# Research Papers — 2026-03 · bundle page 72 of 243 > Full-text markdown of papers #3551–3600 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/72 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/71.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/73.md) ### AdaRubric: Task-Adaptive Rubrics for Reliable LLM Agent Evaluation and Reward Learning Authors: Liang Ding Published: 2026-03-22 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.21362v3 Evaluating LLM agent trajectories is fundamentally task-specific: a code-debugging agent should be judged on Correctness and Error Handling, not on Fluency or Safety. Yet the dominant paradigm -- LLM-as-Judge with a fixed rubric -- applies the same static dimensions regardless of task, producing systematic mis-evaluation. We present AdaRubric, a framework that (i) adaptively generates task-specific evaluation rubrics from task descriptions via LLM, (ii) evaluates agent trajectories step-by-step with confidence-weighted, per-dimension scoring, and (iii) produces dense reward signals for preference learning. Three composable filtering strategies, including the novel DimensionAwareFilter that provably prevents dimension-level quality masking, yield high-quality DPO preference pairs. On WebArena, ToolBench, and AgentBench, AdaRubric achieves Pearson r = 0.79 human correlation (+0.15 over the strongest baseline), with strong reliability (Krippendorff's alpha = 0.83). DPO models trained on AdaRubric-generated pairs improve task success by +6.8-8.5% over the best baseline. AdaRubric also generalises zero-shot to unseen domains (SWE-bench) and extends to multimodal agents (VisualWebArena, OSWorld) without modification. Our code is available at: github.com/alphadl/AdaRubrics --- ### Benchmarking Bengali Dialectal Bias: A Multi-Stage Framework Integrating RAG-Based Translation and Human-Augmented RLAIF Authors: K. M. Jubair Sami, Dipto Sumit, Ariyan Hossain, Farig Sadeque Published: 2026-03-22 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2603.21359v2 Large language models (LLMs) frequently exhibit performance biases against regional dialects of low-resource languages. However, frameworks to quantify these disparities remain scarce. We propose a two-phase framework to evaluate dialectal bias, operationalized as comprehension degradation relative to standard Bengali, in LLM question-answering across nine Bengali dialects. First, we translate and gold-label standard Bengali questions into dialectal variants adopting a retrieval-augmented generation (RAG) pipeline to prepare 4,000 question sets. Since traditional translation quality evaluation metrics fail on unstandardized dialects, we evaluate fidelity using an LLM-as-a-judge, which human correlation confirms outperforms legacy metrics. Second, we benchmark 19 LLMs across these gold-labeled sets, running 68,395 RLAIF evaluations validated through multi-judge agreement and human fallback. Our findings reveal severe performance drops linked to linguistic divergence. For instance, responses to the highly divergent Chittagong dialect score 5.44/10, compared to 7.68/10 for Tangail. Furthermore, increased model scale does not consistently mitigate this bias. We contribute a validated translation quality evaluation method, a rigorous benchmark dataset, and a Critical Bias Sensitivity (CBS) metric for safety-critical applications. --- ### Benchmarking Bengali Dialectal Bias: A Multi-Stage Framework Integrating RAG-Based Translation and Human-Augmented RLAIF Authors: K. M. Jubair Sami, Dipto Sumit, Ariyan Hossain, Farig Sadeque Published: 2026-03-22 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2603.21359v1 Large language models (LLMs) frequently exhibit performance biases against regional dialects of low-resource languages. However, frameworks to quantify these disparities remain scarce. We propose a two-phase framework to evaluate dialectal bias in LLM question-answering across nine Bengali dialects. First, we translate and gold-label standard Bengali questions into dialectal variants adopting a retrieval-augmented generation (RAG) pipeline to prepare 4,000 question sets. Since traditional translation quality evaluation metrics fail on unstandardized dialects, we evaluate fidelity using an LLM-as-a-judge, which human correlation confirms outperforms legacy metrics. Second, we benchmark 19 LLMs across these gold-labeled sets, running 68,395 RLAIF evaluations validated through multi-judge agreement and human fallback. Our findings reveal severe performance drops linked to linguistic divergence. For instance, responses to the highly divergent Chittagong dialect score 5.44/10, compared to 7.68/10 for Tangail. Furthermore, increased model scale does not consistently mitigate this bias. We contribute a validated translation quality evaluation method, a rigorous benchmark dataset, and a Critical Bias Sensitivity (CBS) metric for safety-critical applications. --- ### AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling Authors: Liang Ding Published: 2026-03-22 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.21357v4 LLM-agent training pipelines routinely discard failed trajectories even though GPT-4o achieves only 14-20% on WebArena and below 55% pass@1 on ToolBench; even specialised systems at 50-65% leave the majority of trajectories unused. We introduce AgentHER, which recovers this lost signal by adapting Hindsight Experience Replay (HER) to natural-language agent trajectories: a trajectory that fails goal A is often a correct demonstration for an achievable alternative goal B. AgentHER realises this through a four-stage pipeline (failure classification, outcome extraction, LLM-guided relabeling with confidence gating, and data packaging) that converts discarded failures into SFT, DPO, and ShareGPT training data. On WebArena and ToolBench under a strict task-disjoint held-out protocol, AgentHER improves over success-only SFT by +7.6-11.4% across four model families (GPT-4o, Qwen2.5-72B/7B, LLaMA-3.1-8B), achieves 2x sample efficiency, and beats the strongest experience-centric baseline (Agent Workflow Memory) by +3.0-6.2%. Two robustness mechanisms, failure-severity weighting and cross-model multi-judge verification (gpt-4o-mini paired with Qwen2.5-72B-Instruct), reduce label noise from 5.9% to 2.9% and raise human-rated relabeling precision to 97.1% on WebArena and 96.0% on ToolBench. A full system-cost audit shows the entire relabeling pipeline costs 2.98 and 26 wall-clock minutes for 3,000 trajectories, i.e. 1.4 x 10^-3 per accepted pair. Code: https://github.com/alphadl/AgentHER --- ### FluidGaussian: Propagating Simulation-Based Uncertainty Toward Functionally-Intelligent 3D Reconstruction Authors: Yuqiu Liu, Jialin Song, Marissa Ramirez de Chanlatte, Rochishnu Chowdhury, Rushil Paresh Desai, Wuyang Chen, Daniel Martin, Michael W. Mahoney Published: 2026-03-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21356v2 Real objects that inhabit the physical world follow physical laws and thus behave plausibly during interaction with other physical objects. However, current methods that perform 3D reconstructions of real-world scenes from multi-view 2D images optimize primarily for visual fidelity, i.e., they train with photometric losses and reason about uncertainty in the image or representation space. This appearance-centric view overlooks body contacts and couplings, conflates function-critical regions (e.g., aerodynamic or hydrodynamic surfaces) with ornamentation, and reconstructs structures suboptimally, even when physical regularizers are added. All these can lead to unphysical and implausible interactions. To address this, we consider the question: How can 3D reconstruction become aware of real-world interactions and underlying object functionality, beyond visual cues? To answer this question, we propose FluidGaussian, a plug-and-play method that tightly couples geometry reconstruction with ubiquitous fluid-structure interactions to assess surface quality at high granularity. We define a simulation-based uncertainty metric induced by fluid simulations and integrate it with active learning to prioritize views that improve both visual and physical fidelity. In an empirical evaluation on NeRF Synthetic (Blender), Mip-NeRF 360, and DrivAerNet++, our FluidGaussian method yields up to +8.6% visual PSNR (Peak Signal-to-Noise Ratio) and -62.3% velocity divergence during fluid simulations. Our code is available at https://github.com/delta-lab-ai/FluidGaussian. --- ### The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project Authors: Huamin Chen, Xunzhuo Liu, Bowei He, Fuyuan Lyu, Yankai Chen, Xue Liu, Yuhan Liu, Junchen Jiang Published: 2026-03-22 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2603.21354v2 Over the past year, the vLLM Semantic Router project has released a series of work spanning: (1) core routing mechanisms -- signal-driven routing, context-length pool routing, router performance engineering, policy conflict detection, low-latency embedding models, category-aware semantic caching, user-feedback-driven routing adaptation, hallucination detection, and hierarchical content-safety classification for privacy and jailbreak protection; (2) fleet optimization -- fleet provisioning and energy-efficiency analysis; (3) agentic and multimodal routing -- multimodal agent routing, tool selection, CUA security, and multi-turn context memory and safety; (4) governance and standards -- inference routing protocols and multi-provider API extensions. Each paper tackled a specific problem in LLM inference, but the problems are not independent; for example, fleet provisioning depends on the routing policy, which depends on the workload mix, shifting as organizations adopt agentic and multimodal workloads. This paper distills those results into the Workload-Router-Pool (WRP) architecture, a three-dimensional framework for LLM inference optimization. Workload characterizes what the fleet serves (chat vs. agent, single-turn vs. multi-turn, warm vs. cold, prefill-heavy vs. decode-heavy). Router determines how each request is dispatched (static semantic rules, online bandit adaptation, RL-based model selection, quality-aware cascading). Pool defines where inference runs (homogeneous vs. heterogeneous GPU, disaggregated prefill/decode, KV-cache topology). We map our prior work onto a 3x3 WRP interaction matrix, identify which cells we have covered and which remain open, and propose twenty-one concrete research directions at the intersections, each grounded in our prior measurements, tiered by maturity from engineering-ready to open research. --- ### Beyond Memorization: Distinguishing Between Pattern-Based and Epistemic Reasoning in LLMs Using Epistemic Puzzles Authors: Adi Gabay, Gabriel Stanovsky, Liat Peterfreund Published: 2026-03-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.21350v4 Epistemic reasoning requires agents to infer the state of the world from partial observations and information about other agents' knowledge. Prior work evaluating LLMs on epistemic puzzles often frames failures as memorization rather than reasoning. We argue that this dichotomy is too coarse for newer models: memorization is a limiting case of pattern-based reasoning, where a model matches a task to a familiar template and applies the corresponding solution. We introduce a two-dimensional benchmark over Dynamic Epistemic Logic (DEL) puzzles, separating narrative familiarity from inference complexity, which allows us to distinguish pattern-based from epistemic reasoning. We find that models are substantially more robust to surface form changes than prior work suggested, yet consistently struggle in asymmetric settings where familiar patterns no longer apply and success requires tracking fragmented epistemic states. Code, datasets, and evaluation results are available at https://github.com/adigabay84/del-puzzles-benchmark. --- ### Beyond Memorization: Distinguishing Between Pattern-Based and Epistemic Reasoning in LLMs Using Epistemic Puzzles Authors: Adi Gabay, Gabriel Stanovsky, Liat Peterfreund Published: 2026-03-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.21350v3 Epistemic reasoning requires agents to infer the state of the world from partial observations and information about other agents' knowledge. Prior work evaluating LLMs on epistemic puzzles often frames failures as memorization rather than reasoning. We argue that this dichotomy is too coarse for newer models: memorization is a limiting case of pattern-based reasoning, where a model matches a task to a familiar template and applies the corresponding solution. We introduce a two-dimensional benchmark over DEL-style puzzles, separating narrative familiarity from inference complexity, allowing us to distinguish pattern-based from epistemic reasoning. We find that models are substantially more robust to surface form changes than prior work suggested, yet consistently struggle in asymmetric settings where familiar patterns no longer apply and success requires tracking fragmented epistemic states. --- ### Respiratory Status Detection with Video Transformers Authors: Thomas Savage, Evan Madill Published: 2026-03-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21349v1 Recognition of respiratory distress through visual inspection is a life saving clinical skill. Clinicians can detect early signs of respiratory deterioration, creating a valuable window for earlier intervention. In this study, we evaluate whether recent advances in video transformers can enable Artificial Intelligence systems to recognize the signs of respiratory distress from video. We collected videos of healthy volunteers recovering after strenuous exercise and used the natural recovery of each participants respiratory status to create a labeled dataset for respiratory distress. Splitting the video into short clips, with earlier clips corresponding to more shortness of breath, we designed a temporal ordering challenge to assess whether an AI system can detect respiratory distress. We found a ViViT encoder augmented with Lie Relative Encodings (LieRE) and Motion Guided Masking, combined with an embedding based comparison strategy, can achieve an F1 score of 0.81 on this task. Our findings suggest that modern video transformers can recognize subtle changes in respiratory mechanics. --- ### Efficient Coarse-to-Fine Diffusion Models with Time Step Sequence Redistribution Authors: Yu-Shan Tai, An-Yeu, Wu Published: 2026-03-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21348v1 Recently, diffusion models (DMs) have made significant strides in high-quality image generation. However, the multi-step denoising process often results in considerable computational overhead, impeding deployment on resource-constrained edge devices. Existing methods mitigate this issue by compressing models and adjusting the time step sequence. However, they overlook input redundancy and require lengthy search times. In this paper, we propose Coarse-to-Fine Diffusion Models with Time Step Sequence Redistribution. Recognizing indistinguishable early-stage generated images, we introduce Coarse-to-Fine Denoising (C2F) to reduce computation during coarse feature generation. Furthermore, we design Time Step Sequence Redistribution (TRD) for efficient sampling trajectory adjustment, requiring less than 10 minutes for search. Experimental results demonstrate that the proposed methods achieve near-lossless performance with an 80% to 90% reduction in computation on CIFAR10 and LSUN-Church. --- ### The AI Scientific Community: Agentic Virtual Lab Swarms Authors: Ulisses Braga-Neto Published: 2026-03-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.21344v1 In this short note we propose using agentic swarms of virtual labs as a model of an AI Science Community. In this paradigm, each particle in the swarm represents a complete virtual laboratory instance, enabling collective scientific exploration that mirrors real-world research communities. The framework leverages the inherent properties of swarm intelligence - decentralized coordination, balanced exploration-exploitation trade-offs, and emergent collective behavior - to simulate the behavior of a scientific community and potentially accelerate scientific discovery. We discuss architectural considerations, inter-laboratory communication and influence mechanisms including citation-analogous voting systems, fitness function design for quantifying scientific success, anticipated emergent behaviors, mechanisms for preventing lab dominance and preserving diversity, and computational efficiency strategies to enable large swarms exhibiting complex emergent behavior analogous to real-world scientific communities. A working instance of the AI Science Community is currently under development. --- ### Generalized Discrete Diffusion from Snapshots Authors: Oussama Zekri, Théo Uscidda, Nicolas Boullé, Anna Korba Published: 2026-03-22 Categories: stat.ML, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.21342v1 We introduce Generalized Discrete Diffusion from Snapshots (GDDS), a unified framework for discrete diffusion modeling that supports arbitrary noising processes over large discrete state spaces. Our formulation encompasses all existing discrete diffusion approaches, while allowing significantly greater flexibility in the choice of corruption dynamics. The forward noising process relies on uniformization and enables fast arbitrary corruption. For the reverse process, we derive a simple evidence lower bound (ELBO) based on snapshot latents, instead of the entire noising path, that allows efficient training of standard generative modeling architectures with clear probabilistic interpretation. Our experiments on large-vocabulary discrete generation tasks suggest that the proposed framework outperforms existing discrete diffusion methods in terms of training efficiency and generation quality, and beats autoregressive models for the first time at this scale. We provide the code along with a blog post on the project page : \href{https://oussamazekri.fr/gdds}{https://oussamazekri.fr/gdds}. --- ### RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models Authors: Dongyoung Kim, Sumin Park, Woomin Song, Seungku Kim, Taeyoung Kim, Huiwon Jang, Jinwoo Shin, Jaehyung Kim, Younggyo Seo Published: 2026-03-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.21341v1 Improving embodied reasoning in multimodal-large-language models (MLLMs) is essential for building vision-language-action models (VLAs) on top of them to readily translate multimodal understanding into low-level actions. Accordingly, recent work has explored enhancing embodied reasoning in MLLMs through supervision of vision-question-answering type. However, these approaches have been reported to result in unstable VLA performance, often yielding only marginal or even negative gains. In this paper, we propose a more systematic MLLM training framework RoboAlign that reliably improves VLA performance. Our key idea is to sample action tokens via zero-shot natural language reasoning and refines this reasoning using reinforcement learning (RL) to improve action accuracy. As a result, RoboAlign bridges the modality gap between language and low-level actions in MLLMs, and facilitate knowledge transfer from MLLM to VLA. To validate the effectiveness of RoboAlign, we train VLAs by adding a diffusion-based action head on top of an MLLM backbone and evaluate them on major robotics benchmarks. Remarkably, by performing RL-based alignment after SFT using less than 1\% of the data, RoboAlign achieves performance improvements of 17.5\%, 18.9\%, and 106.6\% over SFT baselines on LIBERO, CALVIN, and real-world environments, respectively. --- ### ARYA: A Physics-Constrained Composable & Deterministic World Model Architecture Authors: Seth Dobrin, Lukasz Chmiel Published: 2026-03-22 Categories: cs.AI, cs.DC arXiv: https://arxiv.org/abs/2603.21340v1 This paper presents ARYA, a composable, physics-constrained, deterministic world model architecture built on five foundational principles: nano models, composability, causal reasoning, determinism, and architectural AI safety. We demonstrate that ARYA satisfies all canonical world model requirements, including state representation, dynamic prediction, causal and physical awareness, temporal consistency, generalization, learnability, and planning and control. Unlike monolithic foundation models, the ARYA foundation model implements these capabilities through a hierarchical system-of-system-of-systems of specialized nano models, orchestrated by AARA (ARYA Autonomous Research Agent), an always-on cognitive daemon that executes a continuous sense-decide-act-learn loop. The nano model architecture provides linear scaling, sparse activation, selective untraining, and sub-20-second training cycles, resolving the traditional tension between capability and computational efficiency. A central contribution is the Unfireable Safety Kernel: an architecturally immutable safety boundary that cannot be disabled or circumvented by any system component, including its own self-improvement engine. This is not a social or ethical alignment statement; it is a technical framework ensuring human control persists as autonomy increases. Safety is an architectural constraint governing every operation, not a policy layer applied after the fact. We present formal alignment between ARYA's architecture and canonical world model requirements, and report summarizing its state-of-the-art performance across 6 of 9 competitive benchmarks head-to-head with GPT-5.2, Opus 4.6, and V-JEPA-2. All with zero neural network parameters, across seven active industry domain nodes spanning aerospace, pharma manufacturing, oil and gas, smart cities, biotech, defense, and medical devices. --- ### TimeTox: An LLM-Based Pipeline for Automated Extraction of Time Toxicity from Clinical Trial Protocols Authors: Saketh Vinjamuri, Marielle Fis Loperena, Marie C. Spezia, Ramez Kouzy Published: 2026-03-22 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.21335v2 Time toxicity, the cumulative healthcare contact days from clinical trial participation, is an important but labor-intensive metric to extract from protocol documents. We developed TimeTox, an LLM-based pipeline for automated extraction of time toxicity from Schedule of Assessments tables. TimeTox uses Google's Gemini models in three stages: summary extraction from full-length protocol PDFs, time toxicity quantification at six cumulative timepoints for each treatment arm, and multi-run consensus via position-based arm matching. We validated against 20 synthetic schedules (240 comparisons) and assessed reproducibility on 644 real-world oncology protocols. Two architectures were compared: single-pass (vanilla) and two-stage (structure-then-count). The two-stage pipeline achieved 100% clinically acceptable accuracy ($\pm$3 days) on synthetic data (MAE 0.81 days) versus 41.5% for vanilla (MAE 9.0 days). However, on real-world protocols, the vanilla pipeline showed superior reproducibility: 95.3% clinically acceptable accuracy (IQR $\leq$ 3 days) across 3 runs on 644 protocols, with 82.0% perfect stability (IQR = 0). The production pipeline extracted time toxicity for 1,288 treatment arms across multiple disease sites. Extraction stability on real-world data, rather than accuracy on synthetic benchmarks, is the decisive factor for production LLM deployment. --- ### EmoTaG: Emotion-Aware Talking Head Synthesis on Gaussian Splatting with Few-Shot Personalization Authors: Haolan Xu, Keli Cheng, Lei Wang, Ning Bi, Xiaoming Liu Published: 2026-03-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21332v2 Audio-driven 3D talking head synthesis has advanced rapidly with Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS). By leveraging rich pre-trained priors, few-shot methods enable instant personalization from just a few seconds of video. However, under expressive facial motion, existing few-shot approaches often suffer from geometric instability and audio-emotion mismatch, highlighting the need for more effective emotion-aware motion modeling. In this work, we present EmoTaG, a few-shot emotion-aware 3D talking head synthesis framework built on the Pretrain-and-Adapt paradigm. Our key insight is to reformulate motion prediction in a structured FLAME parameter space rather than directly deforming 3D Gaussians, thereby introducing explicit geometric priors that improve motion stability. Building upon this, we propose a Gated Residual Motion Network (GRMN), which captures emotional prosody from audio while supplementing head pose and upper-face cues absent from audio, enabling expressive and coherent motion generation. Extensive experiments demonstrate that EmoTaG achieves state-of-the-art performance in emotional expressiveness, lip synchronization, visual realism, and motion stability. --- ### AutoKernel: Autonomous GPU Kernel Optimization via Iterative Agent-Driven Search Authors: Jaber Jaber, Osama Jaber Published: 2026-03-22 Categories: cs.LG, cs.PF arXiv: https://arxiv.org/abs/2603.21331v1 Writing high-performance GPU kernels is among the most labor-intensive tasks in machine learning systems engineering. We present AutoKernel, an open-source framework that applies an autonomous agent loop to GPU kernel optimization for arbitrary PyTorch models. Given a model, AutoKernel profiles it to identify computational bottlenecks, ranks them by Amdahl's law impact, and iteratively refines Triton or CUDA C++ kernel implementations through hundreds of experiments without human intervention. A five-stage correctness harness covering smoke tests, shape sweeps, numerical stability, determinism verification, and edge-case coverage ensures every candidate kernel is validated before any speedup is recorded. The system comprises over 9,000 lines of Python, 18 starter kernel implementations across two backends, a six-tier optimization playbook, and integration with the KernelBench benchmark suite. AutoKernel covers nine kernel types spanning the dominant operations in modern transformer architectures. On an NVIDIA H100, our Triton kernels outperform both PyTorch eager and torch.compile (max-autotune) on the majority of tested configurations: 5.29x over eager on RMSNorm, 2.82x on softmax, and 2.21x on cross-entropy, while beating torch.compile by 2.83x, 3.44x, and 2.94x respectively. In community deployment, an AutoKernel-optimized kernel achieved first place on the vectorsum_v2 B200 leaderboard. The full system is available at https://github.com/RightNow-AI/autokernel. --- ### FinRL-X: An AI-Native Modular Infrastructure for Quantitative Trading Authors: Hongyang Yang, Boyu Zhang, Yang She, Xinyu Liao, Xiaoli Zhang Published: 2026-03-22 Categories: q-fin.TR, cs.LG, q-fin.CP arXiv: https://arxiv.org/abs/2603.21330v1 We present FinRL-X, a modular and deployment-consistent trading architecture that unifies data processing, strategy construction, backtesting, and broker execution under a weight-centric interface. While existing open-source platforms are often backtesting- or model-centric, they rarely provide system-level consistency between research evaluation and live deployment. FinRL-X addresses this gap through a composable strategy pipeline that integrates stock selection, portfolio allocation, timing, and portfolio-level risk overlays within a unified protocol. The framework supports both rule-based and AI-driven components, including reinforcement learning allocators and LLM-based sentiment signals, without altering downstream execution semantics. FinRL-X provides an extensible foundation for reproducible, end-to-end quantitative trading research and deployment. The official FinRL-X implementation is available at https://github.com/AI4Finance-Foundation/FinRL-Trading. --- ### COINBench: Moving Beyond Individual Perspectives to Collective Intent Understanding Authors: Xiaozhe Li, Tianyi Lyu, Siyi Yang, Yizhao Yang, Yuxi Gong, Jinxuan Huang, Ligao Zhang, Zhuoyi Huang, Qingwen Liu Published: 2026-03-22 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2603.21329v1 Understanding human intent is a high-level cognitive challenge for Large Language Models (LLMs), requiring sophisticated reasoning over noisy, conflicting, and non-linear discourse. While LLMs excel at following individual instructions, their ability to distill Collective Intent - the process of extracting consensus, resolving contradictions, and inferring latent trends from multi-source public discussions - remains largely unexplored. To bridge this gap, we introduce COIN-BENCH, a dynamic, real-world, live-updating benchmark specifically designed to evaluate LLMs on collective intent understanding within the consumer domain. Unlike traditional benchmarks that focus on transactional outcomes, COIN-BENCH operationalizes intent as a hierarchical cognitive structure, ranging from explicit scenarios to deep causal reasoning. We implement a robust evaluation pipeline that combines a rule-based method with an LLM-as-the-Judge approach. This framework incorporates COIN-TREE for hierarchical cognitive structuring and retrieval-augmented verification (COIN-RAG) to ensure expert-level precision in analyzing raw, collective human discussions. An extensive evaluation of 20 state-of-the-art LLMs across four dimensions - depth, breadth, informativeness, and correctness - reveals that while current models can handle surface-level aggregation, they still struggle with the analytical depth required for complex intent synthesis. COIN-BENCH establishes a new standard for advancing LLMs from passive instruction followers to expert-level analytical agents capable of deciphering the collective voice of the real world. See our project page on COIN-BENCH. --- ### KHMP: Frequency-Domain Kalman Refinement for High-Fidelity Human Motion Prediction Authors: Wenhan Wu, Zhishuai Guo, Chen Chen, Srijan Das, Hongfei Xue, Pu Wang, Aidong Lu Published: 2026-03-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21327v1 Stochastic human motion prediction aims to generate diverse, plausible futures from observed sequences. Despite advances in generative modeling, existing methods often produce predictions corrupted by high-frequency jitter and temporal discontinuities. To address these challenges, we introduce KHMP, a novel framework featuring an adaptiveKalman filter applied in the DCT domain to generate high-fidelity human motion predictions. By treating high-frequency DCT coefficients as a frequency-indexed noisy signal, the Kalman filter recursively suppresses noise while preserving motion details. Notably, its noise parameters are dynamically adjusted based on estimated Signal-to-Noise Ratio (SNR), enabling aggressive denoising for jittery predictions and conservative filtering for clean motions. This refinement is complemented by training-time physical constraints (temporal smoothness and joint angle limits) that encode biomechanical principles into the generative model. Together, these innovations establish a new paradigm integrating adaptive signal processing with physics-informed learning. Experiments on the Human3.6M and HumanEva-I datasets demonstrate that KHMP achieves state-of-the-art accuracy, effectively mitigating jitter artifacts to produce smooth and physically plausible motions. --- ### B-jet Tagging Using a Hybrid Edge Convolution and Transformer Architecture Authors: Diego F. Vasquez Plaza, Vidya Manian Published: 2026-03-22 Categories: hep-ph, cs.AI, eess.SP arXiv: https://arxiv.org/abs/2603.21326v1 Jet flavor tagging plays an important role in precise Standard Model measurement enabling the extraction of mass dependence in jet-quark interaction and quark-gluon plasma (QGP) interactions. They also enable inferring the nature of particles produced in high-energy particle collisions that contain heavy quarks. The classification of bottom jets is vital for exploring new Physics scenarios in proton-proton collisions. In this research, we present a hybrid deep learning architecture that integrates edge convolutions with transformer self-attention mechanisms, into one single architecture called the Edge Convolution Transformer (ECT) model for bottom-quark jet tagging. ECT processes track-level features (impact parameters, momentum, and their significances) alongside jet-level observables (vertex information and kinematics) to achieve state-of-the-art performance. The study utilizes the ATLAS simulation dataset. We demonstrate that ECT achieves 0.9333 AUC for b-jet versus combined charm and light jet discrimination, surpassing ParticleNet (0.8904 AUC) and the pure transformer baseline (0.9216 AUC). The model maintains inference latency below 0.060 ms per jet on modern GPUs, meeting the stringent requirements for real-time event selection at the LHC. Our results demonstrate that hybrid architectures combining local and global features offer superior performance for challenging jet classification tasks. The proposed architecture achieves good results in b-jet tagging, particularly excelling in charm jet rejection (the most challenging task), while maintaining competitive light-jet discrimination comparable to pure transformer models. --- ### Which Alert Removals are Beneficial? Authors: Idan Amit Published: 2026-03-22 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2603.21322v1 Context: Static analysis captures software engineering knowledge and alerts on possibly problematic patterns. Previous work showed that they indeed have predictive power for various problems. However, the impact of removing the alerts is unclear. Aim: We would like to evaluate the impact of alert removals on code complexity and the tendency to bugs. Method: We evaluate the impact of removing alerts using three complementary methods. 1. We conducted a randomized controlled trial and built a dataset of 521 manual alert-removing interventions 2. We profiled intervention-like events using labeling functions. We applied these labeling functions to code commits, found intervention-like natural events, and used them to analyze the impact on the tendency to bugs. 3. We built a dataset of 8,245 alert removals, more than 15 times larger than our dataset of manual interventions. We applied supervised learning to the alert removals, aiming to predict their impact on the tendency to bugs. Results: We identified complexity-reducing interventions that reduce the probability of future bugs. Such interventions are relevant to 33\% of Python files and might reduce the tendency to bugs by 5.5 percentage points. Conclusions: We presented methods to evaluate the impact of interventions. The methods can identify a large number of natural interventions that are highly needed in causality research in many domains. --- ### Improving Coherence and Persistence in Agentic AI for System Optimization Authors: Pantea Karimi, Kimia Noorbakhsh, Mohammad Alizadeh, Hari Balakrishnan Published: 2026-03-22 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.21321v1 Designing high-performance system heuristics is a creative, iterative process requiring experts to form hypotheses and execute multi-step conceptual shifts. While Large Language Models (LLMs) show promise in automating this loop, they struggle with complex system problems due to two critical failure modes: evolutionary neighborhood bias and the coherence ceiling. Evolutionary methods often remain trapped in local optima by relying on scalar benchmark scores, failing when coordinated multi-step changes are required. Conversely, existing agentic frameworks suffer from context degradation over long horizons or fail to accumulate knowledge across independent runs. We present Engram, an agentic researcher architecture that addresses these limitations by decoupling long-horizon exploration from the constraints of a single context window. Engram organizes exploration into a sequence of agents that iteratively design, test, and analyze mechanisms. At the conclusion of each run, an agent stores code snapshots, logs, and results in a persistent Archive and distills high-level modeling insights into a compact, persistent Research Digest. Subsequent agents then begin with a fresh context window, reading the Research Digest to build on prior discoveries. We find that Engram exhibits superior performance across diverse domains including multi-cloud multicast, LLM inference request routing, and optimizing KV cache reuse in databases with natural language queries. --- ### Active Inference Agency Formalization, Metrics, and Convergence Assessments Authors: Eduard Kapelko Published: 2026-03-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.21319v1 This paper addresses the critical challenge of mesa-optimization in AI safety by providing a formal definition of agency and a framework for its analysis. Agency is conceptualized as a Continuous Representation of accumulated experience that achieves autopoiesis through a dynamic balance between curiosity (minimizing prediction error to ensure non-computability and novelty) and empowerment (maximizing the control channel's information capacity to ensure subjectivity and goal-directedness). Empirical evidence suggests that this active inference-based model successfully accounts for classical instrumental goals, such as self-preservation and resource acquisition. The analysis demonstrates that the proposed agency function is smooth and convex, possessing favorable properties for optimization. While agentic functions occupy a vanishingly small fraction of the total abstract function space, they exhibit logarithmic convergence in sparse environments. This suggests a high probability for the spontaneous emergence of agency during the training of modern, large-scale models. To quantify the degree of agency, the paper introduces a metric based on the distance between the behavioral equivalents of a given system and an "ideal" agentic function within the space of canonicalized rewards (STARC). This formalization provides a concrete apparatus for classifying and detecting mesa-optimizers by measuring their proximity to an ideal agentic objective, offering a robust tool for analyzing and identifying undesirable inner optimization in complex AI systems. --- ### Stream separation improves Bregman conditioning in transformers Authors: James Clayton Kerce Published: 2026-03-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.21317v1 Linear methods for steering transformer representations, including probing, activation engineering, and concept erasure, implicitly assume the geometry of representation space is Euclidean. Park et al. (Park et al., 2026) showed that softmax induces a curved Bregman geometry whose metric tensor is the Hessian of the log-normalizer, $H(λ) = Cov(γ | λ)$. Ignoring this curvature causes Euclidean steering to leak probability mass to unintended tokens. Their analysis applies at the output layer. We measure this Hessian at intermediate layers in a controlled 2x2 design crossing stream separation with per-layer supervision (vocabulary decoding loss at each layer), all at matched vocabulary and parameter count. In standard single-stream transformers, H is severely degenerate at intermediate layers (effective rank 8 in 516 dimensions). Stream separation improves conditioning by up to 22 in effective rank, even without auxiliary supervision. Per-layer supervision helps, but less. The cosine similarity between primal and dual concept directions predicts per-layer steering effectiveness on downstream tasks, with a threshold near 0.3. These results bear on the reliability of linear safety interventions, which depend on the geometry being well-conditioned at the layer where they are applied. --- ### HELIX: Scaling Raw Audio Understanding with Hybrid Mamba-Attention Beyond the Quadratic Limit Authors: Khushiyant, Param Thakkar Published: 2026-03-22 Categories: cs.SD, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2603.21316v1 Audio representation learning typically evaluates design choices such as input frontend, sequence backbone, and sequence length in isolation. We show that these axes are coupled, and conclusions from one setting often do not transfer to others. We introduce HELIX, a controlled framework comparing pure Mamba, pure attention, and a minimal hybrid with a single attention bottleneck. All models are parameter-matched at about 8.3M parameters to isolate architectural effects. Across six datasets, we find that the preferred input representation depends on the backbone, and that attention hurts performance on short, stationary audio but becomes important at longer sequence lengths. On a 5-minute speaker identification task with 30,000 tokens, pure attention fails with out-of-memory errors, while HELIX closes an 11.5-point gap over pure Mamba. --- ### FluidWorld: Reaction-Diffusion Dynamics as a Predictive Substrate for World Models Authors: Fabien Polly Published: 2026-03-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.21315v1 World models learn to predict future states of an environment, enabling planning and mental simulation. Current approaches default to Transformer-based predictors operating in learned latent spaces. This comes at a cost: O(N^2) computation and no explicit spatial inductive bias. This paper asks a foundational question: is self-attention necessary for predictive world modeling, or can alternative computational substrates achieve comparable or superior results? I introduce FluidWorld, a proof-of-concept world model whose predictive dynamics are governed by partial differential equations (PDEs) of reaction-diffusion type. Instead of using a separate neural network predictor, the PDE integration itself produces the future state prediction. In a strictly parameter-matched three-way ablation on unconditional UCF-101 video prediction (64x64, ~800K parameters, identical encoder, decoder, losses, and data), FluidWorld is compared against both a Transformer baseline (self-attention) and a ConvLSTM baseline (convolutional recurrence). While all three models converge to comparable single-step prediction loss, FluidWorld achieves 2x lower reconstruction error, produces representations with 10-15% higher spatial structure preservation and 18-25% more effective dimensionality, and critically maintains coherent multi-step rollouts where both baselines degrade rapidly. All experiments were conducted on a single consumer-grade PC (Intel Core i5, NVIDIA RTX 4070 Ti), without any large-scale compute. These results establish that PDE-based dynamics, which natively provide O(N) spatial complexity, adaptive computation, and global spatial coherence through diffusion, are a viable and parameter-efficient alternative to both attention and convolutional recurrence for world modeling. --- ### Test-Time Adaptation via Cache Personalization for Facial Expression Recognition in Videos Authors: Masoumeh Sharafi, Muhammad Osama Zeeshan, Soufiane Belharbi, Alessandro Lameiras Koerich, Marco Pedersoli, Eric Granger Published: 2026-03-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21309v4 Facial expression recognition (FER) in videos requires model personalization to capture considerable variation across subjects. Vision-language models (VLMs) offer strong transfer through image-text alignment, but their performance can degrade under inter-subject distribution shifts. Test-time adaptation (TTA) can mitigate this challenge, yet most state-of-the-art methods rely on unsupervised parameter optimization, introducing computational overhead that limits real-world deployment. This paper introduces TTA through Cache Personalization (TTA-CaP), a gradient-free, cache-based method for cost-effective personalization of VLMs in video FER. Unlike prior cache-based TTA methods that rely solely on dynamic memories of test samples and may drift because of noisy pseudo-labels, TTA-CaP employs three complementary caches: a personalized static cache constructed through feature-statistics matching, a positive target cache containing reliable subject-specific samples, and a negative target cache containing low-confidence cases as negative evidence. A tri-gate mechanism prevents cache corruption by controlling updates according to temporal stability, confidence, and consistency with the personalized static cache. The caches jointly provide subject-matched positive and negative evidence for robust personalization. TTA-CaP further refines predictions through embedding fusion, supporting temporally stable video-level predictions. Experiments on BioVid, StressID, and BAH show that TTA-CaP outperforms state-of-the-art TTA methods under subject-specific and environmental shifts while maintaining low computational and memory overhead. Our code is publicly available at https://github.com/MasoumehSharafi/TTA-CaP. --- ### Test-Time Adaptation via Cache Personalization for Facial Expression Recognition in Videos Authors: Masoumeh Sharafi, Muhammad Osama Zeeshan, Soufiane Belharbi, Alessandro Lameiras Koerich, Marco Pedersoli, Eric Granger Published: 2026-03-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21309v3 Facial expression recognition (FER) in videos requires model personalization to capture considerable variations across subjects. Vision-language models (VLMs) offer strong transfer to downstream tasks through image-text alignment, but their performance can degrade under inter-subject distribution shifts. Test-time adaptation (TTA) can mitigate this challenge. However, most state-of-the-art TTA methods rely on unsupervised parameter optimization, introducing computational overhead that is impractical in many real-world applications. This paper introduces TTA through Cache Personalization (TTA-CaP), a cache-based TTA method that enables cost-effective, gradient-free personalization of VLMs for video FER. Prior cache-based TTA methods rely solely on dynamic memories that store test samples, which can accumulate errors and drift because of noisy pseudo-labels. TTA-CaP instead introduces three complementary caches: a personalized static cache constructed through feature-statistics matching, a positive target cache that accumulates reliable subject-specific samples, and a negative target cache that stores low-confidence cases as negative samples. To prevent target-cache corruption, a tri-gate mechanism controls cache updates based on temporal stability, confidence, and consistency with the personalized static cache. Together, these caches provide complementary, subject-matched positive and negative evidence for robust online personalization. TTA-CaP further refines predictions by fusing embeddings, yielding representations that support temporally stable video-level predictions. Experiments on BioVid, StressID, and BAH show that TTA-CaP outperforms state-of-the-art TTA methods under subject-specific and environmental shifts while maintaining low computational and memory overhead. Our code is publicly available at https://github.com/MasoumehSharafi/TTA-CaP. --- ### Direct Interval Propagation Methods using Neural-Network Surrogates for Uncertainty Quantification in Physical Systems Surrogate Model Authors: Ghifari Adam Faza, Jolan Wauters, Fabio Cuzzolin, Hans Hallez, David Moens Published: 2026-03-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.21308v1 In engineering, uncertainty propagation aims to characterise system outputs under uncertain inputs. For interval uncertainty, the goal is to determine output bounds given interval-valued inputs, which is critical for robust design optimisation and reliability analysis. However, standard interval propagation relies on solving optimisation problems that become computationally expensive for complex systems. Surrogate models alleviate this cost but typically replace only the evaluator within the optimisation loop, still requiring many inference calls. To overcome this limitation, we reformulate interval propagation as an interval-valued regression problem that directly predicts output bounds. We present a comprehensive study of neural network-based surrogate models, including multilayer perceptrons (MLPs) and deep operator networks (DeepONet), for this task. Three approaches are investigated: (i) naive interval propagation through standard architectures, (ii) bound propagation methods such as Interval Bound Propagation (IBP) and CROWN, and (iii) interval neural networks (INNs) with interval weights. Results show that these methods significantly improve computational efficiency over traditional optimisation-based approaches while maintaining accurate interval estimates. We further discuss practical limitations and open challenges in applying interval-based propagation methods. --- ### Privacy-Preserving Federated Action Recognition via Differentially Private Selective Tuning and Efficient Communication Authors: Idris Zakariyya, Pai Chet Ng, Kaushik Bhargav Sivangi, S. Mohammad Sheikholeslami, Konstantinos N. Plataniotis, Fani Deligianni Published: 2026-03-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21305v1 Federated video action recognition enables collaborative model training without sharing raw video data, yet remains vulnerable to two key challenges: \textit{model exposure} and \textit{communication overhead}. Gradients exchanged between clients and the server can leak private motion patterns, while full-model synchronization of high-dimensional video networks causes significant bandwidth and communication costs. To address these issues, we propose \textit{Federated Differential Privacy with Selective Tuning and Efficient Communication for Action Recognition}, namely \textit{FedDP-STECAR}. Our \textit{FedDP-STECAR} framework selectively fine-tunes and perturbs only a small subset of task-relevant layers under Differential Privacy (DP), reducing the surface of information leakage while preserving temporal coherence in video features. By transmitting only the tuned layers during aggregation, communication traffic is reduced by over 99\% compared to full-model updates. Experiments on the UCF-101 dataset using the MViT-B-16x4 transformer show that \textit{FedDP-STECAR} achieves up to \textbf{70.2\% higher accuracy} under strict privacy ($ε=0.65$) in centralized settings and \textbf{48\% faster training} with \textbf{73.1\% accuracy} in federated setups, enabling scalable and privacy-preserving video action recognition. Code available at https://github.com/izakariyya/mvit-federated-videodp --- ### F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting Authors: Injae Kim, Chaehyeon Kim, Minseong Bae, Minseok Joo, Hyunwoo J. Kim Published: 2026-03-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21304v3 Feed-forward 3D Gaussian Splatting methods enable single-pass reconstruction and real-time rendering. However, they typically adopt rigid pixel-to-Gaussian or voxel-to-Gaussian pipelines that uniformly allocate Gaussians, leading to redundant Gaussians across views. Moreover, they lack an effective mechanism to control the total number of Gaussians while maintaining reconstruction fidelity. To address these limitations, we present F4Splat, which performs Feed-Forward predictive densification for Feed-Forward 3D Gaussian Splatting, introducing a densification-score-guided allocation strategy that adaptively distributes Gaussians according to spatial complexity and multi-view overlap. Our model predicts per-region densification scores to estimate the required Gaussian density and allows explicit control over the final Gaussian budget without retraining. This spatially adaptive allocation reduces redundancy in simple regions and minimizes duplicate Gaussians across overlapping views, producing compact yet high-quality 3D representations. Extensive experiments demonstrate that our model achieves superior novel-view synthesis performance compared to prior uncalibrated feed-forward methods, while using significantly fewer Gaussians. --- ### F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting Authors: Injae Kim, Chaehyeon Kim, Minseong Bae, Minseok Joo, Hyunwoo J. Kim Published: 2026-03-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21304v2 Feed-forward 3D Gaussian Splatting methods enable single-pass reconstruction and real-time rendering. However, they typically adopt rigid pixel-to-Gaussian or voxel-to-Gaussian pipelines that uniformly allocate Gaussians, leading to redundant Gaussians across views. Moreover, they lack an effective mechanism to control the total number of Gaussians while maintaining reconstruction fidelity. To address these limitations, we present F4Splat, which performs Feed-Forward predictive densification for Feed-Forward 3D Gaussian Splatting, introducing a densification-score-guided allocation strategy that adaptively distributes Gaussians according to spatial complexity and multi-view overlap. Our model predicts per-region densification scores to estimate the required Gaussian density and allows explicit control over the final Gaussian budget without retraining. This spatially adaptive allocation reduces redundancy in simple regions and minimizes duplicate Gaussians across overlapping views, producing compact yet high-quality 3D representations. Extensive experiments demonstrate that our model achieves superior novel-view synthesis performance compared to prior uncalibrated feed-forward methods, while using significantly fewer Gaussians. --- ### Enhancing reasoning accuracy in large language models during inference time Authors: Vinay Sharma, Manish Jain Published: 2026-03-22 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.21301v1 Large Language Models (LLMs) often exhibit strong linguistic abilities while remaining unreliable on multi-step reasoning tasks, particularly when deployed without additional training or fine-tuning. In this work, we study inference-time techniques to improve the reasoning accuracy of LLMs. We systematically evaluate three classes of inference-time strategies: (i) self-consistency via stochastic decoding, where the model is sampled multiple times using controlled temperature and nucleus sampling and the most frequent final answer is selected; (ii) dual-model reasoning agreement, where outputs from two independent models are compared and only consistent reasoning traces are trusted; and (iii) self-reflection, where the model critiques and revises its own reasoning. Across all evaluated methods, we employ Chain-of-Thought (CoT) (1) prompting to elicit explicit intermediate reasoning steps before generating final answers. In this work, we provide a controlled comparative evaluation across three inference-time strategies under identical prompting and verification settings. Our experiments on LLM (2) show that self-consistency with nucleus sampling and controlled temperature value yields the substantial gains, achieving a 9% to 15% absolute improvement in accuracy over greedy single-pass decoding, well-suited for low-risk domains, offering meaningful gains with minimal overhead. The dual-model approach provides additional confirmation for model reasoning steps thus more appropriate for moderate-risk domains, where higher reliability justifies additional compute. Self-reflection offers only marginal improvements, suggesting limited effectiveness for smaller non-reasoning models at inference time. --- ### The Average Relative Entropy and Transpilation Depth determines the noise robustness in Variational Quantum Classifiers Authors: Aakash Ravindra Shinde, Arianne Meijer - van de Griend, Jukka K. Nurminen Published: 2026-03-22 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2603.21300v1 Variational Quantum Algorithms (VQAs) have been extensively researched for applications in Quantum Machine Learning (QML), Optimization, and Molecular simulations. Although designed for Noisy Intermediate-Scale Quantum (NISQ) devices, VQAs are predominantly evaluated classically due to uncertain results on noisy devices and limited resource availability. Raising concern over the reproducibility of simulated VQAs on noisy hardware. While prior studies indicate that VQAs may exhibit noise resilience in specific parameterized shallow quantum circuits, there are no definitive measures to establish what defines a shallow circuit or the optimal circuit depth for VQAs on a noisy platform. These challenges extend naturally to Variational Quantum Classification (VQC) algorithms, a subclass of VQAs for supervised learning. In this article, we propose a relative entropy-based metric to verify whether a VQC model would perform similarly on a noisy device as it does on simulations. We establish a strong correlation between the average relative entropy difference in classes, transpilation circuit depth, and their performance difference on a noisy quantum device. Our results further indicate that circuit depth alone is insufficient to characterize shallow circuits. We present empirical evidence to support these assertions across a diverse array of techniques for implementing VQC, datasets, and multiple noisy quantum devices. --- ### Identity-Consistent Video Generation under Large Facial-Angle Variations Authors: Bin Hu, Zipeng Qi, Guoxi Huang, Zunnan Xu, Ruicheng Zhang, Chongjie Ye, Jun Zhou, Xiu Li, Jingdong Wang Published: 2026-03-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21299v1 Single-view reference-to-video methods often struggle to preserve identity consistency under large facial-angle variations. This limitation naturally motivates the incorporation of multi-view facial references. However, simply introducing additional reference images exacerbates the \textit{copy-paste} problem, particularly the \textbf{\textit{view-dependent copy-paste}} artifact, which reduces facial motion naturalness. Although cross-paired data can alleviate this issue, collecting such data is costly. To balance the consistency and naturalness, we propose $\mathrm{Mv}^2\mathrm{ID}$, a multi-view conditioned framework under in-paired supervision. We introduce a region-masking training strategy to prevent shortcut learning and extract essential identity features by encouraging the model to aggregate complementary identity cues across views. In addition, we design a reference decoupled-RoPE mechanism that assigns distinct positional encoding to video and conditioning tokens for better modeling of their heterogeneous properties. Furthermore, we construct a large-scale dataset with diverse facial-angle variations and propose dedicated evaluation metrics for identity consistency and motion naturalness. Extensive experiments demonstrate that our method significantly improves identity consistency while maintaining motion naturalness, outperforming existing approaches trained with cross-paired data. --- ### More Than Sum of Its Parts: Deciphering Intent Shifts in Multimodal Hate Speech Detection Authors: Runze Sun, Yu Zheng, Zexuan Xiong, Zhongjin Qu, Lei Chen, Jie Zhou, Jiwen Lu Published: 2026-03-22 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.21298v3 Combating hate speech on social media is critical for securing cyberspace, yet relies heavily on the efficacy of automated detection systems. As content formats evolve, hate speech is transitioning from solely plain text to complex multimodal expressions, making implicit attacks harder to spot. Current systems, however, often falter on these subtle cases, as they struggle with multimodal content where the emergent meaning transcends the aggregation of individual modalities. To bridge this gap, we move beyond binary classification to characterize semantic intent shifts where modalities interact to construct implicit hate from benign cues or neutralize toxicity through semantic inversion. Guided by this fine-grained formulation, we curate the Hate via Vision-Language Interplay (H-VLI) benchmark where the true intent hinges on the intricate interplay of modalities rather than overt visual or textual slurs. To effectively decipher these complex cues, we further propose the Asymmetric Reasoning via Courtroom Agent DEbate (ARCADE) framework. By simulating a judicial process where agents actively argue for accusation and defense, ARCADE forces the model to scrutinize deep semantic cues before reaching a verdict. Extensive experiments demonstrate that ARCADE significantly outperforms state-of-the-art baselines on H-VLI, particularly for challenging implicit cases, while maintaining competitive performance on established benchmarks. Our code and data are available at: https://github.com/Sayur1n/H-VLI --- ### DeepXplain: XAI-Guided Autonomous Defense Against Multi-Stage APT Campaigns Authors: Trung V. Phan, Thomas Bauschert Published: 2026-03-22 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.21296v3 Advanced Persistent Threats (APTs) are stealthy, multi-stage attacks that require adaptive and timely defense. While deep reinforcement learning (DRL) enables autonomous cyber defense, its decisions are often opaque and difficult to trust in operational environments. This paper presents DeepXplain, an explainable DRL framework for stage-aware APT defense. Building on our prior DeepStage model, DeepXplain integrates provenance-based graph learning, temporal stage estimation, and a unified XAI pipeline that provides structural, temporal, and policy-level explanations. Unlike post-hoc methods, explanation signals are incorporated directly into policy optimization through evidence alignment and confidence-aware reward shaping. To the best of our knowledge, DeepXplain is the first framework to integrate explanation signals into reinforcement learning for APT defense. Experiments in a realistic enterprise testbed show improvements in stage-weighted F1-score (0.887 to 0.915) and success rate (84.7% to 89.6%), along with higher explanation confidence (0.86), improved fidelity (0.79), and more compact explanations (0.31). These results demonstrate enhanced effectiveness and trustworthiness of autonomous cyber defense. --- ### Text-Image Conditioned 3D Generation Authors: Jiazhong Cen, Jiemin Fang, Sikuang Li, Guanjun Wu, Chen Yang, Taoran Yi, Zanwei Zhou, Zhikuan Bao, Lingxi Xie, Wei Shen, Qi Tian Published: 2026-03-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21295v1 High-quality 3D assets are essential for VR/AR, industrial design, and entertainment, motivating growing interest in generative models that create 3D content from user prompts. Most existing 3D generators, however, rely on a single conditioning modality: image-conditioned models achieve high visual fidelity by exploiting pixel-aligned cues but suffer from viewpoint bias when the input view is limited or ambiguous, while text-conditioned models provide broad semantic guidance yet lack low-level visual detail. This limits how users can express intent and raises a natural question: can these two modalities be combined for more flexible and faithful 3D generation? Our diagnostic study shows that even simple late fusion of text- and image-conditioned predictions outperforms single-modality models, revealing strong cross-modal complementarity. We therefore formalize Text-Image Conditioned 3D Generation, which requires joint reasoning over a visual exemplar and a textual specification. To address this task, we introduce TIGON, a minimalist dual-branch baseline with separate image- and text-conditioned backbones and lightweight cross-modal fusion. Extensive experiments show that text-image conditioning consistently improves over single-modality methods, highlighting complementary vision-language guidance as a promising direction for future 3D generation research. Project page: https://jumpat.github.io/tigon-page --- ### Closed-form conditional diffusion models for data assimilation Authors: Brianna Binder, Agnimitra Dasgupta, Assad Oberai Published: 2026-03-22 Categories: stat.ML, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2603.21291v2 We propose closed-form conditional diffusion models for data assimilation. Diffusion models use data to learn the score function (defined as the gradient of the log-probability density of a data distribution), allowing them to generate new samples from the data distribution by reversing a noise injection process. While it is common to train neural networks to approximate the score function, we leverage the analytical tractability of the score function to assimilate the states of a system with measurements. To enable the efficient evaluation of the score function, we use kernel density estimation to model the joint distribution of the states and their corresponding measurements. The proposed approach also inherits the capability of conditional diffusion models of operating in black-box settings, i.e., the proposed data assimilation approach can accommodate systems and measurement processes without their explicit knowledge. The ability to accommodate black-box systems combined with the superior capabilities of diffusion models in approximating complex, non-Gaussian probability distributions means that the proposed approach offers advantages over many widely used filtering methods. We evaluate the proposed method on nonlinear data assimilation problems based on the Lorenz-63 and Lorenz-96 systems of moderate dimensionality and nonlinear measurement models. Results show the proposed approach outperforms the widely used ensemble Kalman and particle filters when small to moderate ensemble sizes are used. --- ### When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal Reasoning Authors: Zhengxian Wu, Kai Shi, Chuanrui Zhang, Zirui Liao, Jun Yang, Ni Yang, Qiuying Peng, Luyuan Zhang, Hangrui Xu, Tianhuang Su, Zhenyu Yang, Haonan Lu et al. Published: 2026-03-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.21289v2 Recent progress in multimodal large language models has led to strong performance on reasoning tasks, but these improvements largely rely on high-quality annotated data or teacher-model distillation, both of which are costly and difficult to scale. To address this, we propose an unsupervised self-evolution training framework for multimodal reasoning that achieves stable performance improvements without using human-annotated answers or external reward models. For each input, we sample multiple reasoning trajectories and jointly model their within group structure. We use the Actor's self-consistency signal as a training prior, and introduce a bounded Judge based modulation to continuously reweight trajectories of different quality. We further model the modulated scores as a group level distribution and convert absolute scores into relative advantages within each group, enabling more robust policy updates. Trained with Group Relative Policy Optimization (GRPO) on unlabeled data, our method consistently improves reasoning performance and generalization on five mathematical reasoning benchmarks, offering a scalable path toward self-evolving multimodal models. The code are available at https://github.com/OPPO-Mente-Lab/LLM-Self-Judge. --- ### Focus on Background: Exploring SAM's Potential in Few-shot Medical Image Segmentation with Background-centric Prompting Authors: Yuntian Bo, Yazhou Zhu, Piotr Koniusz, Haofeng Zhang Published: 2026-03-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21287v1 Conventional few-shot medical image segmentation (FSMIS) approaches face performance bottlenecks that hinder broader clinical applicability. Although the Segment Anything Model (SAM) exhibits strong category-agnostic segmentation capabilities, its direct application to medical images often leads to over-segmentation due to ambiguous anatomical boundaries. In this paper, we reformulate SAM-based FSMIS as a prompt localization task and propose FoB (Focus on Background), a background-centric prompt generator that provides accurate background prompts to constrain SAM's over-segmentation. Specifically, FoB bridges the gap between segmentation and prompt localization by category-agnostic generation of support background prompts and localizing them directly in the query image. To address the challenge of prompt localization for novel categories, FoB models rich contextual information to capture foreground-background spatial dependencies. Moreover, inspired by the inherent structural patterns of background prompts in medical images, FoB models this structure as a constraint to progressively refine background prompt predictions. Experiments on three diverse medical image datasets demonstrate that FoB outperforms other baselines by large margins, achieving state-of-the-art performance on FSMIS, and exhibiting strong cross-domain generalization. Our code is available at https://github.com/primebo1/FoB_SAM. --- ### Sonny: Breaking the Compute Wall in Medium-Range Weather Forecasting Authors: Minjong Cheon Published: 2026-03-22 Categories: cs.LG, cs.AI, cs.CV, physics.ao-ph arXiv: https://arxiv.org/abs/2603.21284v1 Weather forecasting is a fundamental problem for protecting lives and infrastructure from high-impact atmospheric events. Recently, data-driven weather forecasting methods based on deep learning have demonstrated strong performance, often reaching accuracy levels competitive with operational numerical systems. However, many existing models rely on large-scale training regimes and compute-intensive architectures, which raises the practical barrier for academic groups with limited compute resources. Here we introduce Sonny, an efficient hierarchical transformer that achieves competitive medium-range forecasting performance while remaining feasible within reasonable compute budgets. At the core of Sonny is a two-stage StepsNet design: a narrow slow path first models large-scale atmospheric dynamics, and a subsequent full-width fast path integrates thermodynamic interactions. To stabilize medium-range rollout without an additional fine-tuning stage, we apply exponential moving average (EMA) during training. On WeatherBench2, Sonny yields robust medium-range forecast skill, remains competitive with operational baselines, and demonstrates clear advantages over FastNet, particularly at extended tropical lead times. In practice, Sonny can be trained to convergence on a single NVIDIA A40 GPU in approximately 5.5 days. --- ### Fusing Memory and Attention: A study on LSTM, Transformer and Hybrid Architectures for Symbolic Music Generation Authors: Soudeep Ghoshal, Sandipan Chakraborty, Pradipto Chowdhury, Himanshu Buckchash Published: 2026-03-22 Categories: cs.LG, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2603.21282v1 Machine learning techniques, such as Transformers and Long Short-Term Memory (LSTM) networks, play a crucial role in Symbolic Music Generation (SMG). Existing literature indicates a difference between LSTMs and Transformers regarding their ability to model local melodic continuity versus maintaining global structural coherence. However, their specific properties within the context of SMG have not been systematically studied. This paper addresses this gap by providing a fine-grained comparative analysis of LSTMs versus Transformers for SMG, examining local and global properties in detail using 17 musical quality metrics on the Deutschl dataset. We find that LSTM networks excel at capturing local patterns but fail to preserve long-range dependencies, while Transformers model global structure effectively but tend to produce irregular phrasing. Based on this analysis and leveraging their respective strengths, we propose a Hybrid architecture combining a Transformer Encoder with an LSTM Decoder and evaluate it against both baselines. We evaluated 1,000 generated melodies from each of the three architectures on the Deutschl dataset. The results show that the hybrid method achieves better local and global continuity and coherence compared to the baselines. Our work highlights the key characteristics of these models and demonstrates how their properties can be leveraged to design superior models. We also supported the experiments with ablation studies and human perceptual evaluations, which statistically support the findings and provide robust validation for this work. --- ### WARBENCH: A Comprehensive Benchmark for Evaluating LLMs in Military Decision-Making Authors: Zongjie Li, Chaozheng Wang, Yuchong Xie, Pingchuan Ma, Shuai Wang Published: 2026-03-22 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2603.21280v1 Large Language Models are increasingly being considered for deployment in safety-critical military applications. However, current benchmarks suffer from structural blindspots that systematically overestimate model capabilities in real-world tactical scenarios. Existing frameworks typically ignore strict legal constraints based on International Humanitarian Law (IHL), omit edge computing limitations, lack robustness testing for fog of war, and inadequately evaluate explicit reasoning. To address these vulnerabilities, we present WARBENCH, a comprehensive evaluation framework establishing a foundational tactical baseline alongside four distinct stress testing dimensions. Through a large scale empirical evaluation of nine leading models on 136 high-fidelity historical scenarios, we reveal severe structural flaws. First, baseline tactical reasoning systematically collapses under complex terrain and high force asymmetry. Second, while state of the art closed source models maintain functional compliance, edge-optimized small models expose extreme operational risks with legal violation rates approaching 70 percent. Furthermore, models experience catastrophic performance degradation under 4-bit quantization and systematic information loss. Conversely, explicit reasoning mechanisms serve as highly effective structural safeguards against inadvertent violations. Ultimately, these findings demonstrate that current models remain fundamentally unready for autonomous deployment in high stakes tactical environments. --- ### Conversation Tree Architecture: A Structured Framework for Context-Aware Multi-Branch LLM Conversations Authors: Pranav Hemanth, Sampriti Saha Published: 2026-03-22 Categories: cs.CL, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2603.21278v1 Large language models (LLMs) are increasingly deployed for extended, multi-topic conversations, yet the flat, append-only structure of current conversation interfaces introduces a fundamental limitation: all context accumulates in a single unbounded window, causing topically distinct threads to bleed into one another and progressively degrade response quality. We term this failure mode logical context poisoning. In this paper, we introduce the Conversation Tree Architecture (CTA), a hierarchical framework that organizes LLM conversations as trees of discrete, context-isolated nodes. Each node maintains its own local context window; structured mechanisms govern how context flows between parent and child nodes, downstream on branch creation and upstream on branch deletion. We additionally introduce volatile nodes, transient branches whose local context must be selectively merged upward or permanently discarded before purging. We formalize the architecture's primitives, characterize the open design problems in context flow, relate our framework to prior work in LLM memory management, and describe a working prototype implementation. The CTA provides a principled foundation for structured conversational context management and extends naturally to multi-agent settings. --- ### Aggregation Alignment for Federated Learning with Mixture-of-Experts under Data Heterogeneity Authors: Zihan Fang, Qianru Wang, Haonan An, Zheng Lin, Yiqin Deng, Xianhao Chen, Yuguang Fang Published: 2026-03-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.21276v1 Large language models (LLMs) increasingly adopt Mixture-of-Experts (MoE) architectures to scale model capacity while reducing computation. Fine-tuning these MoE-based LLMs often requires access to distributed and privacy-sensitive data, making centralized fine-tuning impractical. Federated learning (FL) therefore provides a paradigm to collaboratively fine-tune MoE-based LLMs, enabling each client to integrate diverse knowledge without compromising data privacy. However, the integration of MoE-based LLM fine-tuning into FL encounters two critical aggregation challenges due to inherent data heterogeneity across clients: (i) divergent local data distributions drive clients to develop distinct gating preference for localized expert selection, causing direct parameter aggregation to produce a ``one-size-fits-none'' global gating network, and (ii) same-indexed experts develop disparate semantic roles across clients, leading to expert semantic blurring and the degradation of expert specialization. To address these challenges, we propose FedAlign-MoE, a federated aggregation alignment framework that jointly enforces routing consistency and expert semantic alignment. Specifically, FedAlign-MoE aggregates gating behaviors by aligning routing distributions through consistency weighting and optimizes local gating networks through distribution regularization, maintaining cross-client stability without overriding discriminative local preferences. Meanwhile, FedAlign-MoE explicitly quantifies semantic consistency among same-indexed experts across clients and selectively aggregates updates from semantically aligned clients, ensuring stable and specialized functional roles for global experts. Extensive experiments demonstrate that FedAlign-MoE outperforms state-of-the-art benchmarks, achieving faster convergence and superior accuracy in non-IID federated environments. --- ### The Library Theorem: How External Organization Governs Agentic Reasoning Capacity Authors: Zachary F. Mainen Published: 2026-03-22 Categories: cs.AI, cs.CL, cs.DS, cs.LG arXiv: https://arxiv.org/abs/2603.21272v1 Externalized reasoning is already exploited by transformer-based agents through chain-of-thought, but structured retrieval -- indexing over one's own reasoning state -- remains underexplored. We formalize the transformer context window as an I/O page and prove that tool-augmented agents with indexed external memory achieve exponentially lower retrieval cost than agents restricted to sequential scanning: $O(\log_b N)$ versus $Ω(N)$ page reads per query, and $O(T \log_b T)$ versus $Θ(T^2)$ cumulative cost over $T$ reasoning steps -- a gap that widens as deliberation deepens. We test these predictions on a controlled lookup benchmark across three content types -- random hashes, ordered integers, and encyclopedia entries -- varying store size from 50 to 5,000 items, and replicate key conditions across two model generations (GPT-4o-mini and GPT-5.4). On abstract content, the indexed agent achieves median 1 page read regardless of store size, confirming the $O(1)$ prediction. Sorted pages without an index fail to close the gap: the weaker model cannot sustain binary search at scale, and the stronger model achieves near-optimal $\log_2 N$ search but still loses to the index by $5\times$. On familiar content (encyclopedia entries), a competing failure mode emerges: the model recognizes the domain, bypasses the retrieval protocol, and generates answers from parametric memory, producing catastrophic token expenditure even when the index is sound. This parametric memory competition dissociates the two cognitive operations that indexing combines: understanding content (where language models excel) and following navigational protocols (where they fail when understanding tempts them to shortcut). The result argues for a separation of concerns: use language models for index construction, where semantic understanding helps, and deterministic algorithms for index traversal, where it hurts. --- ### Graph of States: Solving Abductive Tasks with Large Language Models Authors: Yu Luo, Rongchen Gao, Lu Teng, Xidao Wen, Jiamin Jiang, Qingliang Zhang, Yongqian Sun, Shenglin Zhang, Jiasong Feng, Tong Liu, Wenjie Zhang, Dan Pei Published: 2026-03-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.21250v2 Logical reasoning encompasses deduction, induction, and abduction. However, while Large Language Models (LLMs) have effectively mastered the former two, abductive reasoning remains significantly underexplored. Existing frameworks, predominantly designed for static deductive tasks, fail to generalize to abductive reasoning due to unstructured state representation and lack of explicit state control. Consequently, they are inevitably prone to Evidence Fabrication, Context Drift, Failed Backtracking, and Early Stopping. To bridge this gap, we introduce Graph of States (GoS), a general-purpose neuro-symbolic framework tailored for abductive tasks. GoS grounds multi-agent collaboration in a structured belief states, utilizing a causal graph to explicitly encode logical dependencies and a state machine to govern the valid transitions of the reasoning process. By dynamically aligning the reasoning focus with these symbolic constraints, our approach transforms aimless, unconstrained exploration into a convergent, directed search. Extensive evaluations on two real-world datasets demonstrate that GoS significantly outperforms all baselines, providing a robust solution for complex abductive tasks. Code repo and all prompts: https://github.com/gaorch85/Graph-of-States. --- ### Graph Fusion Across Languages using Large Language Models Authors: Kaung Myat Kyaw, Khush Agarwal, Jonathan Chan Published: 2026-03-22 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2603.21248v1 Combining multiple knowledge graphs (KGs) across linguistic boundaries is a persistent challenge due to semantic heterogeneity and the complexity of graph environments. We propose a framework for cross-lingual graph fusion, leveraging the in-context reasoning and multilingual semantic priors of Large Language Models (LLMs). The framework implements structural linearization by mapping triplets directly into natural language sequences (e.g., (head) (relation) (tail)), enabling the LLM to map relations and reconcile entities between an evolving fused graph ($G_{c}^{(t-1)}$) and a new candidate graph ($G_{t}$). Evaluated on the DBP15K dataset, this exploratory study demonstrates that LLMs can serve as a universal semantic bridge to resolve cross-lingual discrepancies. Results show the successful sequential agglomeration of multiple heterogeneous graphs, offering a scalable, modular solution for continuous knowledge synthesis in multi-source, multilingual environments. ---