risk memorizing and reproducing individual training examples, making strong privacy guarantees essential. While differential privacy (DP) provides a principled framework for such guarantees, standard DP finetuning (e.g., with DP-SGD) often results in severe degradation of image quality, particularly in high-frequency textures, due to the indiscriminate addition of noise across all model parameters. In this work, we propose a spectral DP framework based on the hypothesis that the most privacy-sensitive portions of an image are often low-frequency components in the wavelet space (e.g., facial features and object shapes) while high-frequency components are largely generic and public. Based on this hypothesis, we propose the following two-stage framework for DP image generation with coarse image intermediaries: (1) DP finetune an autoregressive spectral image tokenizer model on the low-resolution wavelet coefficients of the sensitive images, and (2) perform high-resolution upsampling using a publicly pretrained super-resolution model. By restricting the privacy budget to the global structures of the image in the first stage, and leveraging the post-processing property of DP for detail refinement, we achieve promising trade-offs between privacy and utility. Experiments on the MS-COCO and MM-CelebA-HQ datasets show that our method generates images with improved quality and style capture relative to other leading DP image frameworks.

---

### Risk-Aware World Model Predictive Control for Generalizable End-to-End Autonomous Driving

Authors: Jiangxin Sun, Feng Xue, Teng Long, Chang Liu, Jian-Fang Hu, Wei-Shi Zheng, Nicu Sebe
Published: 2026-02-26
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2602.23259v1

With advances in imitation learning (IL) and large-scale driving datasets, end-to-end autonomous driving (E2E-AD) has made great progress recently. Currently, IL-based methods have become a mainstream paradigm: models rely on standard driving behaviors given by experts, and learn to minimize the discrepancy between their actions and expert actions. However, this objective of "only driving like the expert" suffers from limited generalization: when encountering rare or unseen long-tail scenarios outside the distribution of expert demonstrations, models tend to produce unsafe decisions in the absence of prior experience. This raises a fundamental question: Can an E2E-AD system make reliable decisions without any expert action supervision? Motivated by this, we propose a unified framework named Risk-aware World Model Predictive Control (RaWMPC) to address this generalization dilemma through robust control, without reliance on expert demonstrations. Practically, RaWMPC leverages a world model to predict the consequences of multiple candidate actions and selects low-risk actions through explicit risk evaluation. To endow the world model with the ability to predict the outcomes of risky driving behaviors, we design a risk-aware interaction strategy that systematically exposes the world model to hazardous behaviors, making catastrophic outcomes predictable and thus avoidable. Furthermore, to generate low-risk candidate actions at test time, we introduce a self-evaluation distillation method to distill riskavoidance capabilities from the well-trained world model into a generative action proposal network without any expert demonstration. Extensive experiments show that RaWMPC outperforms state-of-the-art methods in both in-distribution and out-of-distribution scenarios, while providing superior decision interpretability.

---

### MASRubric: Auditing Information Flow in Multi-Agent Systems with Failure-Distilled Pitfall Rubrics

Authors: Yutong Wang, Siyuan Xiong, Xuebo Liu, Wenkang Zhou, Liang Ding, Miao Zhang, Min Zhang
Published: 2026-02-26
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.23258v3

While multi-agent systems (MAS) excel at complex reasoning, they are vulnerable to errors that intermediate agents introduce and downstream agents build upon. Auditing intermediate messages before they propagate requires an explicit standard, yet evaluation rubrics are typically authored by domain experts or written against a reference answer, neither of which is available for an unseen message at test time. We present MASRubric, a MAS information flow auditing framework with failure-distilled pitfall rubrics. Offline, trajectories on which the MAS has failed are automatically distilled into a reusable bank of pitfall criteria, each describing a recurrent error by its underlying misconception, the reasoning situations in which it arises, and the check that would expose it. Online, the criteria applicable to each intermediate message are retrieved from this off-the-shelf bank and checked one by one, and the resulting satisfaction rate decides whether the message is broadcast, returned to its author with diagnostic feedback for revision, or withheld. Empirical results demonstrate that MASRubric enhances MAS performance on both fixed and dynamic frameworks, achieving average accuracy gains of up to 2.83 points on math reasoning benchmarks and 1.74 points on code generation benchmarks. Further analysis shows that the retrieved criteria vary systematically with task types, and that the audit effort tracks task difficulty. Moreover, the bank transfers without re-mining to a system with a stronger backbone, which makes more adaptive and more efficient use of it. Our code and dataset are released at https://github.com/TonySY2/MASRubric.

---

### AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning

Authors: Yutong Wang, Siyuan Xiong, Xuebo Liu, Wenkang Zhou, Liang Ding, Miao Zhang, Min Zhang
Published: 2026-02-26
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.23258v2

While Multi-Agent Systems (MAS) excel in complex reasoning, they suffer from the cascading impact of erroneous information from individual agents. Current solutions often resort to rigid structural engineering or expensive fine-tuning, limiting their adaptability. We propose AgentDropoutV2 (ADv2), a test-time rectify-or-reject pruning framework that dynamically optimizes MAS information flow. Acting as an active firewall, ADv2 intercepts agent outputs and employs a retrieval-augmented rectifier to iteratively correct errors. This rectification is guided by an indicator pool, which is constructed offline by distilling error patterns from historical MAS failure trajectories. Irreparable outputs are subsequently pruned to prevent error propagation. Empirical results demonstrate that ADv2 significantly boosts performance on both fixed and dynamic MAS frameworks, achieving average accuracy gains of 6.39 and 2.28 percentage points on extensive math and code benchmarks, respectively. Furthermore, ADv2 exhibits remarkable adaptivity, dynamically modulating rectification efforts based on task difficulty to resolve a wide spectrum of error patterns. Our code is released at https://github.com/TonySY2/AgentDropoutV2.

---

### Mitigating Legibility Tax with Decoupled Prover-Verifier Games

Authors: Yegon Kim, Juho Lee
Published: 2026-02-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.23248v2

As large language models become increasingly capable, it is critical that their outputs can be easily checked by less capable systems. Prover-verifier games can be used to improve checkability of model outputs, but display a degradation in accuracy compared to a baseline trained only to maximize correctness -- a phenonemon named legibility tax. We propose a solution by decoupling the correctness from the checkability condition and instead training a "translator" model that turns a fixed solver model's solution into a checkable form. This allows us to first train the solver to maximize correctness, and then train the translator to translate the solver into a checkable form while retaining the solver's answer. To accommodate this new objective of translation, we formulate a decoupled prover-verifier game (DPVG) where the equilibria correspond to faithful and checkable translators.

---

### A Model-Free Universal AI

Authors: Yegon Kim, Juho Lee
Published: 2026-02-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.23242v4

In general reinforcement learning, all established optimal agents, including AIXI, are model-based, explicitly maintaining and using environment models. This paper introduces Universal AI with Q-Induction (AIQI), the first model-free agent proven to be asymptotically $\varepsilon$-optimal in general RL. AIQI performs universal induction over distributional action-value functions, instead of policies or environments like previous works. Under a grain of truth condition, we prove that AIQI is strong asymptotically $\varepsilon$-optimal and asymptotically $\varepsilon$-Bayes-optimal. We also apply our novel proof techniques to show asymptotic $\varepsilon$-optimality of Self-AIXI without any ad-hoc assumptions. Our results significantly expand the diversity of known universal agents.

---

### Agency and Architectural Limits: Why Optimization-Based Systems Cannot Be Norm-Responsive

Authors: Radha Sarma
Published: 2026-02-26
Categories: cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2602.23239v2

AI systems are increasingly deployed in high-stakes contexts (medical diagnosis, legal research, financial analysis) under the assumption they can be governed by norms. This paper demonstrates that the assumption is formally invalid for optimization-based systems, specifically Large Language Models trained via Reinforcement Learning from Human Feedback (RLHF). Genuine agency requires two necessary and jointly sufficient architectural conditions. First, the capacity to maintain certain boundaries as non-negotiable constraints rather than tradeable weights (Incommensurability). Second, a non-inferential mechanism capable of suspending processing when those boundaries are threatened (Apophatic Responsiveness). RLHF-based systems are constitutively incompatible with both conditions. The operations that make optimization powerful, unifying all values on a scalar metric and always selecting the highest-scoring output, are precisely the operations that preclude normative governance and agency. This incompatibility is not a correctable training bug awaiting a technical fix. It is a formal constraint inherent to what optimization is. Consequently, documented failure modes (sycophancy, hallucination, and unfaithful reasoning) are not accidents but expected structural manifestations. Misaligned deployment triggers a second-order risk termed the Convergence Crisis. When humans are forced to verify AI outputs under metric pressure, they degrade from genuine agents into criteria-checking optimizers, eliminating the only component capable of bearing normative accountability. Beyond the incompatibility proof, this paper's primary positive contribution is a substrate-neutral architectural specification deriving what any system (biological, artificial, or institutional) must necessarily satisfy to qualify as a genuine agent rather than a sophisticated instrument.

---

### Spatio-Temporal Token Pruning for Efficient High-Resolution GUI Agents

Authors: Zhou Xu, Bowen Zhou, Qi Wang, Shuwen Feng, Jingyu Xiao
Published: 2026-02-26
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.23235v1

Pure-vision GUI agents provide universal interaction capabilities but suffer from severe efficiency bottlenecks due to the massive spatiotemporal redundancy inherent in high-resolution screenshots and historical trajectories. We identify two critical misalignments in existing compression paradigms: the temporal mismatch, where uniform history encoding diverges from the agent's "fading memory" attention pattern, and the spatial topology conflict, where unstructured pruning compromises the grid integrity required for precise coordinate grounding, inducing spatial hallucinations. To address these challenges, we introduce GUIPruner, a training-free framework tailored for high-resolution GUI navigation. It synergizes Temporal-Adaptive Resolution (TAR), which eliminates historical redundancy via decay-based resizing, and Stratified Structure-aware Pruning (SSP), which prioritizes interactive foregrounds and semantic anchors while safeguarding global layout. Extensive evaluations across diverse benchmarks demonstrate that GUIPruner consistently achieves state-of-the-art performance, effectively preventing the collapse observed in large-scale models under high compression. Notably, on Qwen2-VL-2B, our method delivers a 3.4x reduction in FLOPs and a 3.3x speedup in vision encoding latency while retaining over 94% of the original performance, enabling real-time, high-precision navigation with minimal resource consumption.

---

### Scaling Search Relevance: Augmenting App Store Ranking with LLM-Generated Judgments

Authors: Evangelia Christakopoulou, Vivekkumar Patel, Hemanth Velaga, Sandip Gaikwad, Sean Suchter, Venkat Sundaranatha
Published: 2026-02-26
Categories: cs.IR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.23234v5

Large-scale commercial search systems optimize for relevance to drive successful sessions that help users find what they are looking for. To maximize relevance, we leverage two complementary objectives: behavioral relevance (results users tend to click or download) and textual relevance (a result's semantic fit to the query). A persistent challenge is the scarcity of expert-provided textual relevance labels relative to abundant behavioral relevance labels. We first address this by systematically evaluating LLM configurations, finding that a specialized, fine-tuned model significantly outperforms a much larger pre-trained one in providing highly relevant labels. Using this optimal model as a force multiplier, we generate millions of textual relevance labels to overcome the data scarcity. We show that augmenting our production ranker with these textual relevance labels leads to a significant outward shift of the Pareto frontier: offline NDCG improves for behavioral relevance while simultaneously increasing for textual relevance. These offline gains were validated by a worldwide A/B test on the App Store ranker, which demonstrated a statistically significant +0.24% increase in conversion rate, with the most substantial performance gains occurring in tail queries, where the new textual relevance labels provide a robust signal in the absence of reliable behavioral relevance labels.

---

### ReCoN-Ipsundrum: An Inspectable Recurrent Persistence Loop Agent with Affect-Coupled Control and Mechanism-Linked Consciousness Indicator Assays

Authors: Aishik Sanyal
Published: 2026-02-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.23232v2

Indicator-based approaches to machine consciousness recommend mechanism-linked evidence triangulated across tasks, supported by architectural inspection and causal intervention. Inspired by Humphrey's ipsundrum hypothesis, we implement ReCoN-Ipsundrum, an inspectable agent that extends a ReCoN state machine with a recurrent persistence loop over sensory salience $N^s$ and an optional affect proxy reporting valence/arousal. Across fixed-parameter ablations (ReCoN, Ipsundrum, Ipsundrum+affect), we operationalize Humphrey's qualiaphilia (preference for sensory experience for its own sake) as a familiarity-controlled scenic-over-dull route choice. We find a novelty dissociation: non-affect variants are novelty-sensitive ($Δ$scenic-entry = 0.07). Affect coupling is stable ($Δ$scenic-entry = 0.01) even when scenic is less novel (median {$Δ$novelty $\approx$ -0.43). In reward-free exploratory play, the affect variant shows structured local investigation (scan events 31.4 vs. 0.9; cycle score 7.6). In a pain-tail probe, only the affect variant sustains prolonged planned caution (tail duration 90 vs. 5). Lesioning feedback+integration selectively reduces post-stimulus persistence in ipsundrum variants (AUC drop 27.62, 27.9%) while leaving ReCoN unchanged. These dissociations link recurrence $\rightarrow$ persistence and affect-coupled control $\rightarrow$ preference stability, scanning, and lingering caution, illustrating how indicator-like signatures can be engineered and why mechanistic and causal evidence should accompany behavioral markers.

---