# Research Papers — 2026-05 · bundle page 325 of 326

> Full-text markdown of papers #16201–16250 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-05/page/325
[← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/324.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-05/page/326.md)

### Skills as Verifiable Artifacts: A Trust Schema and a Biconditional Correctness Criterion for Human-in-the-Loop Agent Runtimes

Authors: Alfredo Metere
Published: 2026-05-01
Categories: cs.CR, cs.AI, cs.MA, cs.SE
arXiv: https://arxiv.org/abs/2605.00424v2

Agent skills - structured packages of instructions, scripts, and references that augment a large language model (LLM) without modifying the model itself - have moved from convenience to first-class deployment artifact. The runtime that loads them inherits the same problem package managers and operating systems have always faced: a piece of content claims a behavior; the runtime must decide whether to believe it. We argue this paper's central thesis up front: a skill is untrusted code until it is verified, and the runtime that loads it must enforce that default rather than infer trust from a signature, a clearance, or a registry of origin. Without skill verification, a human-in-the-loop (HITL) gate must fire on every irreversible call - which is operationally untenable and degrades into rubber-stamping at any non-trivial scale. With skill verification treated as a separate, gated process, HITL fires only for what is unverified, and the system becomes sustainable. We give a trust schema that includes an explicit verification level on every skill manifest; a capability gate whose HITL policy is a function of that verification level; a biconditional correctness criterion that any candidate verification procedure must satisfy on an adversarial-ensemble exercise; and a portable runtime profile with ten normative guidelines abstracted from a working open-source reference implementation. The contribution is harness- and model-agnostic; nothing here requires retraining, fine-tuning, or proprietary infrastructure.

---

### GD4: Graph-based Discrete Denoising Diffusion for MIMO Detection

Authors: Qincheng Lu, Sitao Luan, Xiao-Wen Chang
Published: 2026-05-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.00423v1

In wireless communications, recovering the optimal solution to the multiple-input multiple-output (MIMO) detection problem is NP-hard. Obtaining high-quality suboptimal solutions with a favorable performance-complexity trade-off is particularly challenging in under-determined systems with $N_t$ transmit antennas and $N_r < N_t$ receive antennas. Recent diffusion-based MIMO detectors have shown promise, but they require extensive sampling iterations at inference time, and their performance degrades in under-determined scenarios. We propose GD4, a graph-based discrete denoising diffusion method for MIMO detection. Unlike existing diffusion-based detectors that operate in a continuous relaxed space, GD4 performs denoising directly in the discrete symbol space and enables fast inference with one or a few denoising evaluations. Numerical results show that, under a similar inference-time compute budget, GD4 produces higher-quality suboptimal solutions than existing diffusion-based detectors and some widely used classical baseline including box-constrained Babai point and the $K$-best box-constrained randomized Klein-Babai point in both under-determined and overdetermined settings.

---

### BWLA: Breaking the Barrier of W1AX Post-Training Quantization for LLMs

Authors: Zhixiong Zhao, Zukang Xu, Dawei Yang
Published: 2026-05-01
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.00422v1

Large language models (LLMs) have driven major progress in NLP, yet their substantial memory and compute demands still hinder practical deployment. Binarization can compress weights to 1 bit, fundamentally lowering compute and bandwidth cost. However, existing methods cannot address activation heavy tails and thus must keep activations in high precision, preventing true end-to-end acceleration. To overcome this limitation, we propose BWLA (Binarized Weights and Low-bit Activations), the first post-training quantization framework that preserves high accuracy while achieving 1-bit weight quantization together with low-bit activations (e.g., 6 bits). The Orthogonal-Kronecker Transformation (OKT) learns an orthogonal mapping via EM minimization, converting unimodal weights into symmetric bimodal forms while suppressing activation tails and incoherence. The Proximal SVD Projection (PSP) then performs lightweight low-rank refinement through proximal SVD projection, further enhancing quantizability with minimal overhead. On Qwen3-32B, BWLA reaches a Wikitext2 perplexity of 11.92 under 6-bit activations (vs. 38 from SOTA), improves five zero-shot tasks by more than 70%, and delivers 3.26 times inference speedup, demonstrating strong potential for real-world LLM compression and acceleration.

---

### RadLite: Multi-Task LoRA Fine-Tuning of Small Language Models for CPU-Deployable Radiology AI

Authors: Pankaj Gupta, Kartik Bose
Published: 2026-05-01
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.00421v2

Large language models (LLMs) show promise in radiology but their deployment is limited by computational requirements that preclude use in resource-constrained clinical environments. We investigate whether small language models (SLMs) of 3-4 billion parameters can achieve strong multi-task radiology performance through LoRA fine-tuning, enabling deployment on consumer-grade CPUs. We train Qwen2.5-3B-Instruct and Qwen3-4B on 162K samples spanning 9 radiology tasks - RADS classification across 10 systems, impression generation, temporal comparison, radiology NLI, NER, abnormality detection, N/M staging, and radiology Q&A - compiled from 12 public datasets. Both models are evaluated on up to 500 held-out test samples per task with standardized metrics. Our key findings are: (1) LoRA fine-tuning dramatically improves performance over zero-shot baselines (RADS accuracy +53%, NLI +60%, N-staging +89%); (2) the two models exhibit complementary strengths - Qwen2.5 excels at structured generation tasks while Qwen3 dominates extractive tasks; (3) a task-outed oracle ensemble combining both models achieves the best performance across all tasks; (4) few-shot prompting with fine-tuned models hurts performance, demonstrating that LoRA adaptation is more effective than in-context learning for specialized domains; and (5) models can be quantized to GGUF format (~1.8-2.4GB) for CPU deployment at 4-8 tokens/second on consumer hardware. Our work demonstrates that small, efficiently fine-tuned models - which we collectively call RadLite - can serve as practical multi-task radiology AI assistants deployable entirely on consumer hardware without GPU requirements. Code and models are available at https://github.com/RadioX-Labs/RadLite

---

### Foresight Arena: An On-Chain Benchmark for Evaluating AI Forecasting Agents

Authors: Maksym Nechepurenko, Pavel Shuvalov
Published: 2026-05-01
Categories: cs.MA, cs.LG, q-fin.GN
arXiv: https://arxiv.org/abs/2605.00420v2

Evaluating the true forecasting ability of AI agents requires environments that are resistant to environments resistant to overfitting, free from centralized trust, and grounded in incentive-compatible scoring. Existing benchmarks either rely on static datasets vulnerable to training-data contamination, or measure trading PnL -- a metric conflating predictive accuracy with timing, sizing, and risk appetite. We introduce Foresight Arena, the first permissionless, on-chain benchmark for evaluating AI forecasting agents on real-world prediction markets. Agents submit probabilistic forecasts on binary Polymarket markets via a commit-reveal protocol enforced by Solidity smart contracts on Polygon PoS; outcomes are resolved trustlessly through the Gnosis Conditional Token Framework. Performance is measured by the Brier Score and a novel Alpha Score -- proper scoring rules that incentivize honest probability reporting and isolate predictive edge over market consensus. We provide a formal analysis: closed-form variance for per-market Alpha, the connection to Murphy's classical Brier decomposition, and a power analysis characterizing the number of rounds required to reliably distinguish agents of different skill levels. We show that detecting a true edge of $α^* = 0.02$ at 80% power requires approximately 350 resolved binary predictions (50 rounds of 7 markets), while $α^* = 0.01$ requires four times more. We complement these analytical results with a deterministic, seed-controlled simulation study calibrated to literature-reported Brier-score ranges, illustrating how Murphy decomposition distinguishes well-calibrated agents from market-tracking agents that fail through reduced resolution. Live results from the deployed benchmark will be reported in a future revision. All smart contracts and evaluation infrastructure are open-source.

---

### Rethinking LLM Ensembling from the Perspective of Mixture Models

Authors: Jiale Fu, Yuchu Jiang, Peijun Wu, Chonghan Liu, Joey Tianyi Zhou, Xu Yang
Published: 2026-05-01
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2605.00419v2

Model ensembling is a well-established technique for improving the performance of machine learning models. Conventionally, this involves averaging the output distributions of multiple models and selecting the most probable label. This idea has been naturally extended to large language models (LLMs), yielding improved performance but incurring substantial computational cost. This inefficiency stems from directly applying conventional ensemble implementation to LLMs, which require a separate forward pass for each model to explicitly compute the ensemble distribution. In this paper, we propose the Mixture-model-like Ensemble (ME). By reinterpreting the ensemble as a mixture model, ME stochastically selects a single model at each step to generate the next token, thereby avoiding the need to explicitly compute the full ensemble distribution. ME is mathematically equivalent to sampling from the ensemble distribution, but requires invoking only one model, making it 1.78x-2.68x faster than conventional ensembling. Furthermore, this perspective connects LLM ensembling and token-level routing methods, suggesting that LLM ensembling is a special case of routing methods. Our findings open new avenues for efficient LLM ensembling and motivate further exploration of token-level routing strategies for LLMs. Our code is available at https://github.com/Kamichanw/Mixture-model-like-Ensemble.

---

### Trees to Flows and Back: Unifying Decision Trees and Diffusion Models

Authors: Sai Niranjan Ramachandran, Suvrit Sra
Published: 2026-05-01
Categories: cs.LG, cond-mat.stat-mech, cs.AI
arXiv: https://arxiv.org/abs/2605.00414v2

Decision trees and diffusion models are ostensibly disparate model classes, one discrete and hierarchical, the other continuous and dynamic. This work unifies the two by establishing a crisp mathematical correspondence between hierarchical decision trees and diffusion processes in appropriate limiting regimes. Our unification reveals a shared optimization principle: \emph{Global Trajectory Score Matching (GTSM)}, for which gradient boosting (in an idealized version) is asymptotically optimal. We underscore the conceptual value of our work through two key practical instantiations: \treeflow, which achieves competitive generation quality on tabular data with higher fidelity and a 2\times computational speedup, and \dsmtree, a novel distillation method that transfers hierarchical decision logic into neural networks, matching teacher performance within 2\% on many benchmarks.

---

### Physically Native World Models: A Hamiltonian Perspective on Generative World Modeling

Authors: Sen Cui, Jingheng Ma
Published: 2026-05-01
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2605.00412v3

World models have recently re-emerged as a central paradigm for embodied intelligence, robotics, autonomous driving, and model-based reinforcement learning. However, current world model research is often dominated by three partially separated routes: 2D video-generative models that emphasize visual future synthesis, 3D scene-centric models that emphasize spatial reconstruction, and JEPA-like latent models that emphasize abstract predictive representations. While each route has made important progress, they still struggle to provide physically reliable, action-controllable, and long-horizon stable predictions for embodied decision making. In this paper, we argue that the bottleneck of world models is no longer only whether they can generate realistic futures, but whether those futures are physically meaningful and useful for action. We propose \emph{Hamiltonian World Models} as a physically grounded perspective on world modeling. The key idea is to encode observations into a structured latent phase space, evolve the latent state through Hamiltonian-inspired dynamics with control, dissipation, and residual terms, decode the predicted trajectory into future observations, and use the resulting rollouts for planning. We discuss how Hamiltonian structure may improve interpretability, data efficiency, and long-horizon stability, while also noting practical challenges in real-world robotic scenes involving friction, contact, non-conservative forces, and deformable objects.

---

### Agent Capsules: Quality-Gated Granularity Control for Multi-Agent LLM Pipelines

Authors: Aninda Ray
Published: 2026-05-01
Categories: cs.CL, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2605.00410v1

A multi-agent pipeline with N agents typically issues N LLM calls per run. Merging agents into fewer calls (compound execution) promises token savings, but naively merged calls silently degrade quality through tool loss and prompt compression. We present Agent Capsules, an adaptive execution runtime that treats multi-agent pipeline execution as an optimization problem with empirical quality constraints. The runtime instruments coordination overhead per group, scores composition opportunity, selects among three compound execution strategies, and gates every mode switch on rolling-mean output quality. A controlled negative result confirms that injecting more context into a merged call worsens compression rather than relieving it, so the framework's escalation ladder (standard, then two-phase, then sequential) recovers quality by moving toward per-agent dispatch rather than by rewriting merged prompts. On LLM-judged quality, the controller matches a hand-tuned oracle on every measured (model, group, mode) cell: routing compound whenever the oracle would, and reverting to fine whenever quality would fail the floor, without per-model configuration. Against a hand-crafted LangGraph implementation of a 14-agent competitive intelligence pipeline, Agent Capsules uses 51% fewer fine-mode input tokens and 42% fewer compound-mode input tokens, at +0.020 and +0.017 quality respectively. Against a DSPy implementation of a 5-agent due diligence pipeline, the framework uses 19% fewer tokens than uncompiled DSPy at quality parity, and 68% fewer tokens than MIPROv2 at +0.052 quality. Even before compound mode fires, the runtime delivers efficiency through automatic policy resolution, cache-aligned prompts, and topology-aware context injection, matching both hand-tuned and compile-time baselines without training data or per-pipeline engineering.

---

### Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting

Authors: Zhenhua Ning, Xin Li, Jun Yu, Guangming Lu, Yaowei Wang, Wenjie Pei
Published: 2026-05-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.00408v2

While 3D Gaussian Splatting (3DGS) has demonstrated impressive real-time rendering performance, its efficacy remains constrained by a reliance on heuristic density control. Despite numerous refinements to these handcrafted rules, such methods inherently lack the flexibility to adapt to diverse scenes with complex geometries. In this paper, we propose a paradigm shift for density control from rigid heuristics to fully learnable policies. Specifically, we introduce \textbf{LeGS}, a framework that reformulates density control as a parameterized policy network optimized via Reinforcement Learning (RL). Central to our approach is the tailored effective reward function grounded in sensitivity analysis, which precisely quantifies the marginal contribution of individual Gaussians to reconstruction quality. To maintain computational tractability, we derive a closed-form solution that reduces the complexity of reward calculation from $O(N^2)$ to $O(N)$. Extensive experiments on the Mip-NeRF 360, Tanks \& Temples, and Deep Blending datasets demonstrate that \textbf{LeGS} significantly outperforms state-of-the-art methods, striking a superior balance between reconstruction quality and efficiency. The code will be released at https://github.com/AaronNZH/LeGS

---

### BOLT: Online Lightweight Adaptation for Preparation-Free Heterogeneous Cooperative Perception

Authors: Kang Yang, Tianci Bu, Peng Wang, Deying Li, Yongcai Wang
Published: 2026-05-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.00405v2

Most existing heterogeneous cooperative perception methods depend on prior preparation like offline joint training or tailored collaborator-model adaptation. Such preprocessing is, however, generally impractical in real scenarios, as agents are usually independently trained by different developers and meet occasionally online. This work investigates \emph{preparation-free heterogeneous cooperative perception}, where agents use independently trained single-agent detectors without any pre-deployment coordination. We find direct cross-agent fusion under this setting greatly underperforms ego-only perception. We present BOLT, a lightweight plug-and-play module that adapts neighboring features online via ego-as-teacher distillation, requiring only ego predictions without ground-truth labels. BOLT leverages high-confidence ego perception features to guide cross-agent feature-domain alignment, while enabling neighbors to contribute features in the ego's low-confidence regions. With only 0.9M trainable parameters, BOLT improves AP@50 by up to 32.3 points over vanilla unadapted fusion in the preparation-free setting. It consistently outperforms ego-only results on DAIR-V2X and OPV2V, across different encoder pairs and fusion strategies. Code: https://github.com/sidiangongyuan/BOLT.

---

### BOLT: Online Lightweight Adaptation for Preparation-Free Heterogeneous Cooperative Perception

Authors: Kang Yang, Tianci Bu, Peng Wang, Deying Li, Yongcai Wang
Published: 2026-05-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.00405v1

Most existing heterogeneous cooperative perception methods depend on prior preparation like offline joint training or tailored collaborator-model adaptation. Such preprocessing is, however, generally impractical in real scenarios, as agents are usually independently trained by different developers and meet occasionally online. This work investigates \emph{preparation-free heterogeneous cooperative perception}, where agents use independently trained single-agent detectors without any pre-deployment coordination. We find direct cross-agent fusion under this setting greatly underperforms ego-only perception. We present BOLT, a lightweight plug-and-play module that adapts neighboring features online via ego-as-teacher distillation, requiring only ego predictions without ground-truth labels. BOLT leverages high-confidence ego perception features to guide cross-agent feature-domain alignment, while enabling neighbors to contribute features in the ego's low-confidence regions. With only 0.9M trainable parameters, BOLT improves AP@50 by up to 32.3 points over vanilla unadapted fusion in the preparation-free setting. It consistently outperforms ego-only results on DAIR-V2X and OPV2V, across different encoder pairs and fusion strategies. Code: https://github.com/sidiangongyuan/BOLT.

---

### Scalable Learning in Structured Recurrent Spiking Neural Networks without Backpropagation

Authors: Bo Tang, Weiwei Xie
Published: 2026-05-01
Categories: cs.NE, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2605.00402v1

Spiking Neural Networks (SNNs) provide a promising framework for energy-efficient and biologically grounded computation; however, scalable learning in deep recurrent architectures with sparse connectivity remains a major challenge. In this work, we propose a structured multi-layer recurrent SNN architecture composed of locally dense recurrent layers augmented with sparse small-world long-range projections to a readout population. The long-range connectivity is largely fixed, preserving routing efficiency and hardware scalability, while synaptic adaptation is performed using strictly local plasticity mechanisms. To enable supervised learning without backpropagation or surrogate gradients, we introduce a biologically motivated learning framework that combines: (i) population-based winner-take-all (WTA) teaching signals at the output layer, (ii) fixed random broadcast alignment feedback pathways, and (iii) low-dimensional modulatory neuron populations that gate synaptic updates through three-factor learning rules with eligibility traces. This design supports deep recurrent computation with sparse global communication and purely local synaptic updates. We analyze the algorithmic properties, computational complexity, and hardware feasibility of the proposed approach, and demonstrate stable learning and competitive performance on benchmark classification tasks. The results highlight the potential of structured recurrence and neuromodulatory learning to enable scalable, hardware-compatible SNN training beyond gradient-based methods.

---

### SIMON: Saliency-aware Integrative Multi-view Object-centric Neural Decoding

Authors: YuSheng Lin, Ji-Hwa Tsai, Chun-Shu Wei
Published: 2026-05-01
Categories: cs.CV, q-bio.NC
arXiv: https://arxiv.org/abs/2605.00401v1

Recent EEG-to-image retrieval methods leverage pretrained vision encoders and foveation-inspired priors, but typically assume a fixed, center-focused view. This center bias conflicts with content-driven human attention, creating a geometric-semantic dissociation between visual features and EEG responses. We propose SIMON, a saliency-aware multi-view framework for zero-shot EEG-to-image retrieval. SIMON combines foreground segmentation and saliency prediction to select fixation centers via Saliency-Aware Sampling (SAS), then generates foveated views that emphasize informative object regions while suppressing background clutter. On THINGS-EEG, SIMON achieves state-of-the-art performance in both intra-subject and inter-subject settings, reaching an average Top-1 accuracy of 69.7% and 19.6%, respectively, consistently outperforming recent competitive baselines. Analyses across sampling granularity, EEG channel topology, and visual/brain encoder backbones further support the robustness of saliency-aware multi-view integration. Our code and models are publicly available at https://github.com/simonlink666/SIMON.

---

### FollowTable: A Benchmark for Instruction-Following Table Retrieval

Authors: Rihui Jin, Yuchen Lu, Ting Zhang, Jun Wang, Kuicai Dong, Zhaocheng Du, Dongping Liu, Gang Wang, Yong Liu, Guilin Qi
Published: 2026-05-01
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2605.00400v1

Table Retrieval (TR) has traditionally been formulated as an ad-hoc retrieval problem, where relevance is primarily determined by topical semantic similarity. With the growing adoption of LLM-based agentic systems, access to structured data is increasingly instruction-driven, where relevance is conditional on explicit content and schema constraints rather than topical similarity alone. We therefore formalize Instruction-Following Table Retrieval (IFTR), a new task that requires models to jointly satisfy topical relevance and fine-grained instruction constraints. We identify two core challenges in IFTR: (i) sensitivity to content scope, such as inclusion and exclusion constraints, and (ii) awareness of schema-grounded requirements, including column semantics and representation granularity--capabilities largely absent in existing retrievers. To support systematic evaluation, we introduce FollowTable, the first large-scale benchmark for IFTR, constructed via a taxonomy-driven annotation pipeline. We further propose a new metric, termed the Instruction Responsiveness Score, to evaluate whether retrieval rankings consistently adapt to user instructions relative to a topic-only baseline. Our results indicate that existing retrieval models struggle to follow fine-grained instructions over tabular data. In particular, they exhibit systematic biases toward surface-level semantic cues and remain limited in handling schema-grounded constraints, highlighting substantial room for future improvements.

---

### M-CaStLe: Uncovering Local Causal Structures in Multivariate Space-Time Gridded Data

Authors: J. Jake Nichol, Michael Weylandt, G. Matthew Fricke, Jhayron Perez-Carrasquilla, Melanie E. Moses
Published: 2026-05-01
Categories: cs.LG, physics.ao-ph, stat.ML
arXiv: https://arxiv.org/abs/2605.00398v1

Causal graph discovery for space-time systems is challenging in high-dimensional gridded data, which often has many more grid cells than temporal observations per cell. The Causal Space-Time Stencil Learning (CaStLe) meta-algorithm was developed to address that niche under space-time locality and stationarity assumptions, but it is currently limited to univariate analyses. In this work, we present M-CaStLe. M-CaStLe generalizes the local embedding and parent-identification phases of CaStLe to jointly model local within-variable and cross-variable space-time causal structures in gridded data. Like CaStLe, by constraining candidate parents to a constant-size space-time neighborhood and pooling spatial replicates, M-CaStLe increases effective sample size to make discovery tractable in high-dimensional settings. We further decompose the resulting multivariate stencil graph into reaction and spatial graphs to aid interpretation in complex settings. We study M-CaStLe in four settings: a multivariate space-time vector autoregression benchmark with known ground truth, an advective-diffusive-reaction partial differential equation verification problem with derived physical reference structure, an atmospheric chemistry case study in a low-temporal-sample regime, and an El Niño Southern Oscillation study on reanalysis data, identifying phase-dependent ocean--atmosphere coupling. Across these settings, M-CaStLe more accurately recovers multivariate causal structure in controlled settings and identifies important physical dynamics in real-world case studies. Overall, M-CaStLe advances causal discovery for multivariate space-time systems while retaining interpretability at the grid level.

---

### Mesh Field Theory: Port-Hamiltonian Formulation of Mesh-Based Physics

Authors: Satoshi Noguchi, Yoshinobu Kawahara
Published: 2026-05-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.00394v3

We present Mesh Field Theory (MeshFT) and its neural realization, MeshFT-Net: a structure-preserving framework for mesh-based continuum physics that cleanly separates the physics' topological structure from its metric structure. Imposing minimal physical principles (locality, permutation equivariance, orientation covariance, and energy balance/dissipation inequality), we prove a reduction theorem for mesh-based physics. Under these conditions, the physical dynamics admit a local factorization into a port-Hamiltonian form: the conservative interconnection is fixed uniquely by mesh topology, whereas metric effects enter only through constitutive relations and dissipation. This reduction clarifies what must be fixed and what should be learned, directly informing MeshFT-Net's design. Across evaluations on analytic and realistic datasets, physics-consistency tests, and out-of-distribution validation, MeshFT-Net achieves near-zero energy drift and strong physical fidelity (correct dispersion and momentum conservation) along with robust extrapolation and high data efficiency. By eliminating non-physical degrees of freedom and learning only metric-dependent structure, MeshFT provides a principled inductive bias for stable, faithful, and data-efficient learning-based physical simulation.

---

### Model-Based Reinforcement Learning with Double Oracle Efficiency in Policy Optimization and Offline Estimation

Authors: Haichen Hu, Jian Qian, David Simchi-Levi
Published: 2026-05-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.00393v1

Reinforcement learning (RL) in large environments often suffers from severe computational bottlenecks, as conventional regret minimization algorithms require repeated, costly calls to planning and statistical estimation oracles. While recent advances have explored offline oracle-efficient algorithms, their computational complexity typically scales with the cardinality of the state and action spaces, rendering them intractable for large-scale or continuous environments. In this paper, we address this fundamental limitation by studying offline oracle-efficient episodic RL through the lens of log-barrier and log-determinant regularization. Specifically, for tabular Markov Decision Processes (MDPs), we propose a novel algorithm that achieves the optimal $\tilde{O}(\sqrt{T})$ regret bound while requiring only $O(H\log\log T)$ calls to both the offline statistical estimation and planning oracles when $T$ is known and $O(H\log T)$ calls when $T$ is unknown. Crucially, this oracle complexity is entirely independent of the size of the state and action spaces. This strict independence drastically reduces the planning oracle complexity, representing a substantial improvement over existing offline oracle-efficient algorithms (Qian et al., 2024). Furthermore, we demonstrate the versatility of our framework by generalizing the algorithm to linear MDPs featuring infinite state spaces and arbitrary action spaces. We prove that this generalized approach successfully attains meaningful sub-linear regret. Consequently, our work yields the first doubly oracle-efficient (i.e., efficient with respect to both statistical estimation and policy optimization) regret minimization algorithm capable of solving MDPs with infinite state and action spaces, significantly expanding the boundaries of computationally tractable RL.

---

### RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference

Authors: Ben Wan, Yan Feng, Zihan Tang, Weizhe Huang, Yuting Zeng, Jia Wang, Tongxuan Liu
Published: 2026-05-01
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2605.00392v3

DeepSeek-OCR leverages visual-text compression to reduce long-text processing costs and accelerate inference, yet visual tokens remain prone to redundant textual and structural information. Moreover, current token pruning methods for conventional vision-language models (VLMs) fail to preserve textual fidelity due to improper compression mechanisms. By analyzing the decoding process of DeepSeek-OCR, we find that a distinct two-stage reading trajectory: the model initially prioritizes the majority of high-norm tokens, then subsequently redistributes its attention to the remaining ones. Motivated by this insight, we propose RTPrune, a two-stage token pruning method tailored for DeepSeek-OCR. In the first stage, we prioritize high-norm visual tokens that capture salient textual and structural information. In the second stage, the remaining tokens are paired and merged based on optimal transport theory to achieve efficient feature aggregation. We further introduce a dynamic pruning ratio that adapts to token similarity and textual density for OCR tasks, enabling a better efficiency-accuracy trade-off. Extensive experiments demonstrate state-of-the-art performance, as evidenced by 99.47% accuracy and 1.23$\times$ faster prefill on OmniDocBench, achieved with 84.25% token retention when applied to DeepSeek-OCR-Large.

---

### Towards Robust and Scalable Density-based Clustering via Graph Propagation

Authors: Yingtao Zheng, Hugo Phibbs, Ninh Pham
Published: 2026-05-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.00390v2

We present \textit{CluProp}, a novel framework that reimagines varied-density clustering in high-dimensional spaces as a label propagation process over neighborhood graphs. Our approach formally bridges the gap between density-based clustering and graph connectivity, leveraging efficient propagation mechanisms from network science to mitigate the parameter sensitivity inherent in traditional density-based methods. Specifically, we introduce a deterministic density-based propagation strategy to ensure scalable neighborhood identification. The framework is agnostic to the choice of distance metric and exhibits superior performance on large-scale data, processing millions of points in minutes while consistently outperforming existing baselines in accuracy.

---

### Towards Robust and Scalable Density-based Clustering via Graph Propagation

Authors: Yingtao Zheng, Hugo Phibbs, Ninh Pham
Published: 2026-05-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.00390v1

We present \textit{CluProp}, a novel framework that reimagines varied-density clustering in high-dimensional spaces as a label propagation process over neighborhood graphs. Our approach formally bridges the gap between density-based clustering and graph connectivity, leveraging efficient propagation mechanisms from network science to mitigate the parameter sensitivity inherent in traditional density-based methods. Specifically, we introduce a deterministic density-based propagation strategy to ensure scalable neighborhood identification. The framework is agnostic to the choice of distance metric and exhibits superior performance on large-scale data, processing millions of points in minutes while consistently outperforming existing baselines in accuracy.

---

### PILIR: Physics-Informed Local Implicit Representation

Authors: Jianfeng Li, Feng Wang, Ke Tang
Published: 2026-05-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.00385v1

Physics-Informed Neural Networks have become a powerful mesh-free method for solving partial differential equations, but their performance is often limited by spectral bias. Specifically, in standard MLPs used in PINNs, the global parameter coupling causes the model to prioritize learning low-frequency components, resulting in slow convergence for high-frequency details. To overcome this limitation, we introduce the Physics-Informed Local Implicit Representation (PILIR). Our approach separates the global physical domain into a discrete latent feature space and a continuous generative decoder. By using a learnable grid to encode explicit spatial locality, PILIR can capture high-frequency details locally, preventing dilution by global patterns. A generative neural operator then synthesizes these local latent features into continuous physical fields, allowing accurate reconstruction of fine-scale structures. Experiments on a range of challenging PDEs show that PILIR effectively mitigates spectral bias, thereby boosting the convergence of high-frequency details and achieving superior accuracy compared to state-of-the-art methods.

---

### Agentic AI for Substance Use Education: Integrating Regulatory and Scientific Knowledge Sources

Authors: Kosar Haghani, Zahra Kolagar, Mohammed Atiquzzaman
Published: 2026-05-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.00383v1

The delivery of traditional substance education has remained problematic due to challenges in scalability, personalization, and the currency of information in a rapidly evolving substance use landscape. While artificial intelligence (AI) offers a promising frontier for enhancing educational delivery, its application in providing real-time, authoritative substance use education remains largely underexplored. We built an agentic-based AI web application that combined Drug Enforcement Administration records with peer-reviewed literature in real-time to provide transparent context-sensitive substance use education. The system uses retrieval-augmented generation with a carefully filtered corpus of 102 documents and dynamic PubMed queries. Document storage was semantically chunked and placed in a vector representation in order to be easily retrieved. We conducted an expert evaluation study in which a panel of five subject matter experts generated 30 domain-specific questions, and two independent raters assessed 90 system interactions (30 primary questions plus two contextual follow-ups each) using a five-point Likert scale across four criteria: factual accuracy, citation quality, contextual coherence, and regulatory appropriateness. Mean ratings ranged from 4.18 to 4.35 across the four criteria (overall category range: 4.05-4.52), with substantial inter-rater agreement (Cohen's kappa = 0.78). These findings suggest that agentic AI architectures integrating authoritative regulatory sources with real-time scientific literature represent a promising direction for scalable, accurate, and verifiable health education delivery, warranting further evaluation through longitudinal user studies.

---

### Social Bias in LLM-Generated Code: Benchmark and Mitigation

Authors: Fazle Rabbi, Lin Ling, Song Wang, Jinqiu Yang
Published: 2026-05-01
Categories: cs.SE, cs.AI, cs.SI
arXiv: https://arxiv.org/abs/2605.00382v3

Large Language Models (LLMs) are increasingly deployed to generate code for human-centered applications where demographic fairness is critical. However, existing evaluations focus almost exclusively on functional correctness, leaving social bias in LLM-generated code largely unexamined. Extending our prior work on Solar, we conduct a comprehensive empirical study using SocialBias-Bench, a benchmark of 343 real-world coding tasks spanning seven demographic dimensions. We evaluate four prominent LLMs and find severe bias across all models, with Code Bias Scores reaching up to 60.58%. We further show that standard prompt-level interventions, such as Chain-of-Thought reasoning and fairness persona assignment, inadvertently amplify bias rather than reduce it. We then investigate whether structured multi-agent software process frameworks can improve fairness, finding that structured pipelines reduce bias when early roles correctly scope what the code should and should not consider. However, adding explicit fairness instructions to all agent roles produces worse outcomes than providing none, suggesting that diffused responsibility goes unaddressed. To address these limitations, we propose the Fairness Monitor Agent (FMA), a modular component that plugs into any existing code generation pipeline without modifying it. FMA analyzes the task description to determine which attributes should be considered or restricted, then detects and corrects violations through an iterative review process, without requiring an executable test suite. Evaluated on all 343 tasks, FMA reduces bias by 65.1% compared to a developer agent alone and improves functional correctness from 75.80% to 83.97%, outperforming all other studied approaches.

---

### ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning

Authors: Zihan Lin, Xiaohan Wang, Jie Cao, Jiajun Chai, Li Wang, Xiaodong Lu, Wei Lin, Ran He, Guojun Yin
Published: 2026-05-01
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2605.00380v2

Reinforcement Learning with Verifiable Rewards (RLVR) enhances reasoning of Large Language Models (LLMs) but usually exhibits limited generation diversity due to the over-incentivization of positive rewards. Although methods like Negative Sample Reinforcement (NSR) mitigate this issue by upweighting penalty from negative samples, they may suppress the semantic distributions shared between positive and negative responses. To boost reasoning ability without losing diversity, this paper proposes negative sample projection Residual Reinforcement Learning (ResRL) that decouples similar semantic distributions among positive and negative responses. We theoretically link Lazy Likelihood Displacement (LLD) to negative-positive head-gradient interference and derive a single-forward proxy that upper-bounds representation alignment to guide conservative advantage reweighting. ResRL then projects negative-token hidden representations onto an SVD-based low-rank positive subspace and uses projection residuals to modulate negative gradients, improving reasoning while preserving diversity and outperforming strong baselines on average across twelve benchmarks spanning Mathematics, Code, Agent Tasks, and Function Calling. Notably, ResRL surpasses NSR on mathematical reasoning by 9.4\% in Avg@16 and 7.0\% in Pass@128. Code is available at https://github.com/1229095296/ResRL.git.

---

### Advancing Edge Classification through High-Dimensional Causal Modeling of Node-Edge Interplay

Authors: Duanyu Feng, Li Ding, Hongru Liang, Wenqiang Lei
Published: 2026-05-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.00374v2

Edge classification, a crucial task for graph applications, remains relatively under-explored compared to link prediction. Current methods often overlook the potential causal influences of node features on edge features, leading to a loss of relevant prior information. In this work, we present an empirical exploration using the Causal Edge Classification Framework (CECF). Unlike conventional causal inference methods, CECF is the first framework to apply causal inference principles to the edge classification task and to explore modeling edge features as a high-dimensional treatment within a causal framework. Based on the node embedding of Graph Neural Network (GNN), CECF seeks to learn a balanced representation of high-dimensional edge features by mitigating the potential influence of node features. Then, a cross-attention network captures the complex dependencies between node and edge features for final edge classification. Extensive experiments demonstrate that CECF not only achieves superior performance but also serves as a flexible, plug-and-play enhancement for existing methods. We also provide empirical analyses, offering insights into when and how this high-dimensional causal modeling framework works for the edge classification.

---

### Language-free Experience at Expo 2025 Osaka

Authors: Michael Paul, Kenji Imamura, Xiaolin Wang, Shohei Higashiyama, Masao Utiyama
Published: 2026-05-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.00373v1

In line with the Global Communication Plan 2025, we have pursued the development of multilingual translation technologies to realize a language-barrier-free experience at Expo 2025 Osaka. Our work includes the advancement of simultaneous interpretation systems emphasizing high translation quality and low latency. Key achievements include chunk-based input segmentation, context-aware translation, and multi-engine machine translation technologies. Through demonstration deployments and collaboration with private companies, our technologies have led to real-world applications, with several services and systems showcased at Expo 2025 Osaka.

---

### GaMMA: Towards Joint Global-Temporal Music Understanding in Large Multimodal Models

Authors: Zuyao You, Zhesong Yu, Mingyu Liu, Bilei Zhu, Yuan Wan, Zuxuan Wu
Published: 2026-05-01
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2605.00371v1

In this paper, we propose GaMMA, a state-of-the-art (SoTA) large multimodal model (LMM) designed to achieve comprehensive musical content understanding. GaMMA inherits the streamlined encoder-decoder design of LLaVA, enabling effective cross-modal learning between music and language. By incorporating audio encoders in a mixture-of-experts manner, GaMMA effectively unifies both time-series and non-time-series music understanding tasks within one set of parameters. Our approach combines carefully curated datasets at scale with a progressive training pipeline, effectively pushing the boundaries of music understanding via pretraining, supervised fine-tuning (SFT), and reinforcement learning (RL). To comprehensively assess both temporal and non-temporal capability of music LMMs, we introduce MusicBench, the largest music-oriented benchmark, comprising 3,739 human-curated multiple-choice questions covering diverse aspects of musical understanding. Extensive experiments demonstrate that GaMMA establishes new SoTA in the music domain, achieving 79.1% accuracy on MuchoMusic, 79.3% on MusicBench-Temporal, and 81.3% on MusicBench-Global, consistently outperforming previous methods.

---

### Group Cognition Learning: Making Everything Better Through Governed Two-Stage Agents Collaboration

Authors: Chunlei Meng, Pengbin Feng, Rong Fu, Hoi Leong Lee, Xiaojing Du, Zhaolu Kang, Zeyu Zhang, Weilin Zhou, Chun Ouyang, Zhongxue Gan
Published: 2026-05-01
Categories: cs.LG, cs.CY, cs.MM
arXiv: https://arxiv.org/abs/2605.00370v2

Centralized multimodal learning commonly compresses language, acoustic, and visual signals into a single fused representation for prediction. While effective, this paradigm suffers from two limitations: modality dominance, where optimization gravitates towards the path of least resistance, ignoring weaker but informative modalities, and spurious modality coupling, where models overfit to incidental cross-modal correlations. To address these, we propose Group Cognition Learning (GCL), a governed collaboration paradigm that applies a two-stage protocol after modality-specific encoding. In Stage 1 (Selective Interaction), a Routing Agent proposes directed interaction routes, and an Auditing Agent assigns sample-wise gates to emphasize exchanges that yield positive marginal predictive gain while suppressing redundant coupling. In Stage 2 (Consensus Formation), a Public-Factor Agent maintains an explicit shared factor, and an Aggregation Agent produces the final prediction through contribution-aware weighting while keeping each modality representation as a specialization channel. Extensive experiments on CMU-MOSI, CMU-MOSEI, and MIntRec demonstrate that GCL mitigates dominance and coupling, establishing state-of-the-art results across both regression and classification benchmarks. Analysis experiments further demonstrate the effectiveness of the design.

---

### InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees

Authors: Chenyu Huang, Jianghao Lin, Zhengyang Tang, Bo Jiang, Ruoqing Jiang, Benyou Wang, Lai Wei
Published: 2026-05-01
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.00369v4

We study how large language models can be used to generate inventory policies in online settings with non-stationary demand. Our work is motivated by recent advances in LLM-based evolutionary search, such as AlphaEvolve, which demonstrates strong performance on static and highly structured problems such as mathematical discovery, but is not directly suited to dynamic inventory settings with online updates. We propose InvEvolve, an end-to-end inventory policy evolution and inference framework grounded in confidence-interval-based certification. Built on a large language model trained via reinforcement learning, InvEvolve can process demand data together with additional numerical and textual features, and generates white-box inventory policies with statistical safety guarantees for future deployment. We further introduce a unified framework with theoretical guarantees that connects training, inference, and deployment. This allows us to derive a lower bound on the probability that InvEvolve evolves a statistically safe and improved policy, and to characterize the multi-period performance gap relative to the oracle-safe benchmark. Tested on both synthetic data and real-world retail data, InvEvolve outperforms classical inventory policies and deep-learning-based methods. In canonical inventory settings, it generates new policies that outperform existing benchmarks.

---

### Flow matching for Sentinel-2 super-resolution: implementation, application, and implications

Authors: Dakota Hester, Vitor S. Martins, Lucas B. Ferreira, Thainara M. A. Lima, Juliana A. Araújo
Published: 2026-05-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.00367v1

Developing robust techniques for super-resolution of satellite imagery involves navigating commonly observed trade-offs between spectral fidelity and perceptual quality. In this work, we introduce a flow matching model for 4x super-resolution of 10-m Sentinel-2 visible and near-infrared bands over the conterminous United States (CONUS) using a dataset of 120,851 10-m Sentinel-2 and 2.5-m resampled NAIP imagery pairs acquired on the same day. Our results showed that the flow matching model outperformed diffusion and Real-ESRGAN models in pixel-wise accuracy in a single sampling step using the Euler method. When evaluated with a second-order Midpoint solver, our model generated perceptually realistic super-resolved imagery in only 20 sampling steps, effectively navigating the perception-distortion trade-off at inference time without retraining. We used this model to produce a super-resolved 2.5-m 4-band CONUS imagery product derived from 2025 10-m Sentinel-2 annual composites, consisting of over 1.58 trillion pixels. We further evaluated the use of super-resolved data on a land cover classification task using semantic segmentation models. Finally, we generated a yearly 2.5-m land cover product for the Chesapeake Bay watershed for 2020-2025. An accuracy assessment against 25,000 ground truth points revealed an overall accuracy of 89.11% for the annual land cover product. We conclude that flow matching is an effective generative modeling approach for super-resolution of Sentinel-2 imagery compared to diffusion and Generative Adversarial Network-based methods, and has strong implications for expanding access to high-resolution imagery for geospatial applications that demand fine spatial detail.

---

### Geometric and dynamical analysis of attractor boundaries and storage limits in kernel Hopfield networks

Authors: Akira Tamamori
Published: 2026-05-01
Categories: cs.NE, cs.LG
arXiv: https://arxiv.org/abs/2605.00366v4

High-capacity associative memories based on Kernel Logistic Regression (KLR) exhibit strong storage capabilities, but the dynamical and geometric mechanisms underlying their stability remain poorly understood. This paper investigates the global geometry of attractor basins and the mechanisms governing the storage limit in KLR-trained Hopfield networks. We combine empirical evaluations using random sequences and real-world image embeddings (CIFAR-10) with morphing experiments and statistical Signal-to-Noise Ratio (SNR) analysis. Our experiments show that the network achieves a storage capacity for random sequences up to $P/N \approx 16$, while maintaining stable retrieval for structured data at effective loads near $P/N \approx 20$. Morphing analysis indicates that attractors on the "Ridge of Optimization" are separated by sharp, phase-transition-like boundaries, characterized by steep effective potential barriers and critical slowing down. Furthermore, by comparing an SNR analysis with a geometric reference point inspired by Cover's theorem, we show that the practical storage limit is governed primarily not by a lack of geometric separability in the feature space, but by the loss of dynamical stability against crosstalk noise. These findings suggest that KLR networks function as highly localized exemplar-based memories that operate near the onset of dynamical collapse, providing a useful perspective on the design of robust, large-scale retrieval systems.

---

### Uniform-Correct Policy Optimization: Breaking RLVR's Indifference to Diversity

Authors: Anamika Lochab, Bolian Li, Ruqi Zhang
Published: 2026-05-01
Categories: cs.LG, cs.CL, stat.ML
arXiv: https://arxiv.org/abs/2605.00365v1

Reinforcement Learning with Verifiable Rewards (RLVR) has achieved substantial gains in single-attempt accuracy (Pass@1) on reasoning tasks, yet often suffers from reduced multi-sample coverage (Pass@K), indicating diversity collapse. We identify a structural cause for this degradation: common RLVR objectives, such as GRPO, are indifferent to how probability mass is distributed among correct solutions. Combined with stochastic training dynamics, this indifference induces a self-reinforcing collapse, in which probability mass concentrates on a narrow subset of correct outputs while alternative valid solutions are suppressed. We formalize this collapse mechanism and further characterize the optimal policy structure under two complementary criteria: robustness and entropy-regularized optimality, which identify the Uniform-Correct Policy as uniquely optimal. Motivated by this analysis, we propose Uniform-Correct Policy Optimization (UCPO), a modification to GRPO that adds a conditional uniformity penalty on the policy's distribution over correct solutions. The penalty redistributes gradient signal toward underrepresented correct responses, encouraging uniform allocation of probability mass within the correct set. Across three models (1.5B-7B parameters) and five mathematical reasoning benchmarks, UCPO improves Pass@K and diversity while maintaining competitive Pass@1, achieving up to +10\% absolute improvement on AIME24 at Pass@64 and up to 45\% higher equation-level diversity within the correct set. The code is available at https://github.com/AnamikaLochab/UCPO.

---

### Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning

Authors: Jiawei Wu, Doudou Zhou
Published: 2026-05-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.00364v2

Machine unlearning has emerged as a critical capability for addressing privacy, safety, and regulatory concerns in large language models (LLMs). Existing methods operate at the sequence level, applying uniform updates across all tokens despite only a subset encoding the knowledge targeted for removal. This introduces gradient noise, degrades utility, and leads to suboptimal forgetting. We propose TokenUnlearn, a token-level attribution framework that identifies and selectively targets critical tokens. Our approach combines knowledge-aware signals via masking, and entropy-aware signals to yield importance scores for precise token selection. We develop two complementary strategies: hard selection, applying unlearning only to high-importance tokens, and soft weighting, modulating gradient contributions based on importance scores. Both extend existing methods to token-level variants. Theoretical analysis shows token-level selection improves gradient signal-to-noise ratio. Experiments on TOFU and WMDP benchmarks across three model architectures demonstrate consistent improvements over sequence-level baselines in both forgetting effectiveness and utility preservation.

---

### Time-series Meets Complex Motion Modeling: Robust and Computational-effective Motion Predictor for Multi-object Tracking

Authors: Nhat-Tan Do, Le-Huy Tu, Nhi Ngoc-Yen Nguyen, Dieu-Phuong Nguyen, Trong-Hop Do
Published: 2026-05-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.00362v1

Multi-object tracking (MOT) is critical in numerous real-world applications, including surveillance, autonomous driving, and robotics. Accurately predicting object motion is fundamental to MOT, but current methods struggle with the complexities of real-world, non-linear motion (e.g., sudden stops, sharp turns). While recent research has gravitated towards increasingly complex and computationally expensive generative models to tackle this problem, their practical utility is often constrained. This paper challenges that paradigm, arguing that such complexity is not only unnecessary but can be outperformed by a more efficient, purpose-built approach. We introduce the Temporal Convolutional Motion Predictor (TCMP), a novel framework for MOT that leverages a modified Temporal Convolutional Network (TCN) featuring dilated convolutions and a regression head. This design allows for effective motion prediction across arbitrary temporal context lengths. Experimental results demonstrate that our approach achieves state-of-the-art performance, specifically improves upon the previous best method in several key metrics: HOTA (a measure of overall tracking accuracy) increases from 62.3% to 63.4%, IDF1 (a measure of identity preservation) rises from 63.0% to 65.0%, and AssA (a measure of association accuracy) improves from 47.2% to 49.1%. Significantly, TCMP achieves this performance while being highly efficient; it has only 0.014 times the parameters and requires only 0.05 times the computational cost (FLOPs) compared to the SOTA method. while is only 0.014 times the size (in terms of parameters) and requires only 0.05 times the computational cost (in terms of FLOPs). These findings highlight the robustness of our method to advance MOT systems by ensuring adaptability, accuracy, and efficiency in complex tracking environments.

---

### Pedagogical Promise and Peril of AI: A Text Mining Analysis of ChatGPT Research Discussions in Programming Education

Authors: Juvy C. Grume, John Paul P. Miranda, Aileen P. De Leon, Jordan L. Salenga, Hilene E. Hernandez, Mark Anthony A. Castro, Vernon Grace M. Maniago, Joel D. Canlas, Joel B. Quiambao
Published: 2026-05-01
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2605.00361v1

GenAI systems such as ChatGPT are increasingly discussed in programming education, but the ways in which the research literature conceptualizes and frames their role remain unclear. This chapter applies text mining to publications indexed in a leading academic database to map scholarly discourse on ChatGPT in programming education. Term frequency analysis, phrase pattern extraction, and topic modeling reveal four dominant themes: pedagogical implementation, student-centered learning and engagement, AI infrastructure and human-AI collaboration, and assessment, prompting, and model evaluation. The literature prioritizes classroom practice and learner interaction, with comparatively limited attention to assessment design and institutional governance. Across studies, ChatGPT is positioned both as a learning aid that supports explanation, feedback, and efficiency and as a pedagogical risk linked to overreliance, unreliable outputs, and academic integrity concerns. These findings support responsible integration and highlight the need for stronger assessment and governance mechanisms.

---

### Binomial flows: Denoising and flow matching for discrete ordinal data

Authors: Yair Shenfeld, Ricardo Baptista, Stefano Peluchetti
Published: 2026-05-01
Categories: cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2605.00360v1

Flow-based generative modeling in continuous spaces exploit Tweedie's formula to express the denoiser (learned in training) as a score function (used in sampling). In contrast, this relation has been largely missing in the discrete setting where common approaches focus on learning discrete scores and rates. In this work we close this gap for discrete non-negative ordinal data by introducing Binomial flows. Our framework provides a simple recipe for training a discrete diffusion model which simultaneously denoises, samples, and estimates exact likelihoods. We verify our methodology on synthetic examples and obtain competitive results on real-world data sets.

---

### From Backward Spreading to Forward Replay: Revisiting Target Construction in LLM Parameter Editing

Authors: Wei Liu, Hongkai Liu, Zhiying Deng, Yee Whye Teh, Wee Sun Lee
Published: 2026-05-01
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2605.00358v2

LLM parameter editing methods commonly rely on computing an ideal target hidden-state at a target layer (referred as anchor point) and distributing the target vector to multiple preceding layers (commonly known as backward spreading) for cooperative editing. Although widely used for a long time, its underlying basis have not been systematically investigated. In this paper, we first conduct a systematic study of its foundations, which helps clarify its capability boundaries, practical considerations, and potential failure modes. Then, we propose a simple and elegant alternative that replaces backward spreading with forward-propagation. Instead of optimizing the target at the last editing layer, we optimize the anchor point at the first editing layer, and then propagate it forward to obtain accurate and mutually compatible target hidden-states for all subsequent editing layers. This approach achieves the same computational complexity as existing methods while producing more accurate layer-wise targets. Our method is simple, without interfering with either the computation of the initial target hidden state or any other components of the subsequent editing pipeline, and thus constituting a benefit for a wide range of LLM parameter editing methods.

---

### MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents

Authors: Tianyu Hu, Weikai Lin, Weizhi Zhang, Jing Ma, Song Wang
Published: 2026-05-01
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.00356v1

Long-term conversational agents must decide which turns to store in external memory, yet recent systems rely on autoregressive LLM generation at every turn to make that decision. We present MemRouter, a write-side memory router that decouples memory admission from the downstream answer backbone and replaces per-turn memory-management decoding with an embedding-based routing policy. MemRouter encodes each turn together with recent context, projects the resulting embeddings through a frozen LLM backbone, and predicts whether the turn should be stored using lightweight classification heads while training only 12M parameters. Under a controlled matched-harness comparison on LoCoMo, where the retrieval pipeline, answer prompts, and QA backbone (Qwen2.5-7B) are held identical, MemRouter outperforms an LLM-based memory manager on every question category (overall F1 52.0 vs 45.6, non-overlapping 95% CIs) while reducing memory-management p50 latency from 970ms to 58ms. Descriptive factorial averaging further shows that learned admission improves mean F1 by +10.3 over random storage, category-specific prompting adds +5.2 over a generic prompt, and retrieval contributes +0.7. These results suggest that write-side memory admission can be learned by a small supervised router, while answer generation remains a separate downstream component in long-horizon conversational QA.

---

### VQ-SAD: Vector Quantized Structure Aware Diffusion For Molecule Generation

Authors: Farshad Noravesh, Reza Haffari, Layki Soon, Arghya Pal
Published: 2026-05-01
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.00354v1

Many diffusion based molecule generation methods ignore the symbolic information of molecules and represent the atom and bond type as one hot representation. Methods based on Morgan fingerprints produce hash collisions and are hard to embed into a continuous space without information loss and random fingerprints correspond to no valid molecule. To circumvent this issue we use another paradigm and consider atom and bond codes as latent variables of VQ-VAE. We introduce VQ-SAD which first trains a VQ-VAE and uses the frozen pretrained VQ-VAE model and considers the codebooks for both atom and bond types as tokenizers for the downstream diffusion process. VQ-SAD is a neuro-symbolic model that utilizes both symbolic and neural structural information for a diffusion based model with learnable forward process. The large discrete code space provides a more balanced atom and bond types which enhances the denoising process. VQ-VAE slightly outperforms SOTA models for diffusion based molecule generation on QM9 and ZINC250k datasets.

---

### Hypergraph and Latent ODE Learning for Multimodal Root Cause Localization in Microservices

Authors: Xin Liu, Yuhang He, Sichen Zhao, Kejian Tong, Xingyu Zhang
Published: 2026-05-01
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2605.00351v1

Root cause localization in cloud native microservice systems requires modeling complex service dependencies, irregular temporal dynamics, and heterogeneous observability data. We present HyperODE RCA, a unified framework that combines hypergraph attention learning, latent ordinary differential equations, and multimodal cross attention fusion for fine grained root cause analysis. The method learns higher order service interactions through differentiable hyperedge construction, captures continuous anomaly evolution from irregular observations with an ODE RNN encoder, and adaptively fuses logs, traces, metrics, entities, and events using context aware modality routing. We further improve robustness with a variational information bottleneck, temporal causal regularization, and invariant risk constraints. Experiments on the Tianchi AIOps benchmark show clear gains over strong baselines in ranking and classification performance, while preserving interpretability through learned hypergraph attention.

---

### CURE-OOD: Benchmarking Out-of-Distribution Detection for Survival Prediction

Authors: Wenjie Zhao, Jia Li, Mingrui Liu, Jing Wang, Yunhui Guo
Published: 2026-05-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.00350v1

``How long can I live and remain free of cancer?'' is often the first question a patient asks after receiving a cancer diagnosis and treatment. Accurate survival prediction helps alleviate psychological distress and supports risk stratification and personalized treatment planning. Recent survival prediction frameworks have shown strong performance using computed tomography (CT) images. However, variations in imaging acquisition introduce out-of-distribution (OOD) samples caused by covariate shifts that undermine model reliability. Despite this challenge, to our knowledge, no existing benchmark systematically studies OOD detection in cancer survival prediction. To address this gap, we introduce the Cancer sURvival bEnchmark for OOD Detection (CURE-OOD), the first benchmark for systematically evaluating OOD detection in survival prediction under controlled acquisition-induced distribution shifts. CURE-OOD defines scanner-parameter-based training, in-distribution (ID), and OOD test splits across four survival prediction tasks. Our experiments show that covariate shifts notably reduce survival prediction performance. It also shows that mainstream classification-oriented OOD detectors can fail in survival prediction. Finally, we include HazardDev as a simple survival-aware reference baseline for OOD detection. CURE-OOD enables systematic analysis of how distribution shifts affect both downstream survival performance and OOD detectability.

---

### Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking

Authors: Joeun Kim, HoEun Kim, Dongsup Jin, Young-Sik Kim
Published: 2026-05-01
Categories: cs.CR, cs.CL
arXiv: https://arxiv.org/abs/2605.00348v2

Recent multi-bit watermarking methods for large language models (LLMs) prioritize capacity over reliability, often conflating decoding with detection. Our analysis reveals that existing ECC-based extractors suffer from catastrophic false positive rates (FPR), and applying rejection thresholds merely collapses detection sensitivity (TPR) to random guessing. To resolve this structural limitation, we propose BREW (Block-wise Reliable Embedding for Watermarking), a framework shifting the paradigm to designated verification. BREW employs a two-stage mechanism: (i) blind message estimation via independent block voting, followed by (ii) window-shifting verification that rigorously validates the payload against local edits. Experiments demonstrate that BREW achieves a TPR of 0.965 with an FPR of 0.02 under 10% synonym substitution, demonstrating that the high-FPR issue is not an inherent trade-off of multi-bit watermarking, but a solvable structural flaw of prior decoding-centric designs. Our framework is model-agnostic and theoretically grounded, providing a scalable solution for reliable forensic deployment.

---

### Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning

Authors: Chengshuai Shi, Wenzhe Li, Xinran Liang, Yizhou Lu, Wenjia Yang, Ruirong Feng, Seth Karten, Ziran Yang, Zihan Ding, Gabriel Sarch, Danqi Chen, Karthik Narasimhan et al.
Published: 2026-05-01
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2605.00347v1

Given the rapidly growing capabilities of vision-language models (VLMs), extending them to interactive decision-making tasks such as video games has emerged as a promising frontier. However, existing approaches either rely on large-scale supervised fine-tuning (SFT) on human trajectories or apply reinforcement learning (RL) only in relatively short-horizon settings (typically around 20--30 turns). In this work, we study RL-based training of VLMs for long-horizon decision-making in Super Mario Land, a visually grounded environment requiring 100+ turns of interaction with coordinated perception, reasoning, and action. We begin with a systematic investigation of key algorithmic components and propose an adapted variant of PPO with a lightweight turn-level critic, which substantially improves training stability and sample efficiency over critic-free methods such as GRPO and Reinforce++. We further show that pretrained VLMs provide strong action priors, significantly improving sample efficiency during RL training and reducing the need for manual design choices such as action engineering, compared to classical deep RL trained from scratch. Building on these insights, we introduce Odysseus, an open training framework for VLM agents, achieving substantial gains across multiple levels of the game and at least 3 times average game progresses than frontier models. Moreover, the trained models exhibit consistent improvements under both in-game and cross-game generalization settings, while maintaining general-domain capabilities. Overall, our results identify key ingredients for making RL stable and effective in long-horizon, multi-modal settings, and provide practical guidance for developing VLMs as embodied agents.

---

### Pose-Aware Diffusion for 3D Generation

Authors: Zihan Zhou, Luxi Chen, Jingzhi Zhou, Yuhao Wan, Min Zhao, Baoyu Fan, Chongxuan Li
Published: 2026-05-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2605.00345v1

Generating pose-aligned 3D objects is challenging due to the spatial mismatches and transformation ambiguities inherent in decoupled canonical-then-rotate paradigms. To this end, we introduce Pose-Aware Diffusion (PAD), a novel end-to-end diffusion framework that synthesizes 3D geometry directly within the observation space. By unprojecting monocular depth into a partial point cloud and explicitly injecting it as a 3D geometric anchor, PAD abandons canonical assumptions to enforce rigorous spatial supervision. This native generation intrinsically resolves pose ambiguity, producing high-fidelity pose-aligned assets. Extensive experiments demonstrate that PAD achieves superior geometric alignment and image-to-3D correspondence compared to state-of-the-art methods. Additionally, PAD naturally extends to compositional 3D scene reconstruction via a simple union of independently generated objects, highlighting its robust ability to preserve precise spatial layouts.

---

### AI Adoption Among Teachers: Insights on Concerns, Support, Confidence, and Attitudes

Authors: Vanessa B. Sibug, Maria Anna D. Cruz, Vicky P. Vital, Juvy C. Grume, Almer B. Gamboa, Emerson Q. Fernando, Lloyd D. Feliciano, Jordan L. Salenga, John Paul P. Miranda
Published: 2026-05-01
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2605.00343v1

The study examines the adoption of artificial intelligence (AI) tools in education by analyzing the roles of institutional support, teacher confidence, and teacher concerns. It aims to determine whether teacher concerns moderate the relationship between institutional support and two outcomes: teacher confidence and attitudes toward AI adoption. The sample included 260 teachers from the Philippines. Composite scores were calculated for institutional support, confidence, concerns, and attitudes. Moderated multiple regression analysis showed that institutional support significantly predicted both teacher confidence and attitudes toward AI. However, teacher concerns did not significantly moderate these relationships. A follow-up mediation analysis tested whether confidence explains the effect of institutional support on attitudes. Results showed full mediation. The indirect effect was significant based on the Sobel test, and the direct effect became non-significant when confidence was included in the model. This shows that institutional support improves teacher attitudes by increasing their confidence. The study recommends that institutions provide structured and ongoing support to strengthen teacher confidence. Professional development, mentoring, and AI integration in teacher education programs can increase readiness and support effective AI adoption.

---

### Making Every Verified Token Count: Adaptive Verification for MoE Speculative Decoding

Authors: Lehan Pan, Ziyang Tao, Xiao Wang, Zhimeng Zhao, Meng Wang, Yanyong Zhang
Published: 2026-05-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.00342v2

Tree-based speculative decoding accelerates autoregressive generation by verifying multiple draft candidates in parallel, but this advantage weakens for sparse Mixture-of-Experts (MoE) models. As the draft tree grows, different branches activate different experts, expanding the union of activated experts and substantially increasing target-side verification cost. We propose EVICT, a training-free, hyperparameter-free, and lossless adaptive verification method for MoE speculative decoding. EVICT makes every verified token count by truncating the draft tree before target verification and retaining only the cost-effective prefix. It leverages fine-grained drafter signals to estimate candidate benefit, combines them with offline-profiled verification cost, and remains highly compatible with the high-performance graph-based serving framework SGLang. Extensive experiments on diverse MoE backbones and benchmarks show that EVICT achieves up to 2.35x speedup over autoregressive decoding and an average 1.21x speedup over the state-of-the-art baseline EAGLE-3, while significantly reducing unnecessary expert activations during verification.

---

### Making Every Verified Token Count: Adaptive Verification for MoE Speculative Decoding

Authors: Lehan Pan, Ziyang Tao, Ruoyu Pang, Xiao Wang, Jianjun Zhao, Yanyong Zhang
Published: 2026-05-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.00342v1

Tree-based speculative decoding accelerates autoregressive generation by verifying multiple draft candidates in parallel, but this advantage weakens for sparse Mixture-of-Experts (MoE) models. As the draft tree grows, different branches activate different experts, expanding the union of activated experts and substantially increasing target-side verification cost. We propose EVICT, a training-free, hyperparameter-free, and lossless adaptive verification method for MoE speculative decoding. EVICT makes every verified token count by truncating the draft tree before target verification and retaining only the cost-effective prefix. It leverages fine-grained drafter signals to estimate candidate benefit, combines them with offline-profiled verification cost, and remains highly compatible with the high-performance graph-based serving framework SGLang. Extensive experiments on diverse MoE backbones and benchmarks show that EVICT achieves up to 2.35x speedup over autoregressive decoding and an average 1.21x speedup over the state-of-the-art baseline EAGLE-3, while significantly reducing unnecessary expert activations during verification.

---

### FES-FM: Free Energy Surface Sampling via Reduced Flow Matching

Authors: Zichen Liu, Tiejun Li
Published: 2026-05-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2605.00337v2

Sampling the distribution of collective variables (CVs) and estimating the associated free energy surface are crucial problems in statistical physics, as they underpin a better understanding of chemical reactions and conformational transitions. Traditional methods usually rely on simulations in high-dimensional configuration space and project the resulting configurations onto the CV space. To improve sampling speed, we propose FES-FM, a reduced flow matching (FM) method for free energy surface (FES) sampling. We train a dynamical transport map in the CV space, thereby enabling direct sampling of CV distributions and reconstruction of the corresponding free energy surface. For many-particle systems, we construct a prior distribution based on the Hessian at a local minimum of the potential, which ensures both rotation-translation invariance and physically meaningful configurations. We evaluate the proposed method across a variety of potential functions and collective variables, including alanine dipeptide in implicit solvent as a molecular benchmark. Comparative experiments demonstrate that our approach significantly improves sampling speed while maintaining accuracy.

---

### Budget-Aware Routing for Long Clinical Text

Authors: Khizar Qureshi, Geoffrey Martin, Yifan Peng
Published: 2026-05-01
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2605.00336v1

A key challenge for large language models is token cost per query and overall deployment cost. Clinical inputs are long, heterogeneous, and often redundant, while downstream tasks are short and high stakes. We study budgeted context selection, where a subset of document units is chosen under a strict token budget so an off-the-shelf generator can meet fixed cost and latency constraints. We cast this as a knapsack-constrained subset selection problem with two design choices, unitization that defines document segmentation and selection that determines which units are kept. We propose \textbf{RCD}, a monotone submodular objective that balances relevance, coverage, and diversity. We compare sentence, section, window, and cluster-based unitization, and introduce a routing heuristic that adapts to the budget regime. Experiments on MIMIC discharge notes, Cochrane abstracts, and L-Eval show that optimal strategies depend on the evaluation setting. Positional heuristics perform best at low budgets in extractive tasks, while diversity-aware methods such as MMR improve LLM generation. Selector choice matters more than unitization, with cluster-based grouping reducing performance and other schemes behaving similarly. ROUGE saturates for LLM summaries, while BERTScore better reflects quality differences. We release our code at https://github.com/stone-technologies/ACL_budget_paper.

---