# Research Papers — 2026-06 · bundle page 25 of 260

> Full-text markdown of papers #1201–1250 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-06/page/25
[← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/24.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-06/page/26.md)

### Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views

Authors: Mijin Yoo, In Cho, Subin Jeon, Jiwoo Lee, Eunbyung Park, Seon Joo Kim
Published: 2026-06-28
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2606.29513v1

A 3D scene is understood through its objects, not the primitives that compose them. Yet feed-forward reconstruction methods output dense, unstructured sets of points or Gaussians, leaving object-level structure to be recovered after the fact. We propose a feed-forward framework that decomposes a scene into instance-structured 3D token groups directly from unposed multi-view images -- compact object-centric units from which reconstruction, segmentation, and manipulation all follow. Each token group pairs an instance token capturing entity-level identity with anchor tokens that encode local geometry and appearance, which are decoded into a set of 3D Gaussians. This two-level factorization decouples object identity from local appearance, making object instances a native interface of the representation rather than a derived product. The token groups are learned through differentiable rendering with joint reconstruction and segmentation supervision, requiring no 3D annotations. Our feed-forward model surpasses per-scene optimization baselines in class-agnostic instance segmentation while remaining competitive in novel view synthesis. Beyond these metrics, the same token groups directly unlock instance-level scene editing -- removing, translating, or inserting objects by operating on their groups -- as well as efficient open-vocabulary 3D instance retrieval, where retrieval complexity scales with the number of instances rather than primitives.

---

### Reinforcement Learning in Super Mario Bros: Curriculum, Pedagogy, and Optimal Level Design in World 1-1

Authors: Jesse Ponnock, Lucas Ho
Published: 2026-06-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.29511v1

World 1-1 of Super Mario Bros is widely celebrated as a masterclass in game design: its progressive structure is credited with teaching players core mechanics through the level itself. We ask whether that structure is empirically measurable using reinforcement learning. We implement World 1-1 from scratch as a fully discrete environment and compare four algorithms -- Q-Learning, SARSA, Monte Carlo, and Deep Q-Network (DQN) -- across three progressively complex versions of the same level. Monte Carlo emerges as the strongest agent (94.9% $\pm$ 1.5% win rate), outperforming DQN (76.4% $\pm$ 3.4%) by learning to maximize intermediate rewards along winning paths rather than taking the most direct route. We then use Monte Carlo in a curriculum experiment permuting World 1-1's six canonical segments across twelve conditions. Canonical ordering converges fastest, achieves the highest learning efficiency, and is the only condition with zero catastrophic failures; no random permutation matches all three criteria simultaneously. These results provide, to the best of our knowledge, the first empirical validation that World 1-1's canonical design encodes genuine pedagogical structure: one that measurably accelerates learning and cannot be replicated by chance.

---

### Benchmark AUC Is Not Deployable Reliability: A Cross-Dataset Audit of Off-the-Shelf Features for Surveillance Video Anomaly Detection

Authors: Mohammadreza Rashidi
Published: 2026-06-28
Categories: cs.CV, cs.CR
arXiv: https://arxiv.org/abs/2606.29506v1

Automated "suspicious behavior" flagging is a headline promise of AI surveillance, and the field reports high frame-level ROC-AUC on standard video anomaly detection benchmarks. Those numbers are measured by training and testing on the same camera and scene. We audit what happens when that assumption is dropped. We build an unsupervised normality model from the all-normal training frames of one dataset, using frozen off-the-shelf embeddings (CLIP, DINOv2, ResNet-50, EfficientNet-B0) and a nearest-neighbour distance, and score the test frames of the same and of other datasets. Across 4 real datasets (UCSD Ped1, UCSD Ped2, CUHK Avenue, ShanghaiTech) and 4 backbones, same-dataset AUC averages 0.704 but cross-dataset AUC averages 0.499, which is chance: a detector calibrated on one scene is no better than a coin flip on another, and in several pairs it is below chance. The strongest backbone makes this worse, not better: DINOv2 has the best same-dataset AUC (up to 0.901 on Ped2) and the largest cross-dataset drop. The collapse is not an artefact of the scoring rule: replacing the nearest-neighbour detector with a PaDiM-style Mahalanobis detector reproduces it almost exactly (cross-dataset gap 0.202 versus 0.208). Even at a favourable operating point the false-alarm rate is on the order of 31,931 per hour. We conclude that the benchmark numbers quoted for surveillance anomaly detection describe a calibrated laboratory setting and overstate deployable reliability by a wide margin, and we release the code that reproduces every number.

---

### Empirical Evaluation of Multi-Modal Touch Detection in Over-the-Shoulder Video Surveillance

Authors: Mohammadreza Rashidi
Published: 2026-06-28
Categories: cs.CV, cs.CR
arXiv: https://arxiv.org/abs/2606.29504v1

Video Intelligence Surveillance (VIDINT) on over-the-shoulder footage is a proposed vector for monitoring human-computer interaction patterns without direct screen recording access. In this paper, we evaluate a Behavioral Intelligence (BEHINT) touch-detection framework designed to reconstruct keystroke events on mobile keypad interfaces from physical finger interactions. Our system integrates four parallel detection modalities: (1) anatomical hand landmarks via MediaPipe, (2) HSV skin color filtering, (3) temporal frame differencing for motion detection, and (4) shape-guided Canny edge analysis. We map relative touch coordinates to a reference screen layout to reconstruct typing sequences. Evaluation on a 120-frame first-person staged video of passcode entry reveals that while MediaPipe and Skin Detection fail to run autonomously due to partial hand occlusion and ambient noise, Motion-Only and Edge-Only configurations achieve F1-scores of 18.5% and 18.2%, respectively. The combined multi-modal configuration achieves an F1-score of 16.7% and a sequence similarity of 3.0% when mapped to the iOS passcode layout. We conduct ablation, resolution decay, noise sensitivity, and proximity threshold tuning to characterize the system's operational envelope. We then audit generalization on 5 real, publicly licensed third-person phone videos and find that the detector emits a median of 57 touch points per frame (peaking at 205), one to three orders of magnitude more than the rate of real taps, because the skin filter responds to the whole hand rather than to fingertip contact. The staged keystroke result does not survive contact with uncontrolled footage; the system does not achieve reliable keystroke reconstruction outside the calibrated staged setting.

---

### The Verbose Context Problem in Medical Records

Authors: Shiva Kaul, Min-Gyu Kim, Anjum Khurshid, Sriram Vishwanath
Published: 2026-06-28
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.29503v1

The verbose context problem occurs when structured concepts have token-inefficient textual representations. This bottleneck is acute in population health: cohort-level analysis of longitudinal patient records requires reasoning over thousands of medically-coded events, often exceeding 400K tokens in total. We present PopMedQA, a benchmark isolating this problem through computational tasks on groups of longitudinal patient records. We construct the benchmark using neopatient, a new library for language-controlled generation of artificial patient records. Through extensive ablations -- including prompting strategies, prompt compression, and agentic decomposition -- we find that domain-independent methods fail to alleviate the verbose context problem. There remains significant opportunity to exploit domain-specific structure in language model inputs for population-scale reasoning.

---

### UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation

Authors: Songjun Tu, Chengdong Xu, Qichao Zhang, Yiwen Ma, Yaocheng Zhang, Linjing Li, Dong Li, Xiangyuan Lan, Dongbin Zhao
Published: 2026-06-28
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2606.29502v2

Skill memories can improve agentic reinforcement learning by reusing past experience as textual guidance, but retrieved skills are not oracular: they may help in one state while misleading the same policy in another. This makes the common privileged-teacher assumption fragile, namely that a skill-conditioned prompt can be treated as a fixed teacher for the no-skill prompt. We introduce UCOB, a framework for learning to utilize and evolve agentic skills via credit-aware on-policy bidirectional self-distillation. UCOB treats skill-conditioned and no-skill prompts as two on-policy context views of the same model, compares their return-to-go within the same task and anchor state, and uses the higher-return view as the local teacher. This local credit signal internalizes useful skill-conditioned behavior, corrects misleading skill usage, and guides task/state skill memory updates, utility-aware retrieval, and reflection self-training. Experiments on agentic tasks, including ALFWorld, WebShop, and Search-QA, show that UCOB outperforms skill-free RL, skill-memory baselines, and self-distillation methods across model scales, with up to 23.5 and 18.0 point gains over SOTA baselines on ALFWorld and WebShop. Ablations and analyses further validate its core mechanisms, continual adaptation across environments, and modest training overhead. Code is available at https://github.com/TU2021/UCOB.

---

### Learning Where and When: Patch-Based Spatiotemporal Localization in Weakly Supervised Video Anomaly Detection

Authors: Hamza Karim, Nghia Nguyen, Lokman Bekit, Yasin Yilmaz
Published: 2026-06-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.29498v1

Weakly supervised video anomaly detection (WSVAD) has predominantly focused on temporal localization, identifying when anomalies occur while largely neglecting their spatial extent within frames. Yet, spatial localization is essential for interpretability and practical deployment in real-world settings. We introduce a patch-based spatiotemporal framework for weakly supervised anomaly localization that jointly models where and when anomalies occur. Our approach operates on grid-level patch features and learns region-level anomaly scores under a multiple instance learning paradigm. We further propose a Proximity-Aware Top-k spatiotemporal selection strategy that enables the model to generate fine-grained spatial anomaly maps without requiring bounding-box supervision during training. Our method surpasses existing state-of-the-art approaches across multiple benchmarks, yielding substantial gains in spatiotemporal localization accuracy. In addition, we release frame-level bounding-box annotations for the test sets of two widely used datasets, along with our code and pretrained models, providing new resources to facilitate future research in spatially grounded WSVAD.

---

### Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarios

Authors: Wongi Park, Jiyeon Lim, Minjae Lee, Myeongseok Nam, Seongjun Choi, Jungwoo Kim, Soomok Lee, William J. Beksi, Sang-Hyun Lee
Published: 2026-06-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.29496v2

We present RefineSplat, a systematic framework that effectively constructs transient masks to identify diverse ambiguous distractors. To do this, we qualitatively and quantitatively analyze issues and propose a novel entropy-aware adaptive masking method. Unlike existing approaches that struggle to distinguish transient elements from static scenes due to color or semantic ambiguity, RefineSplat captures ambiguous distractors leveraging entropy and instance masks. Furthermore, we propose a simple yet effective entropy-aware density control to align Gaussians in ambiguous scenarios considering Entropy-aware positional gradients. Additionally, to rigorously validate our method, we first create and release the Ambiguous wild dataset, including 18 scenes where distractors and static scenes are hard to distinguish due to color or semantic resemblances. Experimental results on various datasets demonstrate that RefineSplat shows state-of-the-art performance, showing distractor-free novel view synthesis.

---

### Cognitive World Model for Progressive BDI/E Trajectory Evaluation of Conversational Agents

Authors: Minghui Ma, Bin Guo, Hao Wang, Han Wang, Mengqi Chen, Jingqi Liu, Yan Liu
Published: 2026-06-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.29495v2

As LLM-based conversational agents advance toward increasingly open-ended and interaction-intensive scenarios, task completion alone provides an incomplete assessment of their effectiveness. The evolution of users' internal states, including beliefs, desires, intentions, and emotions (BDI/E), serves as an intermediate signal connecting agent behaviors with interaction outcomes and reflects how conversational strategies shape users during multi-turn interactions. However, existing evaluation paradigms primarily focus on surface-level responses or final outcomes, providing limited insight into the underlying cognitive processes. This limitation makes it difficult to diagnose why agents succeed or fail and to optimize their interaction strategies. To address this challenge, we propose Cognitive World Model (CogWM), an LLM-based cognitive user model that jointly models users' BDI/E states and corresponding responses, enabling explicit cognitive trajectory tracking. Trained on 150K user-turn samples with Qwen3-14B, CogWM achieves superior performance over existing user simulation baselines in both response fidelity and cognitive state understanding. Interactions with six state-of-the-art LLMs demonstrate that CogWM enables progressive comparison of agents through cognitive trajectories, revealing distinct agent patterns and complementary relationships between cognitive evolution and behavioral outcomes.

---

### VCS-SLAM: Geometry-Validated Semantic Evidence Fusion for 3D Gaussian SLAM

Authors: Raman Jha, Shuaihang Yuan, Yi Fang
Published: 2026-06-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.29494v1

Visual SLAM performance often deteriorates in complex real-world applications. Semantic 3D Gaussian SLAM commonly fuses 2D semantic priors into a persistent 3D map using uniform optimization weights. However, such priors are not equally reliable in online mapping: occlusions, unsupported semantic boundaries, and ambiguous ray geometry can introduce persistent semantic artifacts into the global Gaussian map. We propose VCS-SLAM, a geometry-validated semantic evidence fusion framework for RGB-D 3D Gaussian SLAM. Instead of treating all semantic observations as uniformly valid supervision, VCS-SLAM evaluates their geometric reliability through visibility consistency, surface-supported boundary evidence, and ray-level conflict uncertainty. The resulting reliability-aware objective suppresses occluded semantic updates, reduces unsupported semantic bleeding, and delays premature label assignment in ambiguous regions. Experiments on Replica demonstrate improved semantic consistency, boundary preservation, and reconstruction quality. Results on ScanNet further show that VCS-SLAM maintains competitive tracking performance under real RGB-D inputs

---

### Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving

Authors: Pawan Sasanka Ammanamanchi, Siddharth Bhat, Stella Biderman
Published: 2026-06-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.29493v1

Benchmarks for LLM-assisted theorem proving in Lean are often treated as intrinsically reliable because every solved instance comes with a machine-checked proof. However, the kernel only checks that a proof establishes a \emph{formal} statement; it does not verify that the statement faithfully encodes the intended informal problem, nor that evaluation harnesses are robust to trivial or adversarial solutions. We audit five widely used Lean theorem-proving benchmarks and their forks, using corpus-scale static checkers to surface 4,833 findings, including 398 mechanically certified issues such as counterexamples, vacuous theorems, and unsound axioms. We also document semantic defects such as missing hypotheses, problem simplification, incomplete or incorrect translations, and Lean-specific specification hazards. Beyond dataset construction, we survey evaluation-time failure modes and show, on corrected subsets, that defects can both inflate and deflate reported prover scores. We propose a fault taxonomy, a suite of automated checkers and recall-oriented semantic audit prompts, and release standards to guide the creation of formal math datasets and to make evaluation more reproducible and trustworthy. Our checkers, audit prompts, and corrected dataset snapshots are available at https://github.com/Shashi456/atp-checkers.

---

### Reported Confidence in LLMs Tracks Commitment More Than Correctness

Authors: Dharshan Kumaran
Published: 2026-06-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.29490v1

Confidence is an estimate of the probability that a chosen answer is correct. Verbal confidence reports are widely used as uncertainty measures in large language models, but whether they are best understood as estimates of correctness is unclear. We test this with a two-stage abstention paradigm from the neuroscience of perceptual decision making: a model first answers and reports its confidence, then decides whether to commit it to a user or abstain. Across four non-reasoning models, prompt framings, and confidence formats, verbal confidence predicted the commit/abstain decision substantially better than whether the answer was correct. Calibrated token log-probabilities showed the opposite profile, with abstention-prediction coupled to correctness discrimination, the signature of an answer-evidence signal. After removing the variance verbal confidence shared with log-probabilities, the residual stayed aligned with commitment while its link to correctness fell to near chance. The dissociation generalised to four reasoning models across four benchmarks of varying difficulty, from hard multiple-choice to frontier-level freeform questions. Mechanistic analyses in Gemma 3 and 4 were convergent: a post-answer state known to causally support verbal-confidence generation already encoded the future abstention decision before the abstention prompt, organised mainly by that decision rather than by correctness, the two lying in approximately orthogonal directions in activation space. Steering along a verbal-confidence-specific direction causally shifted abstention. Verbal and log-probability confidence are thus not interchangeable: log-probabilities track answer evidence and correctness, whereas verbal confidence is better understood as a behaviour-facing readout of an internal commit-readiness state, challenging the practice of treating verbal reports as proxies for reliability.

---

### Which Tokens Need Context? A Reference-Based Analysis of Translation Responsibility Using Fertility and Entropy

Authors: Ramakrishna Appicharla, Baban Gain, Santanu Pal, Asif Ekbal
Published: 2026-06-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.29489v1

When humans translate, not every word depends equally on the surrounding context. Some tokens, particularly function words like pronouns and auxiliaries, rely heavily on preceding or following sentences, while others, such as proper nouns, do not. Understanding this inherent context sensitivity is essential for evaluating whether machine translation systems use context in human-like ways. However, existing approaches to analysing context usage rely on discourse-specific test sets or model internals, making them narrow or model-dependent. We propose a post-hoc, model-agnostic framework to quantify context sensitivity at lexical and syntactic levels using two measures derived from word alignments: fertility (number of target tokens generated per source token) and entropy (stability of fertility patterns across contexts). Using reference translations for three language pairs (German $\leftrightarrow$ English, English $\rightarrow$ Hindi) under four context conditions, we show that context selectively redistributes generative responsibility from source to context tokens without altering overall fertility. Function words show the largest fertility reductions, while content words remain stable, suggesting that context resolves ambiguity rather than adding new information. Our framework provides a ground-truth characterisation of selective context usage in human translation, establishing a diagnostic baseline for evaluating machine translation models.

---

### The Calibrated Deepfake Trust Score (CDTS): Competence-Coupled Trust Degradation Across Deepfake Detectors

Authors: Md Anas Biswas
Published: 2026-06-28
Categories: cs.CR, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2606.29484v2

In moderation, provenance, and verification pipelines a deepfake detector's output probability is read as a degree of trust, so its calibration matters as much as raw accuracy. We reframe deepfake detection as a calibrated, self-auditing trust instrument, the Calibrated Deepfake Trust Score (CDTS), and identify what governs its trustworthiness. Our central finding is a competence-trust coupling with a sharp division: the raw score's miscalibration tracks discriminative competence almost perfectly (r = -0.98, -0.98, -0.95 across two convolutional networks and a CLIP vision transformer), and a calibrator deployed without target labels fails with competence just as tightly (r = -0.98 on the primary detector, for isotonic, Platt, and beta calibrators alike). Given target labels, by contrast, any well-specified calibrator repairs any detector, including inverted ones: in-domain calibratability is not competence-limited, and the trust failure is a distribution-shift phenomenon concentrated exactly on the low-competence generators that motivate deployment. Explanation faithfulness rises and falls on the same competence axis. We reach this conclusion after uncovering, and correcting, a tie-handling degeneracy in the standard equal-mass expected-calibration-error (ECE) estimator that fabricates strong spurious competence-calibration coupling on tie-heavy calibrated scores; the same degeneracy invalidates calibration-equity gaps we previously reported, a caution for fairness auditing. Competence is trackable without labels: batch predictive entropy flags generators with high deployed calibration error at ROC-AUC 0.99, and routing source-batches on label-free competence beats confidence-based routing precisely in the low-competence regimes the coupling identifies, while confidence regains the advantage where competence is high. Trust scoring must be competence-aware; CDTS is the mechanism.

---

### The Calibrated Deepfake Trust Score (CDTS): Competence-Coupled Trust Degradation Across Deepfake Detectors

Authors: Md Anas Biswas
Published: 2026-06-28
Categories: cs.CR, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2606.29484v1

Modern deepfake detectors are rarely consumed as bare classifiers. In moderation, provenance, and verification pipelines their output probability is read as a degree of trust, so its calibration matters as much as raw accuracy. We reframe deepfake detection as a calibrated, self-auditing trust instrument, the Calibrated Deepfake Trust Score (CDTS), and identify what governs its trustworthiness. Our central finding is a competence-calibration coupling: the calibration of the trust score degrades as the detector's discriminative competence falls. We establish it across 32 configurations (pooled Pearson r = -0.81), demonstrate it within a single dataset, reinforce it by inducing low competence directly, and replicate it on a fourth held-out dataset the detectors never trained on. It holds across three architecturally distinct detectors, two convolutional networks and a CLIP vision transformer (r = -0.88, -0.83, -0.86). The result is also deployable: a single calibrator frozen on in-domain data fails on exactly the low-competence generators the coupling flags (its error tracks competence at r = -0.98), and competence is estimable without labels, so a label-free monitor flags calibration risk on unseen generators and routing source-batches on a reference-free competence estimate lowers overall AURC and improves the low-to-mid coverage operating region relative to confidence-based routing. The same competence factor also drives calibration inequity across demographic subgroups (distinct from accuracy inequity) and explanation faithfulness. We therefore argue that detector trustworthiness is organized by competence as a shared driver, that competence is the right quantity to estimate and condition on, and that trust scoring must be competence-aware. We offer the CDTS wrapper as the mechanism, and report openly where the unification is tight and where it is architecture-specific.

---

### To Reason or to Fabricate: Reasoning Without Shortcuts via Hint-Anchored Pairwise Aggregation

Authors: Jiuheng Lin, Chen Zhang, Yansong Feng
Published: 2026-06-28
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2606.29481v1

While reinforcement learning (RL) significantly enhances LLM reasoning, its efficacy is severely undermined by Pre-RL data overlap, where RL datasets overlap with pretraining or SFT corpora, causing models to exploit shortcuts by memorizing correct answers and fabricating post-hoc reasoning. To address this, we introduce HIPPO, a novel RL framework that integrates hint-injected aggregation with a tailored pairwise reward model. By utilizing hint injection to deliberately trigger overlap-induced behaviors, the resulting traces naturally serve as explicit anchors for pairwise comparison. This provides highly discriminable preference signals, enabling a lightweight judge model to reliably distinguish genuine reasoning deduction from shortcut-driven rationalization, while the pairwise formulation ensures stable and robust optimization compared to standard PRMs. Extensive experiments demonstrate that HIPPO yields substantial improvements over standard baselines and generalizes effectively to out-of-distribution general tasks, showing it extracts authentic, transferable reasoning skills rather than superficial shortcut patterns.

---

### Chamber geometry and specification numbers of Boolean threshold functions

Authors: Martin Anthony
Published: 2026-06-28
Categories: cs.DM, cs.LG, math.CO
arXiv: https://arxiv.org/abs/2606.29477v1

The specification number $σ_n(f)$ of a Boolean threshold function $f$ on $n$ variables is the least number of points whose $f$-values determine $f$ uniquely among all threshold functions. Its essential points form the unique minimum such set. We develop Zuev's geometric interpretation: the threshold functions are the chambers of a central hyperplane arrangement in the $(n+1)$-dimensional space of weights and thresholds, and the essential points of a function correspond exactly to the facets of its chamber, so the specification number is the chamber's facet number. The lower bound $σ_n(f)\ge n+1$ becomes the fact that a pointed full-dimensional cone has at least $n+1$ facets, with equality for simplicial chambers. The average specification number $\overlineσ_n$ becomes an average facet count. We evaluate this average exactly via the resonance arrangement and bound it through a theorem of Fukuda, Tamura, and Tokuyama, obtaining $\overlineσ_n\le 2n$; hence $\overlineσ_n=Θ(n)$. This settles a question of Gutekunst, Mészáros, and Petersen. The method also extends to polynomial threshold functions. The same geometry links threshold functions with a threshold zonotope, whose vertices are modified Chow vectors. Its one-skeleton is the one-inclusion graph, and a vertex's degree is the specification number of that function. Finally, we treat the operations of Lozin et al. on functions of minimum specification number. Adding a variable and extending on a variable both take the product of a chamber closure with a half-line, preserving simpliciality. For the symmetric-variables extension we give an exact thresholdness criterion and show that minimum specification number is preserved whenever the extension is a threshold function. We also resolve a question they pose concerning a fourth operation.

---

### CRAFT: Counterfactual Credit Assignment from Free Sibling Rollouts for Self-Distilled Agentic Reinforcement Learning

Authors: Zibin Meng, Kani Chen
Published: 2026-06-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2606.29476v1

Self-distilled agentic reinforcement learning augments trajectory-level reward with a token-level distillation loss, using as its teacher the same policy conditioned on privileged context. The prevailing recipe gates this loss by a single scalar, the teacher-student log-probability gap. This signal is doubly limited: it is retrospective, scoring only the realised rollout and never the counterfactual ones, and it is sign-blind, never signalling when a teacher-preferred action would have harmed the trajectory. We introduce CRAFT, a three-pillar credit-assignment scheme that addresses both limitations. Pillar 1, Counterfactual Token Importance, reuses the G-1 sibling rollouts that GRPO already samples and importance-weights them by the log-probability gap to form a self-normalised estimate of the group-level counterfactual change in advantage from up-weighting teacher-preferred actions at each step; this yields a signed per-token credit at near-zero extra compute. Pillar 2 is an asymmetric controller that raises the distillation weight as it lowers the reference-KL weight along an exponential moving average of gate activity, and conversely. Pillar 3 polarises the KL penalty token by token, switching between a mode-seeking and a mode-covering update according to the sign of the credit. Each pillar has an independent switch that, when disabled, renders the loss and gradient byte-identical to the baseline in IEEE-754 arithmetic, so any measured gain is attributable to algorithmic change rather than implementation drift. We prove the estimator's consistency and a variance bound, give structural and bit-exact reproducibility guarantees, and evaluate CRAFT across three agentic environments, four model scales, and five end-to-end methods, plus two tabulated prior-work baselines. Among these is Adaptive-CRINGE, a comparator sharing Pillar 2 with CRAFT, isolating the counterfactual contribution.

---

### A Posteriori Error Analysis for Decoupled Neural Approximations of Fully Coupled FBSDEs with Control Mismatch

Authors: Xichuan Zhang
Published: 2026-06-28
Categories: math.OC, cs.AI, math.NA
arXiv: https://arxiv.org/abs/2606.29474v1

This paper develops an a posteriori error analysis framework for decoupled neural approximations of fully coupled forward--backward stochastic differential equations (FBSDEs). It provides an a posteriori error-analysis for the idealized discrete adapted trajectory. The main feature of the proposed formulation is the use of an auxiliary control process in the forward coefficients, which may differ from the backward component approximated by the neural network. This decoupling is useful in practical deep learning implementations, but it creates a control mismatch that must be included in the error analysis. We first establish a continuous-time stability estimate for fully coupled FBSDEs under perturbations of the drift, diffusion, generator, terminal condition, and auxiliary control input. We then transfer this estimate to the discrete-time setting and derive computable a posteriori error bounds depending only on the terminal defect, the pathwise residual, and the control mismatch. When the auxiliary control is identified with the backward approximation, the mismatch term vanishes and the bound reduces to the standard two-term form. Numerical experiments on a linear--quadratic FBSDE with an explicit reference solution and a multidimensional Burgers-type FBSDE without a reference solution illustrate the diagnostic role of the proposed indicators and the contribution of the mismatch penalty to the consistency and reproducibility of the numerical approximations.

---

### MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control

Authors: Kaiqi Liu, Yunyao Mao, Ziqi Cai, Zheng Geng, Jing Wang, Qiulin Wang, Xintao Wang, Pengfei Wan, Kun Gai, Shuchen Weng, Boxin Shi
Published: 2026-06-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.29473v2

While recent generative models produce high-fidelity videos, they struggle with the complex narrative control required for coherent multi-shot audio-visual generation. Existing methods suffer from temporal misalignment, limited controllability, and incomplete scripting. In this paper, we propose MAVIN, the first framework for multi-shot audio-visual generation with customized narrative control. To resolve temporal misalignment, we propose boundary-aware attention, which leverages hierarchical captions and boundary-aware token routing to render audio-visual elements within their respective temporal boundaries. To improve the controllability for multi-subject scenarios, we propose ID-aware propagation, utilizing identity embeddings and an identity-aware mask to bind specific identities to consistent visual appearances and vocal timbres. To provide comprehensive audio-visual narratives, we present a multi-agent scripting pipeline to transform free-form user inputs into hierarchical captions. Furthermore, we construct MAVINSet, a multi-shot audio-visual dataset for robust training and evaluation. Extensive experiments demonstrate that MAVIN achieves state-of-the-art performance, opening up a new avenue for integrating generative models into professional filmmaking workflows.

---

### Agent-Computer Observation Interfaces Enable Dynamic Computer Use

Authors: Bojie Li, Noah Shi
Published: 2026-06-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.29472v1

SWE-agent established the action interface as an underexplored design axis for software-engineering agents; we make the analogous case for the observation interface in computer-use (CU) agents. Current CU agents, closed and open-source alike, tie observation to action--one screenshot every 3-5 s, no audio--leaving them blind and deaf between screenshots to video, animations, transient UI events, meetings, and spoken instructions. We introduce the Agent-Computer Observation Interface (AOI), a model-agnostic perception layer that decouples continuous, adaptive observation from discrete actions through three gated components: inter-step keyframe capture, volume-gated audio transcription, and CU-model-generated visual narration that persists as text. Each produces almost nothing on static, silent content, reducing to the standard loop without degrading it. On DynaCU-Bench (100 dynamic browser tasks plus a 50-task static control), CU models from 7B to frontier scale gain +17 to +48 pp over their screenshot baselines with zero retraining, turning tasks that are near-impossible from periodic screenshots into largely solved ones. The gap is starkest on audio: on a spoken-content subset AOI agents solve every task, whereas streaming voice models hear accurately but cannot act on what they hear without the scaffold. The decomposition is as informative as the headline gain: keyframe selection turns out not to matter--the value comes from narrating captured frames into persistent text--and the interface is not a fixed bundle, since on a newer model (Gemini 3 Flash) the keyframe stream actively regresses through image-token dilution, so its components must be selected per model rather than shipped as one configuration.

---

### Structured Proper Loss Geometries for Multiclass Classification: Theory and Controlled Empirical Evaluation

Authors: Soumyadip Sarkar
Published: 2026-06-28
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2606.29471v1

Strictly proper scoring rules identify the true conditional class distribution at population level, but their curvature can alter optimization and finite-sample behavior. We study three multiclass objectives: a class-aware quadratic Bregman score (CAPM), a strongly convex generator with constrained log-cosh ridges (HPG), and an HPG objective with an annealed probability-margin penalty (APMS). CAPM is treated as a structured instance of established quadratic scoring-rule theory. We derive conditional-regret, curvature, range, and logit-gradient bounds for CAPM and HPG, and prove exact penalty-range and conditional-target displacement bounds for APMS. Controlled five-seed experiments use Digits, Wisconsin breast cancer, and synthetic confusion and long-tail problems under clean labels, symmetric and pair-flip corruption, class imbalance, calibration evaluation, input corruption, and first-order adversarial perturbations. The candidates are close to cross-entropy on clean data and show descriptive gains in some noisy-label cells, but the five-seed comparisons are interpreted descriptively rather than as significance evidence. The selected noisy-label baselines perform better on Digits with 40% symmetric label noise, and explicit prior-adjustment methods perform better in the 30:1 synthetic long-tail experiment. Ablations do not show a consistent benefit from the candidate-specific graph, ridge, or margin components. The mathematical analysis establishes the stated properties, and the experiments delimit the empirical evidence; together they do not support a claim of general superiority.

---

### mamabench and mamaretrieval: Benchmarks for Evaluating Medical Retrieval-Augmented Generation in Maternal, Neonatal, and Reproductive Health

Authors: Yi Ren
Published: 2026-06-28
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2606.29467v3

Medical question-answering benchmarks rarely cover the maternal, neonatal, child, and reproductive-health questions a nurse-midwife asks, and, to our knowledge, no public chunk-level relevance benchmark exists for maternal-health guideline retrieval. We release two benchmarks that fill these gaps. mamabench is a scope-filtered QA set of 25,949 items assembled from seven existing expert-authored sources across multiple-choice, short-answer, and rubric-graded tracks; to help users calibrate the LLM judge that scores the rubric track, we re-scope HealthBench's physician-labelled meta-evaluation to the domain. mamaretrieval pairs 3,185 clinical queries with graded (0-6) relevance labels over a 63,650-chunk maternal-health guideline corpus, using a decomposed rubric that distinguishes a chunk that answers a query from one merely on its topic. Three decisions shape both: assemble and filter expert sources rather than author questions, grade relevance rather than binarise it, and measure and disclose the limits of the labels -- scope-classifier agreement, a frontier-judge check, and a pooling-completeness audit -- rather than treat them as an oracle. A companion paper uses the benchmarks to evaluate a deployed on-device assistant; both are released openly for research.

---

### Self-Supervised Calibration of Scientific Instruments Using Physical Consistency Constraints

Authors: M. Rejmund, A. Lemasson
Published: 2026-06-28
Categories: cs.LG, nucl-ex, physics.ins-det
arXiv: https://arxiv.org/abs/2606.29466v1

Calibration remains one of the principal obstacles to the deployment of machine learning in scientific instrumentation because it typically relies on expert intervention, dedicated procedures, and manually labelled data. We introduce a physics-informed self-supervised framework that jointly learns latent detector calibration parameters and task-specific predictions directly from raw measurements without requiring pre-calibrated signals or external labels. The method exploits known physical constraints to generate pseudo-labels iteratively, transforming calibration into a self-supervised optimization problem. The approach is demonstrated for ionic charge-state determination in the VAMOS++ magnetic spectrometer, where the calibration of a segmented ionization chamber and the inference of ionic charge states are learned simultaneously. Starting from a weak prior on the mean ionic charge state, the model progressively refines its predictions through iterative fractional pseudo-labelling driven by the discrete nature of atomic masses. Beyond accurate ionic charge-state reconstruction, the inferred calibration coefficients provide a compact representation of the detector state that enables automated monitoring of gain drifts, pressure variations, and detector aging. The resulting labels can subsequently be transferred to specialized models that quantify detector imperfections and track their spatial and temporal evolution. These results establish a general paradigm for self-calibrating and self-monitoring scientific instruments and represent a step toward intelligent experimental systems capable of autonomous calibration, analysis, and performance optimization.

---

### Prototype Latent World Model Replay for Class-Incremental Learning

Authors: Weizhi Nie, Hui Wang, Weijie Wang, Yuting Su
Published: 2026-06-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.29465v1

Class-incremental learning requires a model to learn new classes while preserving decision regions for old ones. This is difficult when raw old samples are no longer available. We propose Prototype Latent World Model Replay, a memory-free framework that stores old classes as distributions over stable hidden states rather than as images. A frozen ImageNet-pretrained encoder maps each image into a latent state space. In this space, each class is summarized by several prototype-centered distributions with class-specific variances. When new classes arrive, the model samples old latent states from this prototype world model. It then trains a lightweight adapter and classifier using both sampled old states and real new-class features. We also add a supervised contrastive term in the adapter space to promote intra-class compactness and old-new class separation. On Split CIFAR-100, our method improves over fine-tuning under Inc5, Inc10, and Inc20 without storing raw exemplars. The full Ours-LWM+Con model raises LastAcc from 4.55% to 31.64%, from 9.06% to 37.06%, and from 16.96% to 43.10% in Inc5, Inc10, and Inc20, respectively. It also achieves AvgAcc of 45.86%, 52.19%, and 56.18%. Ablation and retention analyses show that stable latent-state replay is the main source of the gain. Contrastive separation further refines the old-new geometry. These results suggest that prototype latent memory preserves reusable class-state distributions, rather than only fitting the current classifier.

---

### Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation

Authors: Jongoh Jeong, Sun-Kyung Lee, Kuk-Jin Yoon
Published: 2026-06-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2606.29464v1

Vision-language dataset distillation (VLDD) compresses a large image-text paired dataset into a small set of synthetic pairs that can efficiently train contrastive vision-language models under strict data and compute budgets. Most existing methods match expert trajectories or cross-modal statistics, yet still enforce full-dimensional alignment in a Euclidean embedding space. This is often overly restrictive due to rank-deficient image--text correlation, with shared semantics concentrated in a low-dimensional range and remaining variation spread across a weakly correlated residual subspace. LoRS relaxes alignment at the similarity level by low-rank factorization, but does not explicitly control dominant alignment capacity and structure in the representation space. We thus propose a rank-aware hyperbolic alignment (RAHA) that combines hierarchical geometry with explicit alignment-capacity control. RAHA lifts multimodal representations to hyperbolic space and optimizes distilled pairs with asymmetric objectives that enforce geodesic alignment in the shared range while regularizing the residual subspace to preserve modality-private diversity and improve transfer robustness. Experiments on benchmarks show that RAHA demonstrates competitive cross-modal retrieval and improved transfer indicators under fixed budgets.

---

### CellDETR: A Detection-Guided Framework for Scalable Cell Representation Learning from Histopathology Images

Authors: Shikang Zhang, Guojun Li, Yicong Mao, Chulin Sha
Published: 2026-06-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.29463v1

Recent advances in pathology foundation models have substantially improved patch and slide level representation learning from whole-slide images (WSIs).However, cell-level representations learning remain underexplored, limiting cell resolved interpretability, biological discovery, and clinical translation. We propose CellDETR, a detection-guided framework built on Deformable DETR for scalable cell representation learning from WSIs. By introducing location feature decoupling and box-constrained attention mechanism, CellDETR enables automated extraction of cell-level embeddings, and outperform existing state-of-the-art methods in supervised cell classification on PanNuke data. In addition, by incorporating contrastive learning design, we build a CellDETR-based pretraining model for scalable cell representation learning from unlabeled WSIs, which improves downstream cell classification performance. Furthermore, we show that after pretraining with Xenium spatial transcriptomics-derived cell annotations, CellDETR achieves accurate cross-dataset cell classification, demonstrating the transferability and biological relevance of the learned cell embeddings. Together, CellDETR provides a scalable route toward general cell-level representation learning framework for interpretable computational patholog

---

### MIRROR: Aligning Semantic Relations from Language to Image via Gromov--Wasserstein

Authors: Hong-Han Wang, Yuntao Wang, Hu Ding
Published: 2026-06-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.29462v1

Multimodal Large Language Models (MLLMs) inherit rich relational priors from their language backbones, yet often fail when asked to apply these relationships in visual contexts. We trace this failure to a structural blind spot: projection-based alignment trains each visual token to carry the right semantics, but never asks whether the relationships between concepts survive the crossing from language to vision. To address this, we propose MIRROR (Mapping Inter-concept Relations from language to visual Representation via Optimal-transport-based Regularization), a geometric regularization framework that transfers relational priors from language to vision by exploiting the rich relational structure encoded in language representations. Specifically, we derive a surrogate loss from the proposed Semi-Inverse Gromov-Wasserstein (SI-GW) problem, an inverse geometric problem that aligns visual representations with language-derived relational priors. We show that this formulation admits a unique closed-form solution that prescribes the ideal visual relational structure implied by language geometry and cross-modal coupling. The structure of the formulation also enables efficient computation, making it applicable to long token sequences. Applying SI-GW inside decoder-only Transformers requires careful design. We introduce targeted strategies at the layer, head, and token levels to ensure stable extraction without additional parameters or inference cost. MIRROR improves relational consistency while preserving performance on general vision-language tasks.

---

### From Phase to Phenomenon: Self-Supervised Learning of Subsurface Scattering with Minimal Phase-shift Inputs

Authors: Arjun Majumdar, Raphael Braun, Andreas Engelhardt, Hendrik PA. Lensch
Published: 2026-06-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.29461v1

We propose a self-supervised pretraining framework for learning sub-surface scattering (SSS) light transport representations from minimal input. Our method leverages a stereo projector-camera setup that captures only eight high-frequency phase-shift profilometry (PSP) images per view to pretrain an encoder in a multi-view, multi-object setting. We introduce a tailored augmentation strategy for PSP-based SSS data, and show that it significantly outperforms standard ImageNet-style augmentations for SSL pretraining. The pretrained encoder learns generalizable SSS representations that transfer effectively to downstream tasks, including spatially varying relighting and representation evaluation using a kNN classifier. Combined with a decoder, the model reconstructs dense scattering footprint responses, trained using a dedicated cost function that improves accuracy, particularly for anisotropic footprints. Despite using only eight input images per view, our approach generalizes to unseen objects with complex geometry and material properties, achieving high-fidelity reconstructions while requiring orders of magnitude fewer images than prior methods.

---

### Interpretable Inverse Design of Metal-Organic Frameworks with Large Language Model Agents

Authors: Kyungmin Nam, Seunghee Han, Jihan Kim
Published: 2026-06-28
Categories: cs.LG, cond-mat.mtrl-sci, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2606.29459v2

Inverse design of metal-organic frameworks (MOFs) requires navigating combinatorial spaces with costly property labels and opaque machine-learning models. We introduce LLM4MOF, a closed-loop multi-agent framework that converts a natural-language target into chemical hypotheses, constraints, diagnostic tests, and feedback. One agent proposes interpretable hypotheses over metal nodes, linkers, pore geometry, and functionality. Another converts them into constraints selecting MOFs defined by a node, linker, and topology. The Matchmaker forms four beams to attribute gains to geometry, chemistry, or metal choice: full hypothesis, chemistry, metal only, and random baseline. Blind to database landscapes, LLM4MOF enriches top performers across six adsorption, separation, and electronic-structure tasks within 400 evaluations. It also designs and live-simulates de novo MOFs spanning H2 storage, SF6 capture, and C2H6/C2H4 separation, deriving a distinct design rule for each objective. Under an identical nominal evaluation budget it consistently outperforms random search, Bayesian optimization, and genetic algorithms, and the outcome is insensitive to the language-model backend. All of this uses not a single property-labeled training structure, whereas generative alternatives train on thousands to hundreds of thousands. A new objective requires only a natural-language request: interpretable inverse design at a fraction of the data cost of existing approaches.

---

### Interpretable Inverse Design of Metal-Organic Frameworks with Large Language Model Agents

Authors: Kyungmin Nam, Seunghee Han, Jihan Kim
Published: 2026-06-28
Categories: cs.LG, cond-mat.mtrl-sci, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2606.29459v1

Inverse design of metal-organic frameworks (MOFs) requires searching a combinatorially vast space where property labels are expensive and most machine-learning models reveal little about why a structure succeeds. We introduce LLM4MOF, a closed-loop framework in which language-model agents reason about chemistry, build candidate MOFs, and test them in simulation, refining hypotheses over ten autonomous iterations. One agent proposes interpretable design hypotheses over metal nodes, linkers, pore geometry, and functional chemistry, and a second translates them into constraints that select candidate MOFs, each made of a metal node, organic linker, and matching topology. Each hypothesis is tested through four diagnostic beams that apply different subsets of its constraints, so comparing them shows whether geometry, chemistry, or metal choice drives performance. Even when blind to the global property landscape of databases, LLM4MOF concentrates its search on top-performing structures across six adsorption, separation, and electronic-structure tasks within 400 property evaluations. The same loop also generates new MOFs de novo and validates them in live simulation, where it adapts the geometry to each requested condition, outperforming random search and a genetic algorithm at roughly $1 per campaign. LLM4MOF shows that language-model agents can run interpretable, simulation-grounded inverse design without training a model per objective.

---

### How Much Due Diligence Before You Bid? Learning in Intractable Takeover Auctions

Authors: Zain Naboulsi
Published: 2026-06-28
Categories: cs.AI, cs.GT, cs.LG
arXiv: https://arxiv.org/abs/2606.29457v1

When two companies bid to buy the same target, no one knows exactly what the target is worth. Each bidder pays for due diligence: costly, imperfect homework that sharpens its own private estimate before it bids. How much of that homework is worth buying? We build a simple computer model of the bidding contest and let it teach itself to bid well by playing against itself, the way a game engine learns chess. The economic question, how much diligence pays for itself, and the computational question, when the contest becomes too complex to solve exactly, are both controlled by a single thing: how many pieces of private information a bidder carries. Our main finding is that the right amount of diligence is modest and finite. It falls as diligence gets more expensive, and it falls further when both sides are doing their homework, because competition erodes the value of knowing more. We also test a recent claim from AI research: that simple, general self-play methods can rival the specialized, expensive algorithms usually built for games like these. Running on an ordinary laptop with no costly frontier AI, we find the simple methods are the best of the self-learning approaches, though purpose-built exact methods still win whenever the game is small enough to solve outright. The simple methods earn their keep only once the game grows too large to solve exactly, which is the regime real deals live in, and there we show they still find strong bidding strategies. The contribution is threefold: a cheap, reproducible way to study deal-making under uncertainty; a concrete, model-based answer to how much due diligence is worth buying; and evidence about when lightweight, general-purpose AI is good enough to replace specialized methods. We release all the games, code, and experiments.

---

### Resonant Brane Splatting for Arbitrary-Scale Super-Resolution

Authors: Giulio Federico, Giuseppe Amato, Claudio Gennaro, Fabio Carrara, Marco Di Benedetto
Published: 2026-06-28
Categories: cs.CV, cs.AI, cs.GR
arXiv: https://arxiv.org/abs/2606.29453v3

Arbitrary-Scale Super-Resolution (ASR) reconstructs images at continuous magnification factors. Recent methods accelerate inference by replacing computationally heavy implicit neural decoders with explicit 2D Gaussian Splatting (GS). However, since standard Gaussians are smooth low-pass primitives, modeling edges and fine textures requires multiple overlapping, well-aligned splats, which creates severe bottlenecks during rasterization. To address this, we introduce Resonant Brane Splatting (RBS), a feed-forward ASR framework. RBS replaces flat Gaussians with Branes: expressive primitives that emit spatially varying colors to natively model local contrast and complex textures within a single footprint. We achieve this by augmenting the standard Gaussian envelope with internal Gaussian-Hermite modes, assigning a distinct color coefficient to each. The zero-order mode recovers standard GS, while higher-order modes capture high frequencies. We predict Brane parameters directly from low-resolution features. Because Branes provide a mathematically richer formulation than simple Gaussians, far fewer primitives need to overlap to reconstruct a given target pixel. To exploit this, we introduce an efficient fully differentiable rasterizer with a precise culling strategy based on the classical quantum turning point. This allows us to safely skip negligible regions, drastically reducing the rendering overhead. Experiments on standard ASR benchmarks show that RBS improves reconstruction quality over implicit and GS baselines, while achieving superior speed-quality trade-off than prior GS methods.

---

### Resonant Brane Splatting for Arbitrary-Scale Super-Resolution

Authors: Giulio Federico, Giuseppe Amato, Claudio Gennaro, Fabio Carrara, Marco Di Benedetto
Published: 2026-06-28
Categories: cs.CV, cs.AI, cs.GR
arXiv: https://arxiv.org/abs/2606.29453v2

Arbitrary-Scale Super-Resolution (ASR) reconstructs images at continuous magnification factors. Recent methods accelerate inference by replacing computationally heavy implicit neural decoders with explicit 2D Gaussian Splatting (GS). However, since standard Gaussians are smooth low-pass primitives, modeling edges and fine textures requires multiple overlapping, well-aligned splats, which creates severe bottlenecks during rasterization. To address this, we introduce Resonant Brane Splatting (RBS), a feed-forward ASR framework. RBS replaces flat Gaussians with Branes: expressive primitives that emit spatially varying colors to natively model local contrast and complex textures within a single footprint. We achieve this by augmenting the standard Gaussian envelope with internal Gaussian-Hermite modes, assigning a distinct color coefficient to each. The zero-order mode recovers standard GS, while higher-order modes capture high frequencies. We predict Brane parameters directly from low-resolution features. Because Branes provide a mathematically richer formulation than simple Gaussians, far fewer primitives need to overlap to reconstruct a given target pixel. To exploit this, we introduce an efficient fully differentiable rasterizer with a precise culling strategy based on the classical quantum turning point. This allows us to safely skip negligible regions, drastically reducing the rendering overhead. Experiments on standard ASR benchmarks show that RBS improves reconstruction quality over implicit and GS baselines, while achieving superior speed-quality trade-off than prior GS methods.

---

### The Platonic Defense: Backdoor Defense for Self-Supervised Encoders in the Era of Large Scale Pre-training

Authors: Tuo Chen, Minjing Dong, Benlei Cui, Jian Liu, Jie Gui
Published: 2026-06-28
Categories: cs.CV, cs.CR
arXiv: https://arxiv.org/abs/2606.29451v1

Self-supervised learning (SSL) pretrained models have become a dominant paradigm for visual representation learning, but they are vulnerable to backdoor attacks. Existing defenses struggle to defend against such attacks in a fully black-box setting because they often require access to labels, attack patterns, or training data. To tackle this issue, we propose a new attack-agnostic, model-agnostic, and modality-agnostic black-box test-time defense paradigm, called \emph{Platonic Representation Defense}. It is inspired by the Platonic Representation Hypothesis, which suggests that large-scale independently trained encoders converge toward compatible projections of the same underlying reality. We formalize this idea as a conditional energy function defined over source representations and a set of reference representations. The energy function is trained for detection through noise-contrastive estimation and for representation purification through denoising score matching. Theoretically, the energy gap between matched and mismatched samples is lower bounded by the mutual information between source and reference representations. We demonstrate the effectiveness of our method on multiple self-supervised encoders and more than 10 attacks. The method can perform both representation detection and purification, and achieves substantial performance gains across multiple attacks. Code is available \href{https://github.com/jsrdcht/Platonic-Representation-Defense}{here}.

---

### Miti360: A Comprehensive Dataset for Improved Reforestation Monitoring

Authors: Cedric Kiplimo, Samuel Mbatia, Ciira wa Maina, Arthur Sichangi, Dennis Gitundu
Published: 2026-06-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.29447v1

Over the past decade, interest in applying machine learning (ML) to automate forest monitoring has grown significantly. However, existing training datasets are predominantly drawn from North America, Europe, Asia, and Australia, leaving a critical gap in African forestry data. To address this limited geographic diversity, we present Miti360, a comprehensive dataset for reforestation monitoring that comprises high-resolution imagery, ground truth data, and longitudinal weather data. Data collection occurred within a 770-ha reforested section of the Kieni Forest in Kenya between March 2023 and February 2025. Miti360 comprises aerial photos (orthophotos and tiles) with tree bounding box annotations, terrestrial images (single and stereo), and detailed data records including tree biophysical parameters, species, and GPS coordinates, alongside historical weather data. Aerial surveys utilized a DJI Mavic 2 Pro, with imagery stitched via Agisoft Metashape and tiled using ArcGIS Pro, while terrestrial captures used smartphones and custom stereo cameras. Miti360 enables the training of ML systems for tasks such as accelerating tree censuses, matching species to geographical areas, modelling growth based on weather conditions, and developing digital twin frameworks. Models can be trained on Miti360 to address challenges specific to Sub-Saharan Africa, ultimately advancing reforestation monitoring and fostering sustainable forestry practices in underrepresented regions. We demonstrate the utility of this dataset by successfully tracking tree crowns across three years and improving the DeepForest model's box precision and box recall by 12% and 69% respectively through fine-tuning on Miti360.

---

### Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction

Authors: Sunqi Fan, Qingle Liu, Runqi Yin, Meng-Hao Guo, Shuojin Yang
Published: 2026-06-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2606.29445v1

Video understanding is a fundamental capability for multimodal intelligence, and recent Multimodal Large Language Models (MLLMs) have achieved remarkable performance on Video Question Answering (VideoQA) benchmarks. However, existing benchmarks primarily evaluate whether models can perceive shallow visual cues, while rarely examining whether MLLMs can learn deeper knowledge or procedural skills from video tutorials and generalize them to downstream long-horizon agentic tasks. To address this gap, we introduce VG-GUIBench (Video-Guided GUI Benchmark), a new benchmark designed to evaluate whether MLLM-based GUI agents can follow video tutorials to complete corresponding GUI interactive tasks. Furthermore, we observe that the performance of models on both VideoQA and video-guided agentic tasks critically depends on effective keyframe extraction. Based on this observation, we propose TASKER (Task-driven And Scene-aware Keyframe searchER), a keyframe extraction algorithm that jointly considers task relevance and scene dynamics to identify informative frames. Experimental results demonstrate that TASKER achieves significant performance improvements on both VideoQA and video-guided agentic task benchmarks, outperforming the best baseline by 2.0% on the EgoSchema fullset and 1.8% on the NExT-QA dataset, respectively. These results further highlight the potential of generalized keyframe extraction methods for video understanding tasks. Our code and data are available at https://github.com/VG-GUI-TASKER/VG-GUI-TASKER.

---

### Closing the Activation-Cone Blind Spot: Response-Time Probing and Unified Defense

Authors: Subhadip Mitra
Published: 2026-06-28
Categories: cs.CR, cs.AI, cs.CL, cs.ET, cs.LG
arXiv: https://arxiv.org/abs/2606.29441v1

Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists. We evaluate five defense paradigms (no defense, static steering, CAST, AlphaSteer, probe-gated) across seven instruction-tuned models (7-31B) and five attack types (GCG, AutoDAN, DeepInception, prefilling, intent laundering). Our central finding: prompt-time activation defenses are structurally blind to prefilling attacks. AlphaSteer achieves 0% attack success on GCG, AutoDAN, and intent laundering but 50% on prefilling. We prove a corollary: any defense that gates intervention on a single layer's activation alignment with a benign reference (cone, subspace, or null-space) is blind to attacks that craft activations to lie inside that reference, whether checked at prompt time or per token. As its constructive contrapositive we introduce response-time probing: a linear probe on the model's hidden state at the first generated tokens, with AUROC 0.97-1.00 across all seven models. Combined with a halt, it cuts prefilling attack success to 0/40 on every model with 0% benign false positives, outperforming Llama Guard 3. Cross-template generalisation depends on probe depth, so we scope the claim to the canonical prefilling-template family. Composing the response-halt with AlphaSteer's null-space steering gives an orthogonal split (the halt catches prefilling, AlphaSteer catches semantic attacks), reaching defense success 0.983 on Mistral and 0.994 on Llama and dominating both components. We further show MMLU fails to capture steering's true utility cost, which appears as behavioral hedging rather than factual loss, and that diverse negative training sets cut probe false positives from 80-100% to near zero. Code, attacks, per-sample results, and the judge prompt are released.

---

### Randomized neural operator for parametric PDEs with fast training and conformal uncertainty quantification

Authors: Zirui Deng, Jingbo Sun, Deyu Meng, Fei Wang
Published: 2026-06-28
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2606.29440v1

Repeatedly solving parametric PDEs is essential for uncertainty quantification, design optimization and inverse problems, but conventional neural operators require expensive non-convex training. We introduce PCA--RaNN, a randomized latent neural operator that combines PCA-based dimensionality reduction with fixed random features and a closed-form least-squares readout. It recasts latent operator learning as fixed-feature linear regression, reducing training time by one to three orders of magnitude across benchmarks while maintaining competitive accuracy. We introduce an energy-matched scaling rule and a lightweight two-parameter BFGS refinement to correct suboptimal feature scales. Ensemble averaging reduces predictive variance. On Burgers, Darcy, Navier--Stokes and backward heat equation benchmarks, PCA--RaNN provides a favorable speed--accuracy trade-off against operator-learning baselines. The ensemble supports split-conformal prediction intervals, and the linear readout enables rapid online adaptation via recursive least squares without retraining hidden features. This provides an efficient, uncertainty-aware surrogate for many-query scientific workflows.

---

### Fractional Stochastic Neural Networks

Authors: Yuecai Han, Jianming Xu
Published: 2026-06-28
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2606.29438v1

In this paper, we develop a fractional stochastic neural network with residual dynamics driven by fractional Brownian motion. By introducing a discrete stochastic maximum principle for the network, we construct the corresponding adjoint recursion. For deterministic network parameters, we prove mean square convergence of projected samplewise stochastic gradient descent. Numerical experiments include a closed form convergence test, noisy regression with uncertainty quantification, long memory time series generation and image classification under structured perturbations. The results identify settings in which fractional drivers improve long memory recovery or robustness relative to Brownian and deterministic baselines.

---

### LLMography: Transforming Human-AI Conversations into Traceability, Oversight, and Auditability Indicators

Authors: Mohammed Bousmah
Published: 2026-06-28
Categories: cs.HC, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2606.29437v1

The growing use of Large Language Models (LLMs) in education, software engineering, academic writing, and technical documentation raises a key question: how can we evaluate not only AI-assisted outputs, but also the interaction process that produced them? Current debates often focus on detecting whether a final artifact was generated by AI, while overlooking the conversation history that reveals human direction, AI contribution, corrections, validation, and traceability. This paper introduces LLMography, a framework for transforming Human-AI conversations into measurable indicators of provenance, human contribution, AI dependency, reproducibility, and auditability. By analogy with bibliography and webography, LLMography documents the dynamic trajectory of interaction between a human and a Large Language Model as a structured trace of Human-AI co-production. We present a prototype that analyzes Human-AI conversation traces and generates KPI reports including Prompt Quality Score, Human Direction Score, AI Dependency Level, Auditability Score, Final Output Traceability, Privacy Risk Level, and a recommended LLMography label. A preliminary exploratory evaluation was conducted on 19 anonymized audit reports from engineering students. Most interactions were classified as Human-AI co-produced, with average scores of 86.8/100 for Human Direction, 81.9/100 for Prompt Quality, 72.8/100 for Auditability, and 77.1/100 for Final Output Traceability. The paper also applies LLMography to its own writing process, classified as human-originated, human-directed, AI-assisted co-production. The findings suggest that AI transparency should move beyond output detection toward documenting the history of interaction.

---

### Fourier Neural Operators with Least-Squares Readout Refit for Learning Random Obstacle-to-Solution Maps

Authors: Chenhui Zhu, Fei Wang
Published: 2026-06-28
Categories: math.NA, cs.LG
arXiv: https://arxiv.org/abs/2606.29436v1

We study operator learning for random obstacle-to-solution maps arising from elliptic variational inequalities with finite-band self-affine random obstacle fields. Instead of introducing an explicit truncated stochastic parametrization of the random input, we learn the map directly from sampled obstacle realizations on a fixed grid. This problem is challenging because the solution is governed not only by the obstacle field itself, but also by the induced contact set and free-boundary geometry. We introduce a post-training least-squares readout refit for the Fourier neural operator (FNO). After the FNO is trained end to end, its nonlinear backbone is frozen and the final affine readout is recomputed by solving the induced linear least-squares problem over all training samples and grid points. The refit yields the empirical squared-error optimal readout for the learned frozen features while leaving the nonlinear representation unchanged. We compare vanilla DeepONet, POD-DeepONet, a two-stage DeepONet baseline, FNO, and FNO with least-squares readout refit (FNO-LS) on two obstacle ensembles with different amplitude levels. Numerical results show that FNO-LS achieves the strongest overall performance among the tested models, particularly for higher-amplitude obstacles with more complex contact geometry. The method improves average field accuracy, contact-set recovery, and obstacle-violation metrics at low additional cost, especially when the FNO backbone is informative but not fully converged. These results suggest that least-squares readout refit is a simple and effective post-training enhancement for learning random obstacle-to-solution maps.

---

### FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Models

Authors: Yichen Guo, Kai Tang, Jinhao You, Fenglai Lin, Yiding Sun, Dongxu Zhang, Wenya Wang, Lin William Cong, Shanghang Zhang
Published: 2026-06-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.29431v5

Despite the impressive capabilities of Large Vision-Language Models (LVLMs), they remain susceptible to hallucination, generating content inconsistent with the input image. Recent studies attribute this to the dominance of language priors over visual inputs and employ contrastive decoding methods to mitigate this dominance, but the mechanistic origin remains unexplored. We investigate the information flow through each transformer layer and find that attention modules consistently aggregate visual evidence, while FFN modules at critical layers act as the source of language priors. These priors can override visual evidence, causing correct predictions in intermediate layers to drift toward incorrect outputs. Based on this insight, we propose FADE (FFN Attenuation for DEcoding), a training-free method that attenuates FFN outputs to reduce language-prior dominance. Evaluations on POPE, CHAIR, and MME benchmarks across LLaVA-1.5, mPLUG-Owl2, and InstructBLIP show that FADE effectively mitigates hallucinations while preserving inference efficiency.

---

### FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Models

Authors: Yichen Guo, Kai Tang, Fenglai Lin, Yiding Sun, Dongxu Zhang, Wenya Wang, Lin William Cong, Shanghang Zhang
Published: 2026-06-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.29431v4

Despite the impressive capabilities of Large Vision-Language Models (LVLMs), they remain susceptible to hallucination, generating content inconsistent with the input image. Recent studies attribute this to the dominance of language priors over visual inputs and employ contrastive decoding methods to mitigate this dominance, but the mechanistic origin remains unexplored. We investigate the information flow through each transformer layer and find that attention modules consistently aggregate visual evidence, while FFN modules at critical layers act as the source of language priors. These priors can override visual evidence, causing correct predictions in intermediate layers to drift toward incorrect outputs. Based on this insight, we propose FADE (FFN Attenuation for DEcoding), a training-free method that attenuates FFN outputs to reduce language-prior dominance. Evaluations on POPE, CHAIR, and MME benchmarks across LLaVA-1.5, mPLUG-Owl2, and InstructBLIP show that FADE effectively mitigates hallucinations while preserving inference efficiency.

---

### EvLIR: Learning Illumination Residuals from Ordered Events for Low-Light Image Enhancement

Authors: Haoxian Zhou, Chuanzhi Xu, Langyi Chen, Pengfei Ye, Haodong Chen, Qiang Qu, Ali Anaissi, Weidong Cai
Published: 2026-06-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.29430v1

Low-light image enhancement is severely ill-posed when the input frame contains missing structure, saturated noise, and weak local contrast. Event cameras provide asynchronous brightness-change observations with high temporal resolution, but prior works often treat voxel channels as an unordered or static feature stack before fusion, rather than explicitly modeling their within-window temporal evolution, weakening the temporal evidence that makes events useful. We propose EvLIR, a temporal-residual enhancement framework that learns illumination residuals from ordered events for low-light image enhancement. Given a low-light frame and its aligned event voxel, EvLIR preserves the ordered temporal bins of the event stream and introduces a Temporal Event Residual Module (TERM) to encode short-window event dynamics with a lightweight ConvGRU. The resulting temporal state is converted into a bounded illumination correction, which provides spatially adaptive photometric guidance for Retinex-style illumination estimation and subsequent reliability-aware image-event restoration. On SDE and SDSD indoor/outdoor benchmarks, EvLIR achieves the best result on eleven of twelve dataset-metric pairs, with average scores of 25.63~dB PSNR, 28.30~dB PSNR*, and 0.827 SSIM across the four benchmarks.

---

### Robust Zero-shot Anomaly Detection under Limited Auxiliary Anomaly Priors

Authors: Guanyu Lu, Fang Zhou, Cheqing Jin
Published: 2026-06-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2606.29428v1

Zero-shot anomaly detection aims to identify defects in arbitrary novel domains; however, existing models assume that the auxiliary data contains a rich diversity of anomalies, neglecting the far more complex and unpredictable variations in real-world target domains. This study introduces DIVE, the first approach to investigate the scenario of limited auxiliary anomaly priors and resolve the resulting substantial performance degradation. Through a shallow-and-deep text embedding injection strategy during visual encoding, DIVE learns to abstract generic anomaly concepts shared across the auxiliary training domain and diverse target domains. Moreover, we propose a disentanglement mechanism to tackle the suboptimal alignment between visual embeddings entangled with object semantics and object-agnostic textual prompts. Experiments demonstrate that, under the setting of limited anomaly patterns in auxiliary data, DIVE outperforms SOTA baselines by up to 16.2% and 28.5% on two classification metrics, and 23.4%, 24.1%, and 47.0% on three segmentation metrics, in terms of average performance across twelve datasets. Furthermore, it maintains highly competitive performance when auxiliary data exhibits sufficient anomaly diversity.

---

### Mixture of Debaters: Learn to Debate at Architectural Level in Multi-Agent Reasoning

Authors: Dayong Liang, Kaisong Gong, Yi Cai, Changmeng Zheng, Xiao-Yong Wei
Published: 2026-06-28
Categories: cs.AI, cs.CL, cs.MA, cs.MM
arXiv: https://arxiv.org/abs/2606.29425v1

Existing multi-agent debate frameworks suffer from two critical limitations: they rely on static architectures where agent roles and coordination patterns are fixed at design time, and they require instantiating multiple model copies, incurring substantial computational overhead. We propose Mixture of Debaters (MoD), a unified framework that enables dynamic self-debate within a single model by leveraging the Mixture-of-Experts paradigm. We address three key challenges in adapting MoE for dialectical reasoning: (1) dual-routing that decouples role allocation from process flow, dynamically determining when to debate versus when to synthesize; (2) momentum switching that smooths token-level routing with local context, reducing expert-switch jitter; and (3) unified self-debate that encapsulates diverse debating personas into lightweight expert modules, eliminating inter-agent communication while preserving behavioral diversity. Extensive experiments on multimodal benchmarks demonstrate that MoD outperforms both single-model baselines and conventional multi-agent systems, achieving superior accuracy with 3.7x lower latency and 87% reduction in token consumption.The source code can be accessed at https://github.com/YongLD/MoD.

---

### EntroRouter: Learning Efficient Model Routing via Entropy Regulation

Authors: Kaiyi Zhang, Xueliang Zhao, Zhuocheng Gong, Wei Wu, Yankai Lin
Published: 2026-06-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2606.29424v1

Model routing balances solution accuracy and computational cost by selecting among models of varying capabilities. While recent multi-round frameworks interleave reasoning and planning, we identify a structural failure mode termed Trust Region Collapse. We demonstrate that the deep coupling of reasoning and routing, exacerbated by the dominance of strong pre-training priors under sparse supervision, leads to degenerate local optima where capable experts are systematically suppressed. To decouple these processes, we propose $\textbf{EntroRouter}$, a single-round routing framework that treats entropy regulation as a core objective. We first initialize the policy via Soft Supervision, fitting a distribution of suitable models to establish a high-entropy prior for exploration. Subsequently, we stabilize Reinforcement Learning using a Soft Anchor, which utilizes offline capability estimates to orchestrate controlled entropy contraction within a safe trust region. Extensive experiments demonstrate that EntroRouter retains 98.3% of the strongest expert's accuracy while reducing computational costs by 48.25%.

---

### Temporal Posed and Spontaneous Gesture Recognition from Electromyography in the Rock-Paper-Scissors Game

Authors: Xin Wei, Huakun Liu, Felix Dollack, Monica Perusquia-Hernandez
Published: 2026-06-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2606.29423v1

The importance of gesture recognition has been acknowledged in many domains requiring real-time recognition systems. Two requirements for these are fast recognition in multiuser contexts. Therefore, we explored the temporal characteristics of electromyography (EMG) and its accuracy in recognizing gestures in a Rock-Paper-Scissors (RPS) game. Twenty-four participants played RPS in dyads, while a two-channel EMG was recorded from the forearm. We found out that EMG onsets could be detected at least 800 ms before the gesture's visible onset, and that the EMG peaks around 342 ms before the visible onset of the gesture. Furthermore, we evaluated self-gesture recognition in both posed and spontaneous gesture conditions. The mean accuracy for posed gestures reached 63.4%. The model trained on posed gestures achieved 53.6% for spontaneous gestures, with considerable variation across individuals. We also checked whether detecting a player's gesture from the opponent's EMG was possible. The peak mean accuracy was 65%, peaking at 2082 ms after the visual onset of the gesture. This suggests that the opponent's reaction to an observed gesture contains information about the observed gesture due to the dynamics of the interactions while playing. The temporal predictive advantage of EMG signals, where muscle activation precedes observable movement, offers potential benefits for applications requiring rapid intent recognition, such as human-computer interaction and assistive technologies. Future work should focus on refining onset detection and reducing the impact of spontaneous movement variability across conditions to improve recognition performance in dynamic and real-world environments.

---

### Bit-ViP: Leveraging Bit-planes to Preserve Visual Privacy in Images through Obfuscation

Authors: Vishesh Kumar Tanwar, Ashish Gupta, Sanjay Madria, Sajal K. Das
Published: 2026-06-28
Categories: cs.CV, cs.CR, cs.ET
arXiv: https://arxiv.org/abs/2606.29417v1

The unprecedented growth of computer vision applications, such as surveillance systems and social media, raises security and visual privacy concerns, especially when data is stored on cloud servers. Image obfuscation offers a way to preserve visual privacy while maintaining an adequate level of usability; thus, it has been a topic of great interest in recent years. However, prior obfuscation schemes are either vulnerable to malicious attacks, such as model inversion to reconstruct original images from obfuscated images, or generate non-trainable obfuscated images, making them unusable for achieving reasonable accuracy. This paper proposes a novel bit-plane-based image obfuscation scheme, {\em Bit-ViP}, to preserve visual privacy for image-based recognition tasks. The Bit-ViP scheme produces secure, usable images by incorporating an innovative end-to-end obfuscation function. While doing so, the obfuscated image would contain non-invertible noise (generated by Lorenz's chaotic system and differential privacy), making it hard for an adversary to reconstruct the original image. We conduct extensive experiments on two popular activity recognition datasets, namely UCF101 and HMDB51, to validate the effectiveness of Bit-ViP. In the face of attacks on reconstruction, pixel frequency, information entropy, and pixel inter-correlation, we present a rigorous security analysis demonstrating tangible improvements over existing schemes.

---