中 EN
Sign In Register

Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

Sign In Register
01.
medRxiv (Medicine) 2026-06-15

ICD-10 Code Ambiguity Obscures Treatment-Eligible Adults with Spinal Muscular Atrophy: A Single-Center Chart Review and Patient Outreach Study

Authors:
Holly↗Bean↗Beshay↗Edwards↗Streicher↗N. S↗

Background. Three disease-modifying therapies (DMTs) for spinal muscular atrophy (SMA) have been approved since 2016, yet many adults remain untreated. Identifying them depends on ICD-10 codes that capture SMA but do not reliably distinguish it from other related conditions. We examined, in one U.S. health system, both patients' engagement with therapy and the accuracy of the codes used to find them. Methods. We conducted a retrospective chart review of adults in an academic health system identified by SMA-associated ICD-10 codes, with manual adjudication of diagnosis and DMT status. Confirmed SMA-positive, DMT-naive patients were invited to a structured telephone interview on treatment awareness and barriers. Results. Of 60 charts, 22 (36.7%; 95% CI 25.6-49.3%) were appropriately coded for SMA or a related disorder; only 16 (26.7%) had molecularly confirmed SMA. The other 38 (63.3%) were miscoded, spanning spinal and bulbar muscular atrophy, asymptomatic carriers, prenatal screening, and conditions unrelated to SMA. Ten of the 16 confirmed patients (62.5%) were DMT-naive; one was interviewed, one declined, and eight could not be reached. The non-response is itself a finding: the patients least visible to administrative data are the hardest to reach. Conclusions. ICD-10 ambiguity is a barrier to treatment access in adult SMA, as is loss to follow-up. We make two recommendations: continuous documentation-coding alignment that uses natural language processing to verify the genetic precondition, and type-specific SMA codes (subcodes for Types 0-4) anchored on molecular SMN1 confirmation. Together these would support cohort identification, outreach, and evidence generation without adding to clinician burden.

Read & Discuss → View Source →
02.
arXiv (CS.CV) 2026-06-12

PaLMR: Towards Faithful Visual Reasoning via Multimodal Process Alignment

Authors:
Yantao Li↗Qiang Hui↗Chenyang Yan↗Kanzhi Cheng↗Fang Zhao↗Chao Tan↗Huanling Gao↗Jianbing Zhang↗Kai Wang↗Xinyu Dai↗Shiguo Lian↗

Reinforcement learning has recently improved the reasoning ability of Large Language Models and Multimodal LLMs, yet prevailing reward designs emphasise final-answer correctness and consequently tolerate process hallucinations–cases where models reach the right answer while misperceiving visual evidence. We address this process-level misalignment with PaLMR, a framework that aligns not only outcomes but also the reasoning process itself. PaLMR comprises two complementary components: a perception-aligned data layer that constructs process-aware reasoning data with structured pseudo-ground-truths and verifiable visual facts, and a process-aligned optimisation layer that constructs a hierarchical reward fusion scheme with a process-aware scoring function to encourage visually faithful chains-of-thought and improve training stability. Experiments on Qwen2.5-VL-7B show that our approach substantially reduces reasoning hallucinations and improves visual reasoning fidelity, achieving state-of-the-art results on HallusionBench while maintaining strong performance on MMMU, MathVista, and MathVerse. These findings indicate that PaLMR offers a principled and practical route to process-aligned multimodal reasoning, advancing the reliability and interpretability of MLLMs.

Read & Discuss → View Source →
03.
arXiv (CS.CL) 2026-06-11

Redesign Mixture-of-Experts Routers with Manifold Power Iteration

Authors:
Songhao Wu↗Ang Lv↗Ruobing Xie↗Yankai Lin↗

Router is the cornerstone component to the Mixture-of-Experts models. Serving as expert proxies, the rows of the router matrix compute their similarity to the MoE inputs to determine which subset of experts is activated. Ideally, each router row is designed to encode the expert matrix into this representative vector, such that its dot-product with token can better reflect token-expert affinity. However, there exists no design principles to enforce this condensation. In this paper, we propose to align each router row with the principal singular direction of the associated expert, as this direction provides the most expressive mathematical description of a matrix. Based on this principle, we propose a router redesign with Manifold Power Iteration (MPI). Specifically, it introduces a "Power-then-Retract" paradigm, where a power iteration step is performed on the router weights, followed by a retraction to impose a norm constraint to ensure both efficiency and stability. Theoretically, we show that MPI drives router rows to converge toward the principal singular directions of associated experts. Empirically, we pretrain MoE model across scales from 1B to 11B parameters to confirm that this alignment facilitates more effective MoE models.

Read & Discuss → View Source →
04.
arXiv (CS.LG) 2026-06-16

Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion Guidance

Authors:
Bohdan Turbal↗Blossom Metevier↗Max Springer↗Aleksandra Korolova↗

arXiv:2606.15531v1 Announce Type: new Abstract: Fine-tuning aligned language models on benign tasks (e.g. math tutoring) systematically breaks safety guardrails, even when training data contains no harmful content. While mechanistic approaches have shed light on where alignment resides in model weights, they do not by provide a general formal framework for deriving guarantees about when fine-tuning degrades it – leaving the field without principled tools for predicting or preventing alignment collapse. We develop a local geometric framework through geometric analysis of parameter-space trajectories and apply it to understand the fragility of alignment in fine-tuning. While first-order analysis suggests orthogonal updates are safe, we prove this is illusory: the curvature of the fine-tuning loss induces second-order acceleration that can induce second-order drift into alignment-sensitive regions. We formalize a construct of our framework as the Alignment Instability Condition (AIC), three geometric properties that, when present, are sufficient to guarantee degradation. Our main result proves quartic onset of alignment degradation along gradient-flow trajectories, determined by how sharply alignment depends on specific parameters and how strongly tasks couple to these parameters. These findings yield formal sufficient conditions under which static first-order protection can fail under gradient descent. We further empirically validate the framework's foundations, showing that the Fisher Information Matrix provides a proxy for the degree of safety degradation across diverse fine-tuning.

Read & Discuss → View Source →
05.
arXiv (CS.CL) 2026-06-11

On the Optimal Reasoning Length for RL-Trained Language Models

Authors:
Daisuke Nohara↗Taishi Nakamura↗Rio Yokota↗

Reinforcement learning substantially improves reasoning in large language models, but it also tends to lengthen chain-of-thought outputs and increase computational cost. Although length-control methods have been proposed, the length-accuracy relationship they induce remains unclear. We train policies with several length-control methods on multiple base models in a controlled setup and find that, across both mathematical reasoning and code generation, accuracy is non-monotonic in output length, peaking at an intermediate value. Mode accuracy, however, continues to improve with length even in settings where sample accuracy plateaus or declines, indicating that the non-monotonic length-accuracy relationship is driven by dispersion around an increasingly correct center.

Read & Discuss → View Source →
06.
PLOS Computational Biology 2026-06-04

CIPHER: An end-to-end framework for designing optimized aggregated spatial transcriptomics experiments

Authors:
Zachary Hemminger↗

by Zachary Hemminger, Haley De Ocampo, Fangming Xie, Zhiqian Zhai, Jingyi Jessica Li, Roy Wollman Motivation Most imaging-based spatial transcriptomics methods measure individual genes, which limits scalability and typically requires integration with scRNA-seq to recover full cellular states. Recent approaches such as CISI, FISHnCHIPs, and ATLAS address this limitation by measuring aggregate transcriptional signatures, where multiple genes are pooled into each channel to increase throughput. While aggregate measurements improve scalability, they shift the problem from gene selection to feature design. For effective integration with scRNA-seq, these signatures must be not only discriminative in transcriptional space but also straightforward to measure, with balanced signal, sufficient dynamic range, and robustness to experimental noise. By optimizing decoding accuracy in isolation, existing methods leave substantial performance on the table. Results We present CIPHER (Cell Identity Projection using Hybridization Encoding Rules), a neural-network framework that jointly optimizes the experimental encoding matrix, i.e., the way that genes are aggregated to signatures, and the downstream cell embedding. CIPHER integrates the physical limits of imaging assays directly into its loss function, shaping the latent space to maximize discriminability while maintaining robustness to measurement noise and signal constraints. Using a large-scale mouse brain scRNA-seq reference, we show that CIPHER-designed encodings yield latent spaces with improved cell-type separability, uniform signal utilization, and greater resilience to hybridization variability, resulting in higher decoding accuracy from both simulated and experimental data. Conclusion CIPHER formulates aggregate signature design as a joint optimization problem over decoding accuracy and experimental measurability. This enables systematic, scRNA-seq-aligned feature design for scalable spatial transcriptomics based on aggregate measurements. Availability Code and documentation are available at https://github.com/wollmanlab/Design/.

Read & Discuss → View Source →
07.
arXiv (CS.AI) 2026-06-19

Playful Agentic Robot Learning

Authors:
Junyi Zhang↗Jiaxin Ge↗Hanjun Yoo↗Letian Fu↗Zihan Yang↗Yaowei Liu↗Raj Saravanan↗Shaofeng Yin↗Justin Yu↗Dantong Niu↗Zirui Wang↗Roei Herzig↗…

arXiv:2606.19419v1 Announce Type: cross Abstract: Current agentic robot systems can write executable Code-as-Policy programs, observe feedback, and revise behavior across multiple attempts, but they remain largely task-driven: reusable skills are acquired only after explicit instructions. We study Playful Agentic Robot Learning, where an embodied coding agent uses self-directed play as a continual skill-learning stage before downstream tasks arrive. We introduce RATs, Robotics Agent Teams designed for play-time skill acquisition. During play, RATs proposes novel yet learnable exploratory tasks, plans and executes robot-code policies, verifies intermediate progress, diagnoses failures, retries with dense, step-level feedback, and distills successful executions into a persistent code skill library. At test time, the agent reuses relevant skills from this frozen library to help solve new tasks. Experiments in LIBERO-PRO and MolmoSpaces show that play-learned skills improve held-out downstream tasks over no-play and random-play baselines, with 20.6 and 17.0 percentage-point gains over CaP-Agent0 on LIBERO-PRO and MolmoSpaces, respectively. Moreover, the learned skills can be plugged into other inference-time Code-as-Policy agents by simply retrieving them into the context, improving RoboSuite and real-world transfer by 8.9 and 8.8 points, respectively, without finetuning the underlying model.

Read & Discuss → View Source →
08.
arXiv (CS.CL) 2026-06-15

OLaPh: Optimal Language Phonemizer

Authors:
Johannes Wirth↗

Phonemization is a critical component in text-to-speech synthesis. Traditional approaches rely on deterministic transformations and lexica, while neural methods offer potential for higher generalization on out-of-vocabulary (OOV) terms. We introduce OLaPh (Optimal Language Phonemizer), a hybrid framework that integrates extensive multilingual lexica with advanced NLP techniques and a statistical subword segmentation function. Evaluations on the WikiPron benchmark show OLaPh significantly outperforms established baselines in overall accuracy and maintains robustness on OOV data through advanced fallback mechanisms. To further explore neural generalization, we utilize the framework to synthesize a high-consistency training corpus for an instruction-tuned Large Language Model (LLM). While the deterministic framework remains more accurate overall, the LLM demonstrates strong generalization, matching or partly exceeding the framework's performance. This suggests that the LLM successfully internalized phonetic intuitions from the synthetic data that transcend the framework's capabilities. Together, these tools provide a comprehensive, open-source resource for multilingual grapheme-to-phoneme conversion (G2P) research.

Read & Discuss → View Source →
09.
Nature (Science) 2026-06-11

‘Footballers are not superheroes’: we must tackle the mental and physical pressures of elite sport

Authors:
David Adam↗

As the men’s football World Cup gets under way, how the game weighs on the health of athletes still isn’t talked about enough, says player-turned-medic Vincent Gouttebarge. As the men’s football World Cup gets under way, how the game weighs on the health of athletes still isn’t talked about enough, says player-turned-medic Vincent Gouttebarge.

Read & Discuss → View Source →
10.
arXiv (CS.CV) 2026-06-11

Bridging Day and Night: Unsupervised Cross-Domain Re-Identification with Synergistic Prompt and Prototype Learning

Authors:
Jiyang Xu↗Rui Liu↗Hang Dai↗

Cross-domain day-night re-identification (ReID) is fundamentally challenged by the substantial visual appearance discrepancies between daytime and nighttime scenes. Existing fully supervised methods rely heavily on labor-intensive annotations, which are costly and exhibit limited generalization across domains. In this work, we investigate unsupervised day-night ReID and propose a novel framework that synergistically combines prompt learning and prototype-based representation learning to associate identities across domains without requiring manual labels. Our approach follows a progressive two-stage training strategy. In the first stage, we exploit the vision-language model to generate instance-specific textual prompts in an annotation-free manner. We employ an instance-level alignment mechanism to embed visual features and textual prompts into a unified semantic space, aligning unlabeled day/night images with learnable prompts via instance-aware dynamic-bias adaptation. In the second stage, we construct domain-specific prototype memory banks and introduce two complementary modules: i) an intra-domain identity association module to enhance feature discriminability within each domain, and ii) a cross-domain prototype matching module to reliably identify positive and negative prototype pairs, thereby establishing robust identity correspondences across day and night. Extensive experiments on public benchmarks validate the effectiveness of our method. Under the unsupervised setting, our framework attains Rank-1 accuracy comparable to state-of-the-art fully supervised methods.

Read & Discuss → View Source →
11.
bioRxiv (Bioinfo) 2026-06-10

HOMED enables hierarchical and multimodal optimization of DNA methylation deconvolution across tissues

Authors:
Liu↗Chen↗Du↗Garmire↗

Cellular heterogeneity is a major confounder in bulk DNA methylation data for epigenome-wide association studies. Existing reference-based DNAm deconvolution methods often ignore hierarchies among related cell types and may generalize poorly across datasets due to limited variability in reference profiles. We developed HOMED (Hierarchically Optimized Methylation Deconvolution), a framework that integrates cell-lineage hierarchies, single-cell RNA sequencing-guided deconvolution, and paired bulk RNA-seq/DNAm data for CpG signature optimization. Across simulated and real peripheral blood mononuclear cell, lung, and placental datasets, HOMED consistently yielded the highest PCCs and lowest RMSEs, outperforming existing scRNA-seq-guided DNAm deconvolution methods, improving accuracy, resolution, and cross-tissue generalizability.

Read & Discuss → View Source →
12.
arXiv (CS.AI) 2026-06-24

IPO Finance Agent: Evaluation of LLM Financial Analysts beyond Finance Agent v2, with Automated Rubric Generation – the Case of the SpaceX (SPCX) IPO

Authors:
Mostapha Benhenda↗

arXiv:2606.23032v2 Announce Type: replace Abstract: Finance Agent v2 (by Vals AI) has emerged as the reference benchmark for evaluating both Anthropic Claude and OpenAI ChatGPT frontier language models on financial tasks. However, it narrowly deals with periodic reporting from publicly traded companies (SEC 10-K and 10-Q filings), and its agentic harness relies on naive, unenriched chunk retrieval. Neither the task design nor the retrieval approach addresses the distinct challenges of IPO due diligence. SEC S-1 filings combine historical financial statements, governance structures, pro forma and common-control accounting treatments, capital-formation narratives, and underwriting-sensitive risk disclosures within substantially longer documents than typical periodic filings. That is why we introduce IPO Finance Agent, which extends the Finance Agent v2 framework along two directions: task domain and retrieval architecture. During our experiments, the original Finance Agent v2 harness basically failed to deliver any output related to the SpaceX S-1 filing, due to document length. We therefore had to improve the agentic harness with contextual retrieval, a more realistic and industry-standard approach for long documents. We also built a dataset of 1,000 IPO-diligence questions, and publicly release 70 questions on the SpaceX (SPCX) S-1 filing to support reproducibility, while the remainder are held private to guard against benchmark contamination. In addition, we introduce an evaluator-optimizer pipeline to automatically generate evaluation rubrics for the benchmark: candidate facts are extracted from model answers, consolidated into draft criteria, then automatically audited for omissions, hallucinations, mistiered items, and redundancy, with LLM feedback driving iterative repair, targeted enrichment, and deduplication. Human experts only review final rubrics before deployment. Results show that the best-performing evaluated model, Alibaba Qwen 3.7 Max, reaches 79.4% accuracy at 0.30 USD per query, and the most cost-efficient model on the resulting Pareto frontier, Xiaomi MiMo-2.5 Pro, reaches slightly lower accuracy (76.8%) at 0.05 USD per query. Both exceed the current Finance Agent v2 leaderboard ceiling-Google Gemini 3.5 Flash at 57.9% for 2.51 USD per querywhile undercutting even FABv2's cheapest entry (MiniMax M3: 48.3% at 0.32 USD) on cost-efficiency. Code and data are released on GitHub: https://github.com/benstaf/ipoagent

Read & Discuss → View Source →
13.
arXiv (CS.AI) 2026-06-16

Semantics-Enhanced Retrieval-Augmented Time Series Forecasting

Authors:
Shiqiao Zhou↗Zipeng Wu↗Holger Sch\"oner↗Edouard Fouch\'e↗IAG Wilson↗Shuo Wang↗

arXiv:2606.14941v1 Announce Type: new Abstract: Time series forecasting models often benefit from historical patterns. Inspired by Retrieval-Augmented Generation (RAG), recent research explored retrieving relevant historical time series segments to enhance forecasting. However, relying solely on time series similarity is often insufficient for retrieval under non-stationarity. To address this, we propose a multimodal approach: a Semantics-Enhanced Retrieval-Augmented Time Series Forecasting framework, SERAF. Unlike mainstream approaches that depend only on time series similarity, SERAF conducts dual retrieval over the time series and their self-generated textual descriptions. It retrieves two complementary sets of historical patterns and corresponding futures, which are selectively and jointly used to guide future predictions. Experiments across seven real-world datasets demonstrate the effectiveness of SERAF in bridging numerical and semantic views of time series compared with state-of-the-art baselines.

Read & Discuss → View Source →
14.
arXiv (CS.LG) 2026-06-16

Evolutionary Bilevel Reward Shaping for Generalization in Reinforcement Learning

Authors:
Ekasit Usaratniwart↗Xilin Gao↗Marc Ong↗Youhei Akimoto↗

arXiv:2606.16236v1 Announce Type: new Abstract: Reinforcement learning (RL) often suffers from performance degradation when deployed in environments that differ from those encountered during training. Existing techniques such as domain randomization (DR) mitigate this, but require access to diverse training environments and full trajectory observability, assumptions that fail in privacy-preserving or restricted scenarios where only scalar performance metrics are available. We propose Generalization via Evolutionary Reward Shaping (GERS), a bilevel optimization approach to improve generalization on unseen test environments using only scalar feedback from validation environments. At the lower level, an RL agent guided via a reward function shaped by the upper level learns a policy on a limited set of training environments with accessible trajectory data; at the upper level, CMA-ES optimizes the reward shaping parameters to maximize the cumulative unshaped reward on separate validation environments for which trajectory access is unavailable. Results on continuous control tasks indicate that GERS outperforms the standard RL baseline on unseen test environments. GERS performance is comparable to DR, despite DR treating the combined set of training and validation environments of GERS as a single training set that requires trajectory access, whereas GERS cannot access validation trajectories. These results confirm that GERS effectively enhances generalization under restricted data access constraints.

Read & Discuss → View Source →
15.
arXiv (CS.AI) 2026-06-24

NoContactNoWorries: Estimating Contact through Vision and Proprioception for In-Hand Dexterous Manipulation

Authors:
Soham Patil↗Avirup Das↗Sourabh Bhosale↗Spandan Roy↗

arXiv:2606.24450v1 Announce Type: cross Abstract: Perceiving physical contact is fundamental to dexterous manipulation. While robots often rely on dedicated hardware tactile sensors, humans exhibit a remarkable ability to infer contact by integrating visual information with an innate sense of their body's pose and movement. Inspired by this embodied perceptual skill, we investigate whether a robot can learn to infer contact from vision, an approach that also offers a scalable alternative to tactile hardware specifically for binary contact estimation, which faces practical challenges in cost, fragility, and integration. We present NoContactNoWorries, a transformer-based multimodal framework that fuses RGB-D vision with the robot's proprioception to infer binary contact states as a pseudo-tactile signal for hand-object interactions. We validate by training a single contact prediction model on multiple objects and show that the inferred contact signal supports downstream reinforcement learning agents for in-hand object reorientation, generalizing to novel objects. Experiments in both simulation and on a real-world robot validate our approach, highlighting the feasibility of inferring contact from vision and proprioception. Project Page: https://soham2560.github.io/no-contact-no-worries/

Read & Discuss → View Source →
16.
arXiv (CS.AI) 2026-06-24

Synergizing Physically Constrained MCMC and Chemical-Informed Gaussian Processes for Reaction Network Discovery

Authors:
Runzhe Liu↗Zihao Wang↗Wenbo Yang↗Shengyang Tao↗

arXiv:2606.23757v1 Announce Type: cross Abstract: Extracting interpretable governing equations from sparse, noisy chemical time-series data remains difficult because discrete reaction topology and continuous kinetic parameters are tightly coupled. We present PC-MCMC-CIGP, a reproducible gray-box workflow that combines spike-and-slab topology sampling, hard conservation and thermodynamic screening, and a Chemical-Informed Gaussian Process (CIGP) residual model for parameter calibration and experimental design. The methodological contribution is not a new MCMC or GP family in isolation; rather, it is the integration of these components into a physically constrained workflow with explicit uncertainty-aware acquisition choices. On the H2 + Br2 benchmark, the constrained sampler distinguishes elementary radical pathways from deceptive phenomenological fits in our experiments. On styrene epoxidation, the CIGP optimization loop improves final yield by 12.5% over the reported GP-BO baseline. A new 10-seed acquisition study shows that EI, GWU, PC-EI, uncertainty sampling, discrepancy hunting, and random search have different trade-offs: PC-EI substantially reduces low-yield BO suggestions, while EI-style criteria give the strongest final-yield performance.

Read & Discuss → View Source →
17.
arXiv (math.PR) 2026-06-16

Sharp freezing time estimates for the subcritical Facilitated Exclusion Process

Authors:
Oriane Blondel↗Cl\'ement Erignoux↗Seonwoo Kim↗Sanha Lee↗

arXiv:2606.15233v1 Announce Type: new Abstract: We investigate the exact transience time of the Facilitated Exclusion Process (FEP) on the one-dimensional torus with $N$ sites. The FEP exhibits an active/inactive phase transition at critical density $1/2$, such that in the subcritical density regime $(0,1/2)$, it becomes frozen after a finite time period – the transience time or freezing time. We first show that for the FEP starting from a Bernoulli product measure of marginal density $\rho \in (0,1/2)$, the transience time has exactly the scale of $\Theta(\log^3 N)$. Secondly, we prove that in the near-critical case $\rho \simeq 1/2 - N^{-\alpha}$ for $\alpha \in (0,1)$, the transience time is polynomial and has a scale of $N^{1 \wedge (2\alpha)}$. The key idea is to estimate the typical size of locally supercritical intervals of the initial distribution, which has order $\log N$ in the subcritical case and $N^{1 \wedge (2\alpha)}$ in the near-critical case. In the subcritical case this is enough, whereas in the near-critical case we need additional dynamical decorrelation inequalities to apply this static result to estimate the freezing time.

Read & Discuss → View Source →
18.
arXiv (CS.LG) 2026-06-24

Hybrid Sequence Modeling and Reinforced Verification for Controllable Target-Conditioned Decision Making

Authors:
Yue Pei↗Hongming Zhang↗Chao Gao↗Martin M\"uller↗Yingying Zhang↗Mengxiao Zhu↗Hao Sheng↗Ziliang Chen↗Liang Lin↗Haogang Zhu↗

arXiv:2508.16420v3 Announce Type: replace Abstract: Target-conditioned sequence models provide a simple interface for controllable offline decision making, but the requested target return can be an unreliable control signal, especially when the target return lies in underrepresented regions of the dataset. This paper proposes Doctor, a hybrid sequence modeling and reinforced verification framework for controllable target-conditioned offline decision making. Doctor trains a shared masked trajectory Transformer with two complementary objectives: masked trajectory reconstruction for candidate generation and in-sample value learning for action-value verification. At inference time, the model samples multiple nearby target returns, generates candidate actions in parallel, and selects the action whose verified value is closest to the requested target return. We analyze this verifier-guided selection rule and show that its value-level alignment error is bounded by candidate-value coverage around the target return and verifier accuracy. Experiments on D4RL and EpiCare show that Doctor improves target-return alignment under reduced high-return coverage, remains competitive on standard offline return-maximization benchmarks, and enables a single policy to modulate between conservative and aggressive operating points in a simulated clinical decision-making task. These results suggest that reinforced verification can improve the controllability of target-conditioned policies.

Read & Discuss → View Source →
19.
bioRxiv (Bioinfo) 2026-06-10

A Unified Spatial AI Framework for Cross-Domain Tissue-State Analysis in Trauma, Oral, and Cardiovascular Pathology

Authors:
Pham↗T. D↗

Objective: To develop a cross-domain spatial AI framework for identifying conserved tissue-state organisation across trauma, oral disease, and cardiovascular tissue using spatial transcriptomic data. Methods: Four public spatial transcriptomic datasets spanning wound healing, periodontitis, oral squamous cell carcinoma, and cardiac tissue were integrated using recurrence modelling, graph-based spatial learning, fuzzy tissue-state analysis, and tensor decomposition. Cross-domain coupling, spatial fragmentation, recurrence structure, and permutation-based topological validation were evaluated. Results: Six conserved fuzzy tissue states were identified, dominated by extracellular matrix remodelling, fibroblast/stromal activation, endothelial signalling, and inflammatory pathways. Latent embedding analysis demonstrated strong overlap between trauma and oral domains, while cardiovascular tissue exhibited more compact spatial organisation. Oral inflammatory tissue showed the highest fragmentation, whereas cardiovascular tissue demonstrated greater recurrence coherence. Tensor decomposition identified conserved stromal-remodelling programmes across domains. Permutation testing confirmed significantly elevated graph modularity and reduced spatial entropy relative to null distributions. Conclusion: The proposed framework identified conserved spatial tissue-state architecture linking wound healing, oral pathology, and cardiovascular tissue despite differences in tissue origin, pathology, and acquisition technology. Significance: These findings demonstrate the potential of spatial AI for investigating conserved stromal and inflammatory microenvironmental organisation across clinically related disease systems and may support spatial biology research in trauma–oral–systemic health.

Read & Discuss → View Source →
20.
arXiv (CS.CL) 2026-06-12

Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents

Authors:
Yujun Zhou↗Kehan Guo↗Haomin Zhuang↗Xiangqi Wang↗Yue Huang↗Zhenwen Liang↗Pin-Yu Chen↗Tian Gao↗Nuno Moniz↗Nitesh V. Chawla↗Xiangliang Zhang↗

Interactive LLM agents are becoming part of daily work, but they do not reliably become easier to work with over time: a correction remembered in one session may still be violated in the next. We study this gap between preference access and preference compliance. In tasks derived from anonymized real-user friction cases, Mem0 memory still leaves 57.5% of applicable preference checks violated. We introduce Test-time Rule Acquisition and Compiled Enforcement (TRACE), a drop-in skill-layer pipeline for coding-agent runtimes that mines user corrections, rewrites them as atomic rules, and compiles them into runtime checks that must pass before an agent completes future tasks. Unlike runtime checks written ahead of time by developers, TRACE skills come from the user's own chat corrections. We evaluate TRACE with simulated user-in-the-loop experiments on ClawArena coding-agent tasks and MemoryArena-derived memory-intensive tasks. On ClawArena, TRACE reduces held-out preference violation from 100.0% to 37.6% on in-distribution tasks and from 100.0% to 2.0% on out-of-distribution tasks. On MemoryArena-derived tasks, TRACE reduces in-distribution violation from 100.0% to 60.5% while matching or exceeding the strongest memory baseline on task pass. These results suggest that compiling corrections into runtime enforcement can address a repeated-friction failure mode that memory alone does not reliably solve, reducing the need for users to restate the same correction across future sessions. Experiment code is available at https://github.com/YujunZhou/TRACE_exp, and the deployable skill is available at https://github.com/YujunZhou/tellonce.

Read & Discuss → View Source →
21.
arXiv (CS.CL) 2026-06-12

It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO

Authors:
Naihao Deng↗Yilun Zhu↗Naichen Shi↗Clayton Scott↗Rada Mihalcea↗

Warning: This paper contains several toxic and offensive statements. Modern large language models (LLMs) are typically aligned through large-scale post-training to ensure fair and reliable behavior. In this work, we investigate how easily such guardrails can be broken by Group Relative Policy Optimization (GRPO). We show that one-shot GRPO training on a single biased example is sufficient to induce systematic bias, with stereotype-driven reasoning generalizing across attributes, categories, and benchmarks. We further find that models differ in their susceptibility based on the initial likelihood of producing biased outputs. Our results reveal a critical vulnerability in post-training: alignment can be overridden by a single example.

Read & Discuss → View Source →
22.
arXiv (CS.CV) 2026-06-16

Lesion-DDPM: Lesion-Enhanced 3D Diffusion for MS MRI Synthesis

Authors:
Weidong Zhang↗Yongchan Jung↗Shafayat Mowla Anik↗Furen Xiao↗Vasudevan Janarthanan↗Enkhzaya Chuluunbaatar↗Byeong Kil Lee↗Jeeho Ryoo↗

3D FLAIR MRI is widely recommended as one of the standard MRI sequences for brain imaging in multiple sclerosis (MS), but publicly available MS datasets remain relatively small and vary across scanners, acquisition protocols, and lesion patterns. This scarcity and variability hinder the development of robust neuroimaging machine learning models and are particularly challenging for generative models that aim to synthesize images while preserving small, sparse lesions. We propose Lesion-DDPM, a 3D conditional diffusion framework for lesion-aware FLAIR synthesis that incorporates multi-level anatomical mask injection together with a lesion-weighted reconstruction loss to emphasize lesion voxels while maintaining global brain structure. Using a curated subset of the MSLesSeg dataset, we compare Lesion-DDPM with representative state-of-the-art GAN- and diffusion-based models, assessing both image-generation metrics and downstream 3D U-Net segmentation. In our experiments, Lesion-DDPM achieved the lowest lesion-region reconstruction error among all methods. In a downstream 3D U-Net lesion segmentation task, a model trained only on Lesion-DDPM-generated scans and evaluated on real MRIs reached a Dice score of 0.616 compared with 0.569 for the best competing synthetic dataset. When Lesion-DDPM images were added to the real training set, the Dice score further increased to 0.685.

Read & Discuss → View Source →
23.
arXiv (CS.AI) 2026-06-12

MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMs

Authors:
He Li↗Haoang Chi↗Qizhou Wang↗Yunxin Mao↗Zhiheng Zhang↗Jie Tan↗Tongliang Liu↗Wenjing Yang↗Bo Han↗

arXiv:2606.12809v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are trained on massive multimodal data, making data unlearning increasingly important as data owners may request the removal of specific content. In practice, these requests often arrive sequentially over time, giving rise to the challenging problem of MLLM Lifelong Unlearning. However, most existing benchmarks are limited in scale and scope, failing to capture the complexities of MLLM lifelong unlearning. To fill this gap, we introduce the MLUBench, a large-scale and comprehensive benchmark featuring 127 entities across 9 classes under lifelong unlearning requests. We perform extensive experiments using MLUBench and reveal that existing unlearning methods suffer from severe, cumulative degradation. More critically, we further identify the unique challenge of this problem: unlike in unimodal models, MLLM lifelong unlearning is constrained by the need to preserve multimodal alignment. Continually unlearning from one modality could degrade the entire model. To alleviate this challenge, we propose LUMoE, an effective method. Experiments demonstrate that LUMoE significantly mitigates the degradation problem faced by baselines. The source code and the MLUBench dataset are open-sourced in https://github.com/lihe-maxsize/Lifelong_Unlearning_main.

Read & Discuss → View Source →
24.
arXiv (CS.CL) 2026-06-11

Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models

Authors:
Jia Deng↗Junyi Li↗Wayne Xin Zhao↗Jinpeng Wang↗Hongyu Lu↗Ji-Rong Wen↗

Diffusion large language models (dLLMs) offer an efficient alternative to autoregressive models through parallel decoding, yet existing post-training methods largely rely on random masking strategies that overlook intrinsic token dependencies. In this work, we present an empirical analysis of attention in dLLMs and show that tokens attending more strongly to unmasked context exhibit greater generation stability and play a critical role in reasoning. Motivated by these findings, we propose AGDO, an attention-guided denoising and optimization framework that aligns both training and optimization with attention-derived dependencies. AGDO determines the denoising order based on attention structure and emphasizes attention-critical tokens during supervised fine-tuning and reinforcement learning. Experiments on mathematical and coding benchmarks demonstrate that AGDO consistently improves reasoning performance, outperforming state-of-the-art post-training methods for dLLMs.

Read & Discuss → View Source →
25.
arXiv (CS.CV) 2026-06-16

Closed-Loop Triplet Synergistic Generation for Long-Form Video

Authors:
Xinlei Yin↗Xiulian Peng↗Xiao Li↗Zhiwei Xiong↗Yan Lu↗

Multi-shot long-form video generation remains challenging due to identity drift and compounding inconsistencies across shots. While storyboard-driven pipelines improve controllability, they are often executed in a feed-forward manner, with limited mechanisms to incorporate generated visual evidence back into subsequent conditioning. We propose CoTriSyGen, an agentic framework that formulates multi-shot long video generation as a closed-loop visual-text-memory synergy process, where planned intent, persistent memory, and generated visuals are jointly leveraged for iterative correction and long-range coherence. A vision-language-model-based analyzer reasons over this triplet and produces updates to both prompts and memory along two pathways: (i) intra-shot refinement, which triggers targeted regeneration when semantic or compositional violations are detected and refines image-to-video prompt for coherent motions; and (ii) inter-shot refinement, which rewrites subsequent-shot prompts to propagate newly manifested entities or attributes and improve prompt quality (e.g., compositional grounding and cinematic fluency) based on generated evidence. The loop is grounded in an entity-centric memory modeled as a mutable visual state that evolves as the story progresses, which is continuously updated by both the generator and the analyzer by adding new and evolved entities to reflect appearance changes, accumulated multi-view evidence, and multi-entity compositions. Experiments on our curated StoryBench benchmark demonstrate substantial improvements in cross-shot consistency, prompt adherence, and cinematic continuity over representative methods.

Read & Discuss → View Source →