# Research Papers — 2026-06 · bundle page 201 of 260 > Full-text markdown of papers #10001–10050 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/201 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/200.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/202.md) ### 3D Oral Modelling with Improved Vertex Distribution Using Matching-Based Learning Authors: Jihun Cho, Soo-Yeon Jeong, Eun-Jeong Bae, Sun-Young Ihm Published: 2026-06-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.07907v2 In our previous work, a deep learning-based framework for 3D intraoral reconstruction was proposed. The model directly predicts explicit 3D point cloud coordinates from ten fixed-angle intraoral images, employing MobileNetV2 and Multi-head Attention for multi-view feature fusion, with a combined L1 Loss and Chamfer Distance as the loss function. Although the model achieved an accuracy of 77.49%, predicted vertices tended to concentrate in high-density regions of the ground truth, leaving other regions largely uncovered. In this paper, an improved loss function is proposed to address this limitation. Hungarian matching with filtering and Repulsion Loss are introduced to enforce more uniform vertex distribution across the reconstructed model. The proposed model achieves an accuracy of 68.02%, which is numerically lower than the previous model. However, the vertex clustering issue observed in the prior work is substantially alleviated, with predicted vertices distributed more evenly across the entire reconstructed surface. --- ### 3D Oral Modelling with Improved Vertex Distribution Using Matching-Based Learning Authors: Jihun Cho, Soo-Yeon Jeong, Eun-Jeong Bae, Sun-Young Ihm Published: 2026-06-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.07907v1 In our previous work, a deep learning-based framework for 3D intraoral reconstruction was proposed. The model directly predicts explicit 3D point cloud coordinates from ten fixed-angle intraoral images, employing MobileNetV2 and Multi-head Attention for multi-view feature fusion, with a combined L1 Loss and Chamfer Distance as the loss function. Although the model achieved an accuracy of 77.49%, predicted vertices tended to concentrate in high-density regions of the ground truth, leaving other regions largely uncovered. In this paper, an improved loss function is proposed to address this limitation. Hungarian matching with filtering and Repulsion Loss are introduced to enforce more uniform vertex distribution across the reconstructed model. The proposed model achieves an accuracy of 68.02%, which is numerically lower than the previous model. However, the vertex clustering issue observed in the prior work is substantially alleviated, with predicted vertices distributed more evenly across the entire reconstructed surface. --- ### CIFQA: A Deterministic Tool-Grounded Multi-Agent LLM Framework for Financial Query Answering Authors: Kunjesh Parekh, Anil Kumar Tiwari, Divya Saxena Published: 2026-06-05 Categories: cs.AI, cs.CL, q-fin.CP arXiv: https://arxiv.org/abs/2608.26114v1 Calculation-intensive financial question answering requires exact reasoning over structured rates, temporal conditions, numerical formulas, and rule-based constraints. Although Large Language Models (LLMs) perform strongly on natural language tasks, they often produce numerically incorrect yet plausible answers when solving multi-step financial calculations. To address this limitation, we introduce CIFQA (Calculation-Intensive Financial Query Answering), a deterministic tool-grounded multi-agent LLM framework for financial question answering. CIFQA separates language understanding from numerical execution by assigning specialized agents to query interpretation, routing, parameter extraction, computation planning, and response generation, while deterministic Python-based tools perform financial calculations and rule application. We instantiate CIFQA for fixed deposit query answering and evaluate it on a curated benchmark of fixed deposit queries. CIFQA achieves 95.54% accuracy on calculation-intensive queries and 90.87% overall accuracy, substantially outperforming direct LLM baselines even when provided with complete formulas, rate cards, and benchmark instructions. Ablation studies show that deterministic components such as exact rate lookup, tenure computation, rolling-year adjustment, and premature-withdrawal logic are critical contributors to performance. Notably, a 17B open-source backbone operating within CIFQA outperforms substantially larger frontier models evaluated with the same financial information, demonstrating that architectural design is a more important determinant of numerical reliability than model scale. While evaluated on fixed deposit queries, CIFQA provides a generalizable framework for calculation-intensive financial reasoning tasks. --- ### RENDER: Controlling Reader-Facing Evidence in LLM Memory Evaluation Authors: Yuan Si, Simeng Han, Daming Li, Jialu Zhang Published: 2026-06-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.23568v1 Memory and RAG evaluations often treat the answering model's input as an implementation detail, even though systems may render the same history as a memory entry, summary, typed record, or raw excerpt. We introduce RENDER, a benchmark control that fixes the conversation while varying the reader-facing artifact. RENDER combines a five-level packet ladder, localizing when answer-bearing content enters the input, with deterministic templates approximating ChatGPT-style entries, LangChain summaries, MemGPT-style typed records, and raw conversation. On 500 LongMemEval questions and nine models, matched-budget resolved packets beat recency-truncated raw dialogue by 42.4-72.6 points. In deployed-style templates, best-worst spread is 24.6-48.8 points per model; under the primary scorer, ChatGPT-style entries have higher point estimates than raw conversation on 7 of 9 models. Judge rescoring preserves the positive aggregate effect, but model-specific significance is mixed. Three models scoring 0 percent on formal ledger packets answer the same facts from natural-language entries at 45.4-53.4 percent. The effect persists under retrieval noise and transfers to HotpotQA, suggesting that memory/RAG evaluations should report or control the reader-facing artifact. --- ### Automatic bioinformatic software named entity recognition from literature Authors: Hao Xuan, Rithvij Pasupuleti, Ben Liu, Haishuo Sun, Jun Zhang, Zijun Yao, Cuncong Zhong Published: 2026-06-05 Categories: cs.CL, cs.AI, cs.IR, q-bio.QM arXiv: https://arxiv.org/abs/2608.19201v1 Bioinformatics software and databases are essential components of modern life science research, yet their mentions in the scientific literature are often inconsistent and difficult to systematically identify at scale. The lack of a comprehensive and up-to-date catalog of bioinformatics resources hinders efforts toward automated biomedical knowledge extraction and streamlined data analysis. Here we present SNAIL, a hybrid named entity recognition framework designed to automatically identify bioinformatics software and database (SW/DB) names from biomedical texts. SNAIL integrates complementary lexical and semantic modeling strategies. The lexical component captures orthographic patterns and contextual cues characteristic of SW/DB names, while the semantic component leverages contextual embeddings generated by transformer-based language models such as SciBERT, combined with an explicit token-masking strategy to enhance entity-focused representations. A large training corpus was constructed automatically through a hybrid pipeline that integrates citation-hinted extraction with large language model-assisted distillation. Evaluation on two independent benchmark datasets and real-world research articles demonstrates that SNAIL substantially outperforms existing approaches, including domain-specific methods such as bioNerDS2 and general-purpose large language models such as ChatGPT, Gemini, Grok and Claude. Applying SNAIL to large-scale literature analysis further reveals distinct journal-level preferences across bioinformatics subfields. These results demonstrate that SNAIL provides an accurate and scalable solution for identifying bioinformatics resources in scientific texts and enables systematic meta-analysis of tool usage and research trends. --- ### Nine Emotion Centroids: A Label-Free Valence Axis That Transfers Across Four Modalities Authors: Yousef Radwan Published: 2026-06-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.18090v1 Inside a modern language model sits a single internal direction that tracks how positive or negative a sentence feels. We show how to find this valence axis (V-axis) from just 9 emotion category names plus 50 short narrative paragraphs per emotion -- about 1,500 fewer labels than the usual supervised approach -- and that the same direction appears in vision, audio, and human-brain encoders never jointly trained. The recipe: embed nine emotion-anchored story sets in a frozen encoder, take the top principal direction of the nine averaged embeddings. Projecting new inputs onto it captures 93% of supervised performance on SST-2 (Llama-3-8B-Instruct, AUC 0.772 vs. 0.828), correlates with human valence ratings on 11,811 EmoSet images at r=0.636, reaches AUC 0.906 on ESC-50 audio (p<2.2e-15), and AUC 0.720+/-0.055 on EEG from 123 subjects (p<3.65e-8). The direction is mechanistically active: ablating it collapses sentiment accuracy by 5.5-37.2 pp across three LLMs vs. at most 0.88 pp for matched random directions (z>12). A 2-parameter classifier trained on text labels transfers to images (AUC 0.961), audio (0.764), and brain recordings (0.828) without target-modality labels; a generic 16-D subspace stays at chance (0.525). The recipe is bounded to continuous attributes -- seven tests on categorical concepts return near-chance -- and steering is family-specific (Llama/Mistral yes, Qwen/Gemma no). --- ### Latent Space Refusal Anchoring for Low-Resource African Languages: Mechanistic Safety Recovery Without Retraining Authors: Godwin Abuh Faruna Published: 2026-06-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.18089v1 Instruction-tuned models often refuse harmful requests in English but comply with the same requests in Yoruba, Igbo, Igala, and Hausa. This suggests that the refusal mechanism is present in the residual stream but fails to activate for low-resource inputs. Recovering it normally requires labelled target-language data and retraining, neither of which is available at scale for most African languages. We introduce Latent Space Refusal Anchoring (LSR-Anchoring), a training-free method that extracts the refusal direction from English prompts and clamps it onto the residual stream at inference time. The primary variant, Mean-Activation Steering (MAS), operates across the four architectures we tested: Llama-3-8B, Llama-3.1-70B, Mistral-7B-Instruct, and Qwen2.5-7B. On Mistral and Qwen it recovers safety with benign degradation below 0.08. On Llama-3-8B it overcorrects, with Degraded Performance on Legitimate prompts (DPL) reaching 1.00. We address this with SAE-Derived Steering (SDS), which replaces the dense mean-difference direction with a single Sparse Autoencoder (SAE) feature and reduces Kullback-Leibler (KL) divergence by 3.5-7x without benign collapse. Four languages transfer positively, but Arabic fails on every architecture and at every steering magnitude, indicating a geometric mismatch rather than a baseline effect. Massive Multitask Language Understanding (MMLU) accuracy drops remain below 0.35 percentage points at every effective steering magnitude. --- ### A Metamorphic Artificial Age Score Decision-Support Prototype for Flight-Log-Based Drone Propeller Health Monitoring Authors: Seyma Yaman Kayadibi Published: 2026-06-05 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2608.18088v1 Drone propeller faults can create safety and reliability risks when their effects are distributed across multiple flight-log channels rather than appearing as a single diagnostic signal. This paper proposes a Metamorphic Artificial Age Score (AAS) decision-support prototype for flight-log-based drone propeller health monitoring. Using selected historical real flight logs from the 2024 DronePropA public dataset, the framework computes six health-related indicators from raw MATLAB matrices: trajectory tracking error, attitude instability, thrust-command burden, motor-command imbalance, ESC-command instability, and battery-level stress. These indicators are normalized relative to a healthy baseline and evaluated through candidate scoring policies, metamorphic adequacy relations, and a redundancy-adjusted AAS formulation. In this context, AAS is used as a structural policy-adequacy and burden measure rather than as a chronological age measure. A controlled retrospective evaluation was performed using one healthy baseline and three defective propeller cases under the same speed profile and trajectory. The healthy case was assigned to routine monitoring. The Severity 1 case was dominated by ESC-command instability and assigned to maintenance review. The Severity 2 case reached maximum motor-command and ESC-command burden, while the Severity 3 case reached maximum trajectory tracking error; both triggered mandatory inspection. The results show that propeller fault effects may appear through different operational channels, supporting the need for a multi-indicator decision-support layer for post-flight maintenance prioritization and autonomous-system oversight. --- ### SuTRA : Structurally-Unified Tokenization with Root Awareness Authors: Vaibhav Rathore, Siddhant Gole, Dadhichi Telwadkar, Rooshil Bhatia, Maulik Ruparel, Siddharth Sureka, Neha Bhargava Published: 2026-06-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.18087v2 Existing subword tokenizers optimize statistical compression but ignore morphological structure, particularly the relationship between roots and affixes. This is harmful for morphologically rich Indic languages, where basic units are complex orthographic syllables (aksharas) rather than letters. Frequency-based methods over-fragment words, arbitrarily splitting roots and affixes - a phenomenon we term Morphological Shattering. We propose SuTRA (Structurally-Unified Tokenization with Root Awareness), a morphology-aware algorithm that preserves akshara indivisibility and penalizes merges crossing morphological boundaries. We also release a new morphological segmentation dataset for Hindi, Marathi, and Gujarati. SuTRA reduces shattering, achieving peak gains of +14.7% in morphological alignment (Boundary F1) and +34% in semantic recoverability (Hindi) over BPE. These structural gains yield an average improvement of +8.08 chrF2 in machine translation. --- ### Position: Current Model Cards Are Insufficient for Downstream Governance of Open-Weight Foundation Models Authors: Sungwon Chae, Keonwoo Kim, Hoki Kim, Jaeyeon Ju, Sangchul Park Published: 2026-06-05 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.18086v1 The growth of open-weight foundation models (OWFMs) has prompted the AI community to re-evaluate strategies for effective downstream governance. Although model cards have been widely adopted as transparency artifacts in model repositories, existing frameworks often fail to adequately inform downstream developers and users about the distinct safety challenges posed by OWFMs. This position paper analyzes 500 model cards hosted on Hugging Face and argues that effective governance of OWFMs requires a multi-layered approach integrating three complementary components: (i) model cards, (ii) acceptable use policies (AUPs), and (iii) licenses. To motivate this claim, we identify a safety gap left by existing regulatory approaches, including model heritage, alignment provenance, and empirically observed behaviors, through an analysis of model cards with safety-critical information. We further argue that standard open-source licenses (OSLs) are not well suited for OWFMs and may weaken the enforceability of AUPs. Building on these observations, we outline directions for evolving model cards, AUPs, and licenses into integrated safety artifacts to enable a more comprehensive governance framework that coherently integrates informational, normative, and legal dimensions. --- ### Position: Want Better ML Reviews? Stop Asking Nicely and Start Incentivizing with a Credit System Authors: Shaochen Zhong Published: 2026-06-05 Categories: cs.AI, cs.DL arXiv: https://arxiv.org/abs/2608.14571v1 With soaring submission counts, stricter reciprocal review policies, widespread adoption of platforms like OpenReview, and without the offsetting pressure of publication fees, the machine learning (ML) community has one of the largest scholarly presences among all scientific fields. And yet, \textbf{almost \textit{everyone} has \textit{many} unpleasant things to share about their review experience.} Worse, there is little public space to seriously discuss, let alone debate, what makes a review system effective or how it might be improved.\quad In this position paper, we expand our discussion from two core problems: \textit{How can we reasonably limit submission volume?} and \textit{How can we incentivize good and discourage bad reviewing?} We first assess the strengths and shortcomings of existing attempts to address such problems. Specifically, we present four takes on some popular conference mechanisms and propose two alternative designs for improvement.\quad Our general position is that meaningful improvement in ML peer review won't come from polite best-practice suggestions tucked into Calls for Papers or Reviewer Guidelines: it requires \textbf{enforceable yet fine-grained procedural safeguards} paired with \textbf{a currency-like credit system (e.g., our proposed \textit{OpenReview Points})}. ML practitioners can ``earn'' such points by contributing good review practices, and ``spend'' them across one or multiple major conferences to redeem different kinds of ``perks,'' such as complimentary registration or the right to request additional review resources. --- ### Coarse-to-Fine Multi-Resolution Diffusion Models for Trajectory Generation in Urban Systems Authors: Wen Ye, Muyan Weng, Chuizheng Meng, Hao Niu, Yizhou Zhang, Yan Liu Published: 2026-06-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.14570v1 Understanding human mobility is critical for a wide range of urban applications, including traffic management, epidemic control, and urban planning. However, due to privacy concerns, the availability of large-scale public trajectory data remains limited, posing challenges for downstream mobility analysis. Existing methods for synthetic trajectory generation primarily focus on matching global distribution similarity, while often overlooking mobility patterns across different spatial and temporal resolutions that are essential for practical utility. To address these challenges, we propose a novel multi-resolution diffusion framework, MR-Traj, for large-scale trajectory generation. MR-Traj explicitly models trajectories as compositions of coarse-grained milestones and fine-grained segments, enabling the capture of complex spatial-temporal dependencies at multiple resolutions. Experimental results demonstrate that MR-Traj achieves comparable performance to state-of-the-art methods in terms of global distribution similarity, while consistently outperforming them in modeling fine-resolution mobility patterns and supporting downstream urban mobility tasks. In addition, by introducing stochasticity at multiple resolution levels, MR-Traj generates more diverse trajectories, which empirically reduces trajectory linkage risk under a seed-guided data release setting. Our code is available at https://github.com/Ray0202/MR-Traj. --- ### Position: The Alignment Community is Unintentionally Building a Censor's Toolkit Authors: Sarah Ball, Phil Hackemann Published: 2026-06-05 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2608.12346v1 This position paper argues that modern AI alignment methods - originally designed to prevent harmful output - are dual-use technologies that may easily be misused by malicious actors for censorship and manipulation. By mapping current alignment techniques to the possibility and actual cases of misuse, we show that the quest for a "perfectly aligned" model inadvertently also provides malicious actors with an ever-improving tool for informational dominance. We need to discuss this dual-use potential now, as its risk is exacerbated by rapid user adoption of AI as information provider, economic power asymmetries, and a political landscape that increasingly shifts towards authoritarianism. We conclude by urging the community to consider the intentional misuse of AI alignment mechanisms and propose mitigation strategies to safeguard against this dual-use potential. --- ### Multimodal Drivers' Emotion Recognition and Safety-Oriented Intervention for Intelligent Transportation Systems Authors: Chang Liu, Dalai Mengke, Hanbo Zhou, Jia Hu, Peter Mihajlik, Tamas Sziranyi Published: 2026-06-05 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2608.06378v1 Driver emotions can affect risk perception, decision-making, and vehicle control under complex road conditions. Existing studies mainly focus on driver emotion recognition, while limited attention has been given to context-aware intervention that jointly considers driver emotion and road perception. This paper proposes a safety-prioritized multimodal driver assistance framework that analyzes speech-derived emotional cues and visual road conditions to generate structured driving interventions. The framework first provides road safety reminders and then generates emotion-aligned verbal support. We construct a multimodal dataset by aligning emotional speech signals with structured road environment descriptors and introduce the CARE (Context-Aware Road-Emotion Evaluation) score to jointly evaluate emotion recognition, risk identification, and intervention generation. Experimental results show that the proposed framework balances environmental risk reporting and emotion-aware verbal regulation, providing a feasible safety-driven direction for intelligent transportation systems. --- ### Measuring and Improving Behavioral Consistency in Large Language Models through Fact-Heuristic-Emotion State Enforcement Authors: Gi-Hun Lee, Joong Yull Park Published: 2026-06-05 Categories: cs.CL, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2607.24765v1 Large language models (LLMs) can give different answers to the same decision problem across runs, and reverse a decision when their own prior answer returns as context. We ask whether this instability can be measured and partially reduced without changing model weights. We test the Cognitive Kernel Model (CKM), a prompt-level state-enforcement layer. Before deciding, the model must separate its input into three epistemic roles: Fact (given or verifiable), Heuristic (inferred or assumed), and Emotion (evaluative or priority signal). CKM adds no capability; it forces the model to track what kind of information it uses before acting. Formally it maintains a structured state S_t = {F_t, H_t, E_t} updated by a transition function. We evaluate CKM on Korean-language decision scenarios (ambiguity, ethical conflict, resource allocation, error handling) across 26 LLMs from four vendors and 37,403 observations, via four core experiments, a 4-arm ablation, a 5-arm sham-restriction ablation, and a temperature probe. Findings: (1) CKM reduces repeated-output variability (random-effects Hedges' g=1.09, 95% CI (0.83, 1.35), 31 model pairs); (2) state persistence cuts the decision-flip rate by 82% in newer models (g=1.52); (3) the effect is not JSON formatting alone (value-only recomputation, g=2.24); (4) intrinsic randomness under fixed anchor states is negligible; (5) the advantage grows under sampling stochasticity (g=2.87 at temperature 0.7); (6) a sham ablation attributes about 45% of the gain to structural scaffolding and 55% to Fact/Heuristic/Emotion content, and CKM is the only arm that both raises consistency and reduces flipping. CKM does not improve reasoning correctness. The narrower result: behavioral consistency is measurable, varies across models, and is partially improvable by forcing models to separate facts, assumptions, and evaluative signals before deciding. --- ### Temporal Context Reinstatement Drives Episodic-Like Order Memory in Long-Context Language Models Authors: Mathis Pink, Vy Ai Vo, Qinyuan Wu, Jianing Mu, Javier Turek, Uri Hasson, Kenneth A. Norman, Sebastian Michelmann, Alexander Huth, Mariya Toneva Published: 2026-06-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.22575v1 Human episodic memory supports the retrieval of experiences that unfold over extended timescales, yet the computational mechanisms underlying this ability remain debated due to the limited mechanistic accessibility in long-term memory experiments in humans. Long-context LLMs may offer promising ways to reveal plausible computational mechanisms that drive this type of retrieval. Here, we investigate whether and how LLMs capture the core behavioral signatures of episodic memory via a temporal order memory task. Using a new dataset of human behavior based on memory of a full-length novel, we show that models exhibit the same characteristic distance effect observed in humans on this task. We next apply long-context mechanistic interpretability analyses to uncover how models solve this task, and find that model performance relies on a one-dimensional temporal code that is reinstated during retrieval by a single time-reinstatement attention head. These findings support temporal context reinstatement as an important mechanism for episodic-like temporal-order memory in LLMs, offering new insights into how temporal aspects of long-term episodic memory may be instantiated in both artificial and biological systems. --- ### Too much evidence, too little time: From text to actionable recommendations through multi-objective evidence reasoning Authors: Adela Bara, Simona-Vasilica Oprea Published: 2026-06-05 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2607.22574v1 Evidence-based clinical decision making requires specialists to identify, evaluate and synthesize relevant scientific literature. However, PubMed searches for complex clinical cases often return hundreds of publications that cannot be reviewed manually under time constraints. This study proposes SCEPTER (Single-Case Evidence-driven PubMed-To-rEcommendation Reasoner), a framework for transforming clinical case descriptions into evidence-based recommendations. SCEPTER combines PubMed retrieval, PubMedBERT semantic ranking, large language model (LLM)-based claim extraction, evidence-level weighting, contradiction detection, consensus analysis and multi-objective Pareto claim selection. The framework generates structured evidence syntheses and grounded actionable recommendations. A Paper Q&A module further enables interactive exploration of selected publications. The proposed framework introduces multi-objective reasoning model that integrates literature support, contradiction analysis and interactive literature interrogation into a unified clinical decision-support pipeline. Evaluation on 150 case studies demonstrated that the framework reduced an average search space of 576 papers to 53 retained papers, 7 Pareto-optimal claims and 3 final recommendations, corresponding to an overall compression ratio of 192:1. Despite this reduction, the retained evidence maintained high diversity (entropy=0.901). The ablation study showed that Pareto-based selection increased evidence diversity and recommendation utility compared with conventional ranking approaches. --- ### SAE-StatSteer: Statistical Consensus Feature Selection for Optimization-Free Activation Steering of Large Language Models Authors: Oshayer Siddique, J. M Areeb Uzair Alam, Md Jobayer Rahman Rafy, Syed Rifat Raiyan, Hasan Mahmud, Md Kamrul Hasan Published: 2026-06-05 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.19364v2 Activation steering adds a residual-stream direction at inference time, providing lightweight behavioral control without fine-tuning. Sparse autoencoders (SAEs) can make such interventions auditable by decomposing dense activations into an approximately monosemantic feature basis. We introduce SAE-StatSteer, a transparent, optimization-free pipeline. It first filters features through six reliability conditions, then ranks the survivors by an unweighted Borda consensus over three statistics, an $F$-test, KSG mutual information, and Cohen's $d$, and finally combines the selected SAE decoder rows using Cohen's-$d$ weights. We evaluate three Gemma-family models across four behavioral domains against seven dense or SAE-based baselines. Our quality-conditioned protocol requires attribute movement while preserving relevance, richness, and coherence. Raw success systematically overstates usable control because strong shifts often degrade generation quality, and effective steering is not governed by a universal layer or strength. SAE-StatSteer remains competitive with optimization-based methods while exposing every selection and weighting decision for audit. These results motivate reporting quality-conditioned success alongside raw behavioral shift. Our code and data are available at https://github.com/Oshayer-Siddique/LLM-Steering-Using-SAE. --- ### Statistically Grounded Sparse-Feature Interventions for Activation-Space Control in Large Language Models Authors: Oshayer Siddique, J. M Areeb Uzair Alam, Md Jobayer Rahman Rafy, Syed Rifat Raiyan, Hasan Mahmud, Md Kamrul Hasan Published: 2026-06-05 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.19364v1 Activation steering offers a lightweight alternative to fine-tuning for behavioral control of large language models, but SAE-based steering methods often rely on learned steering objectives or single-criterion feature selection. We introduce a transparent SAE-feature steering pipeline that first applies a six-condition reliability filter, then ranks sparse features through an unweighted Borda consensus over three complementary statistics: $F$-test, KSG mutual information, and Cohen's $d$. The resulting steering direction is constructed as a Cohen's-$d$-weighted combination of SAE decoder rows, providing an optimization-free direction motivated by Fisher-LDA under approximate SAE-feature decorrelation. Across three Gemma-family models, four behavioral domains, and 356 layer-strength configurations, the method produces measurable domain-specific shifts while revealing a substantial gap between raw attribute movement and quality-preserving generation. In the strongest configuration, logical-correctness steering reaches a primary-score delta of $+1.16$ in Gemma~2 9B; however, our broader finding is that usable steering is highly localized by model, domain, layer, and strength. These results argue that activation-steering evaluations should report quality-conditioned success alongside raw behavioral shift. Our code and data are available at https://github.com/Oshayer-Siddique/LLM-Steering-Using-SAE. --- ### AdaRoPE: Not All Attention Heads Should Rotate and Scale Equally Authors: Shaowen Wang, Yuke Zheng, Tansheng Zhu, Shuang Chen, Shaofan Liu, Suncong Zheng, Jian Li Published: 2026-06-05 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.19363v3 Rotary Position Embedding (RoPE) is widely adopted in Transformers to encode positional information, yet standard implementations enforce a uniform frequency schedule and scaling across all attention heads. Using simplified retrieval tasks and length generalization scenarios, we show -- both empirically and theoretically -- that heads with different functional roles require distinct frequency ranges and attention scaling factors to operate effectively. Ignoring this structure leads to suboptimal utilization of embedding dimensions and degraded performance, particularly under long-context settings. To address these limitations, we propose AdaRoPE, which equips each attention head with learnable rotation frequencies and attention scaling factors. Pretrained LLMs with AdaRoPE consistently outperform existing RoPE variants, including partial RoPE and NoPE baselines. For context extension, we further show that uniform frequency and attention scaling, used in methods such as YaRN, are suboptimal. By applying head-specific scaling, AdaRoPE enables better context extension while better preserving short-context performance in both the extrapolation setting and the long-context continued pretraining setting. These results highlight the importance of optimizing rotary position embedding at the level of individual attention heads. --- ### AdaRoPE: Not All Attention Heads Should Rotate and Scale Equally Authors: Shaowen Wang, Yuke Zheng, Tansheng Zhu, Shuang Chen, Shaofan Liu, Suncong Zheng, Jian Li Published: 2026-06-05 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.19363v2 Rotary Position Embedding (RoPE) is widely adopted in Transformers to encode positional information, yet standard implementations enforce a uniform frequency schedule and scaling across all attention heads. Using simplified retrieval tasks and length generalization scenarios, we show -- both empirically and theoretically -- that heads with different functional roles require distinct frequency ranges and attention scaling factors to operate effectively. Ignoring this structure leads to suboptimal utilization of embedding dimensions and degraded performance, particularly under long-context settings. To address these limitations, we propose AdaRoPE, which equips each attention head with learnable rotation frequencies and attention scaling factors. Pretrained LLMs with AdaRoPE consistently outperform existing RoPE variants, including partial RoPE and NoPE baselines. For context extension, we further show that uniform frequency and attention scaling, used in methods such as YaRN, are suboptimal. By applying head-specific scaling, AdaRoPE enables better context extension while better preserving short-context performance in both the extrapolation setting and the long-context continued pretraining setting. These results highlight the importance of optimizing rotary position embedding at the level of individual attention heads. --- ### GraphContainer: A Unified Platform for Comparing and Debugging Graph RAG Methods Authors: Seonho An, Chaejeong Hyun, Min-Soo Kim Published: 2026-06-05 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2607.19362v1 Graph RAG mitigates hallucinations and stale knowledge in LLMs, particularly for multi-hop question answering. However, existing approaches remain highly fragmented and incompatible. The structural heterogeneity of graph formats across different frameworks and the lack of granular visualization tools make it exceedingly difficult to evaluate and compare retrieval behaviors. To bridge this gap, we propose GraphContainer, a novel platform designed to unify and visualize diverse graph RAG workflows. GraphContainer features two key components: (1) a Unified Graph Representation (UGR) layer that seamlessly standardizes multi-format graphs, and (2) a Graph Recorder that tracks and visually renders the step-by-step retrieval process. Through an interactive web interface, we demonstrate GraphContainer's ability to import heterogeneous graphs and perform live, traceable visual debugging of graph RAG methods. Ultimately, we show how GraphContainer enables controlled comparisons of various graph formats and retrieval strategies, lowering the barrier for researchers and practitioners to design optimal graph RAG pipelines. A demonstration video is available at https://youtu.be/O02eNJLwkU0. --- ### The Hidden Water Geography of U.S. Hyperscale Data Centers in the AI Era Authors: Gianluca Guidi, Francesca Dominici Published: 2026-06-05 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2607.02531v1 Water use by data centers is routinely reported as a single footprint, but water is consumed through two physically distinct pathways: at the site for cooling and in the power system that generates electricity. We mapped both pathways for 472 U.S. hyperscale facilities by linking facility locations to electricity regions, hydrologic basins, and water-stress data. Under baseline assumptions, operational water consumption totals approximately 300 GL yr^-1 (range 205-451 across scenarios), with electricity-related water contributing three-quarters of the total. The two pathways produce different hotspot geographies: direct cooling burdens concentrate in stressed western and south-central basins, whereas electricity-related burdens concentrate in a few eastern grid regions with fossil-heavy supply. Just 3 of 24 hosting balancing authorities account for 59% of electricity-related water. Separating pathways identifies which decisions matter where: cooling design and water sourcing locally, electricity planning and procurement regionally --- ### The Rising Unsustainability of AI Graphics Cards Production Authors: Clément Morand, Aurélie Névéol, Anne-Laure Ligozat Published: 2026-06-05 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2607.01258v1 The rapid advancement of Artificial Intelligence (AI) has been accompanied by significant increases in computational and environmental costs, driven by large-scale investments in AI infrastructure, hardware, and software. In particular, graphics cards have become central to AI training, with frequent hardware updates required to meet escalating computational demands. However, the environmental damages of graphics cards production remain understudied. This study addresses this gap by estimating the environmental damages associated with graphics cards production over the past decade (2013-2025). We analyze trends in energy consumption, carbon emissions and resource depletion. We compile and provide a dataset documenting the environmental damages of NVIDIA workstation graphics cards production since 2013. Our analysis of this dataset reveals a steady increase in production-related impacts over the period. Our finding highlights the need for greater transparency in life-cycle data, a persistent challenge in AI environmental assessments. While operational efficiency improvements (e.g., energy-efficient training, carbon-aware computing) are often prioritized, our results underscore that production-related impacts are also escalating and cannot be overlooked. The AI community must move beyond incremental optimizations and confront the necessity of sufficiency. This shift may demand structural changes such as policy interventions, hardware design for longevity, and cultural shifts away from perpetual growth and increased performance. --- ### MediEncoder: Nonlinear Representation Learning for High-Dimensional Causal Mediation Analysis Authors: Shi Bo, Debarghya Mukherjee, AmirEmad Ghassami Published: 2026-06-05 Categories: stat.ME, cs.LG, math.ST, stat.ML arXiv: https://arxiv.org/abs/2606.30648v1 Causal mediation analysis decomposes a treatment effect into indirect pathways through mediators and direct pathways not operating through them. Modern biomedical studies often involve high-dimensional covariates and mediators that are noisy proxies for lower-dimensional latent biological processes. Existing methods typically rely on sparsity, linear factor models, or ignore the connection among variables in the learned representations, which can be restrictive when measurements are nonlinear and covariate and mediator factors are structurally dependent. We propose MediEncoder, a representation-learning framework for nonlinear high-dimensional mediation analysis. MediEncoder jointly learns low-dimensional covariate and mediator representations using a coupled encoder-decoder architecture with a cross-factor network that links treatment and covariate representations to mediator representations. The learned features are then used in a cross-fitted efficient influence function-based estimator of natural direct and indirect effects. The resulting estimator is multiply robust and asymptotically normal under suitable regularity conditions. Simulations show that MediEncoder improves estimation accuracy over competing dimension-reduction approaches, and an application to Alzheimer's Disease Neuroimaging Initiative data illustrates its utility in high-dimensional biomedical causal mediation analysis. --- ### Sifei at SemEval-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn RAG Authors: Sifei Meng, Dmitry Ilvovsky Published: 2026-06-05 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2606.28352v1 Multi-turn retrieval-augmented generation (RAG) is challenging due to evolving user intent, conversational noise, and strict context limits. We propose a training-free hybrid retrieval pipeline for SemEval-2026 Task 8 that combines dense and sparse retrieval with controlled query rewriting and cross-encoder reranking. On the official test set of Task A, our system achieves 0.5453 nDCG@5, ranking third among 38 teams and outperforming the strongest baseline score of 0.4795. For Task C, we reuse the documents retrieved for Task A and apply a lightweight generation pipeline guided by the official prompt, achieving 0.5312 as the harmonic mean of relevance and faithfulness and ranking 15th among 29 teams. All retrieval components are open-source, while query rewriting and answer generation rely on LLM APIs. --- ### Bridging Multi-Valued Heuristics and Dimensionality Reduction in Multi-Objective Search Authors: Maya Wolff, Ariel Felner, Oren Salzman Published: 2026-06-05 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2606.20644v1 Multi-objective shortest-path (MOSP) algorithms traditionally rely on single-valued heuristics (SVHs), which associate each state with a single admissible cost vector. While SVHs provide safe lower bounds, they fail to capture the trade-off structure of the Pareto frontier and often yield weak search guidance. Multi-valued heuristics (MVHs) address this limitation by mapping states to sets of cost estimates, enabling a richer approximation of possible trade-offs. Modern MOSP algorithms are highly dependent on dimensionality reduction (DR) techniques to efficiently perform dominance checks. However, integrating MVHs with DR introduces subtle correctness challenges. We show that naively combining DR with MVHs destroys the ordering invariants required for DR, leading to unsound and incomplete search. To address this issue, we develop the first theoretical frameworks for safely integrating MVHs with DR. First, we introduce $\text{NAMOA}^*{\text{dr}\text{-}\text{mvh}}$, a theoretical baseline that restores search correctness by enforcing heuristic consistency. Recognizing the practical limitations of this approach, we then introduce our primary contribution, $\text{L}\text{-}\text{NAMOA}^*{\text{dr}\text{-}\text{mvh}}$. This algorithm employs a "lazy," optimistic approach to DR, preserving exact correctness with only an admissible MVH by dynamically detecting and repairing local ordering violations. Across a range of benchmarks, $\text{L}\text{-}\text{NAMOA}^*{\text{dr}\text{-}\text{mvh}}$ matches or improves over state-of-the-art MOSP algorithms, and achieves speedups of over 10x in instances where the additional guidance provided by the MVH translates into stronger pruning. --- ### SPARC: A Multi-Agent System for Electrical Circuit Question Answering Authors: Mushtari Sadia, Zhenning Yang, Umme Habiba Lamia, Nishat Shawrin, Ang Chen, Amrita Roy Chowdhury Published: 2026-06-05 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2606.20643v1 Electrical circuit diagram QA tasks require complex mathematical reasoning, which remains challenging for multimodal LLMs. We present SPARC, a multi-agent system that answers questions over circuit diagrams by grounding reasoning in executable physics-based simulations. SPARC uses LLM agents to synthesize, execute, and analyze simulation programs, improving accuracy and reliability by design. It achieves 83% accuracy, with up to a 58% absolute improvement over baselines, while enabling systematic error diagnosis. --- ### A physical adaptive material motor unit neural network: a hygromorph composite material machine Authors: Charles de Kergariou, David Correa, Adam W. Perriman, Helmut Hauser, Fabrizio Scarpa Published: 2026-06-05 Categories: cs.ET, cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2606.18275v1 Advances in novel materials science enable structures to function as intelligent machines by embedding memory and learning capabilities directly into materials. Our work introduces a physical adaptive material motor unit neural network,leveraging a new generation of controllable actuators composed of wood- and carbon black-based composites, sensitive to temperature and relative humidity. These material actuators are assembled into a motor unit-like structure inspired by muscle contraction trigger, forming an intelligent machine capable of dynamic shading control that can be used, for example, in buildings. The machine is governed by a neural network trained on over 350 experimental data points collected under diverse environmental conditions. By establishing a new data-aware backpropagation training, we show that the machine predicts shading responses and learns to predict appropriate behaviour incrementally as the database expands. We also demonstrate the ability of the machine to optimise configurations to achieve similar shading outputs under two distinct conditions. --- ### Continuous Audio Thinking for Large Audio Language Models Authors: Gyojin Han, Dong-Jae Lee, Changho Choi, Jongsuk Kim, Junmo Kim Published: 2026-06-05 Categories: cs.CL, cs.AI, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2606.18273v1 Large audio language models (LALMs) have shown impressive capabilities on diverse audio understanding tasks, ranging from speech transcription to music analysis. However, because LALMs are typically trained to produce text-aligned responses, their hidden states are progressively shaped for text generation rather than for preserving acoustic information. As a result, the diverse acoustic content that audio carries, such as phonetic detail, prosody, sound events, affect, and pitch, is lost along the way and difficult to leverage in the response. We introduce Continuous Audio Thinking (CoAT), a framework that equips audio language models with a continuous latent workspace for organizing acoustic information prior to response generation, grounded by distillation from audio experts. Within the thinking space, the model can utilize the rich acoustic information provided by expert distillation when generating its response. Furthermore, the proposed continuous thinking block can be processed in a single prefill, so CoAT does not require additional autoregressive decoding cost over the baseline. Across three LALMs, Qwen2-Audio, Qwen2.5-Omni-7B, and Audio Flamingo~3, performance gains on a broad benchmark suite spanning audio reasoning, audio understanding, music classification, speech emotion, and speech transcription demonstrate the effectiveness of CoAT. Further analysis confirms that the auxiliary supervision propagates from the thinking positions to the model's textual responses. --- ### Mitigating Anchoring Bias in LLM-Based Agents for Energy-Efficient 6G Autonomous Networks Authors: Hatim Chergui, Claudia Carballo González, Farhad Rezazadeh, Merouane Debbah Published: 2026-06-05 Categories: cs.NI, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2606.18272v2 This paper presents an autonomous agentic resource negotiation framework designed to enable zero-touch network slicing in 6G architectures using Large Language Model (LLM) agents. While LLMs offer powerful reasoning capabilities, we demonstrate that such agents inherently suffer from anchoring bias, rigidly adhering to initial heuristic proposals and causing severe network over-provisioning. To systematically mitigate this cognitive bias, we propose a novel randomized anchoring strategy modeled via a Truncated 3-Parameter Weibull distribution. This mathematically bounded approach seamlessly integrates with burst-aware Digital Twins (DTs) employing Conditional Value at Risk (CVaR) to rigorously guarantee strict Service Level Agreement (SLA) tail-latencies. To validate our methodology, we introduce and prove the \emph{Bimodal Constraint-Avoidance Utility Theorem}, demonstrating that while feasible negotiations follow classical convex bounds, highly constrained scenarios undergo a phase transition governed by an inverse rational decay envelope. Empirical results generated using a locally hosted 1B-parameter model otel-llm-1b-it confirm these dual-regime bounds. Our cognitive de-biasing successfully dismantles rigid negotiation patterns, forcing agents into active exploration to safely ride SLA boundaries and boost system energy savings up to 25\%. Crucially, the lightweight 1B LLM achieves sub-second inference latencies (0.95s mean), ensuring our multi-agent framework is compatible with the operational timescales of the O-RAN non-Real-Time RAN Intelligent Controller (non-RT RIC)\footnote{Our source code is available for non-commercial use at https://github.com/HatimChergui. --- ### NAVI-Orbital: First In-Orbit Demonstration of a Zero-Shot Vision-Language Model for Autonomous Earth Observation Authors: Juan Manuel Delfa Victoria, Taran Cyriac John, Andrew W. Herson Published: 2026-06-05 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.18271v1 As Earth Observation data generation outpaces downlink bandwidth and human-in-the-loop processing, a widening gap has emerged between onboard collection and actionable ground intelligence. This paper presents NAVI-Orbital, a software system deployed on a Low Earth Orbit (LEO) spacecraft. On April 16, 2026, NAVI-Orbital achieved what is, to the authors' knowledge, the first in-orbit demonstration of a vision-language model performing autonomous multi-modal inference entirely onboard. NAVI-Orbital uses a local vision-language model (Gemma 3) to classify each captured scene, produce a text description of its content and the relationships between its features, and respond to operator follow-up via natural-language dialogue. The system is re-tasked through plain-English prompts in place of conventional command sequences, and is orchestrated by a graph-based state machine (LangGraph) coordinating dedicated agents for detection and dialogue. Results across ground benchmarking (88.16% accuracy on the 7,960-image curated AID benchmark), Flatsat validation, and live in-orbit captures of newly acquired, previously unseen Earth imagery (including uncorrected YAM-9 imagery, processed onboard with hardware-accelerated GPU inference and no fine-tuning for the flight instrument) demonstrate the feasibility of running foundation models on satellite-class edge computers to invert the conventional acquire-then-downlink-everything bandwidth profile through semantic compression of Earth observations in-orbit. --- ### Pixel-TTS: Image based Text Rendering for Robust Text-to-Speech Authors: Adarsh Arigala, Arjun Gangwar, S Umesh, Yova Kementchedjhieva Published: 2026-06-05 Categories: eess.AS, cs.AI, cs.CV, cs.SD arXiv: https://arxiv.org/abs/2606.14750v2 Recent advances in pixel-based text modeling show that representing text as images enables models to exploit visual cues for language understanding. Grounding text in its visual form allows structurally similar characters with different Unicode encodings to produce similar embeddings, benefiting cross-lingual and zero-shot scenarios. Conventional text-based approaches treat each character independently, limiting generalization to unseen characters and requiring embedding expansion during cross-lingual adaptation. We propose Pixel-TTS, a text-to-speech framework for visually grounded speech synthesis. It renders text as images and projects them through a 2D convolutional layer to generate embeddings. This design eliminates embedding matrix expansion during fine-tuning while improving robustness to unseen characters and orthographic variations. Extensive experiments show Pixel-TTS achieves competitive performance with strong baselines, faster convergence and robust zero-shot generalization. --- ### Automated 3D Kinematic Monitoring for Circadian Activity and Anomaly Detection in Juvenile Fish Authors: Chih-Wei Huang, Chang-Wen Huang, Chung-Ping Chiang, Tsung-Wei Pan Published: 2026-06-05 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.14749v1 Precision aquaculture faces a "phenotyping bottleneck" in tracking high-resolution behavioral traits, as conventional methods cannot quantify instantaneous three-dimensional (3D) physical exertion. To address this, we present a high-throughput 3D behavioral phenotyping framework integrating deep learning object detection with binocular stereo vision for real-time monitoring of juvenile tilapia in high-density environments. The system automates non-contact body length estimation and reconstructs 3D swimming trajectories from absolute spatial coordinates. By eliminating 2D perspective distortions, this approach precisely quantifies 3D velocity and acceleration, marking the first estimation of true physical swimming speeds in free-roaming juveniles. Results show the framework successfully establishes circadian locomotor baselines, serving as an early warning system for physiological stress and providing an objective metric for fish vitality. --- ### Is My Vision-Language Data in Your AI? Membership Inference Test (MINT) Demo 2 Authors: Daniel DeAlcala, Gonzalo Mancera, Julian Fierrez, Aythami Morales, Ruben Tolosana, Ruben Vera-Rodriguez Published: 2026-06-05 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.14748v1 We present the Membership Inference Test (MINT) Demo 2, a framework designed to improve transparency in machine learning training processes. MINT is a technique for experimentally determining whether specific data were used during machine learning model training. We establish the theoretical framework and propose multiple architectures for MINT depending on the amount of information known about the models that are being audited. Experimental results using a popular face recognition model, 4 state-of-the-art LLMs, and multiple, diverse, and large-scale public image and text databases achieve promising accuracy levels in the detection of training data of up to 90%. Building on these results, we introduce a comprehensive web platform1 that expands these capabilities to image and text modalities. The platform integrates a diverse technological stack, including MINT, aMINT, and gMINT, allowing users to audit a wide range of models. This demonstrator aims to promote AI transparency and provides a practical tool to foster compliance with emerging AI regulations. --- ### MMLongEmbed: Benchmarking Multimodal Embedding Models in Long-Context Scenarios Authors: Haitian Wang, Ruoxi Sun, Quantong Qiu, Juntao Li, Junhui Li, Hua Chen, Jinxiong Chang, Min Zhang Published: 2026-06-05 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.14747v2 Recent advancements have significantly expanded the theoretical context windows of Multimodal Embedding Models (MEMs). However, larger context windows do not necessarily translate into effective comprehension and representation of long-context multimodal inputs, which remains a critical bottleneck for real-world deployment. To address the lack of systematic evaluation in this setting, we introduce MMLongEmbed, the first comprehensive benchmark for evaluating MEMs in long-context scenarios. MMLongEmbed comprises four retrieval tasks spanning multiple context-length ranges, covering text, document, and video modalities. Through extensive evaluation of state-of-the-art models, we find that current architectures rely heavily on superficial feature matching and struggle to capture deep semantic and structural dependencies. We further observe that performance degradation varies systematically with context length and key information placement. Moreover, models exhibit substantially different robustness to redundant contextual information across modalities. For reproducibility, the benchmark and code are publicly available. --- ### MMLongEmbed: Benchmarking Multimodal Embedding Models in Long-Context Scenarios Authors: Haitian Wang, Ruoxi Sun, Quantong Qiu, Juntao Li, Junhui Li, Hua Chen, Jinxiong Chang, Min Zhang Published: 2026-06-05 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.14747v1 Recent advancements have significantly expanded the theoretical context windows of Multimodal Embedding Models (MEMs). However, larger context windows do not necessarily translate into effective comprehension and representation of long-context multimodal inputs, which remains a critical bottleneck for real-world deployment. To address the lack of systematic evaluation in this setting, we introduce MMLongEmbed, the first comprehensive benchmark for evaluating MEMs in long-context scenarios. MMLongEmbed comprises four retrieval tasks spanning multiple context-length ranges, covering text, document, and video modalities. Through extensive evaluation of state-of-the-art models, we find that current architectures rely heavily on superficial feature matching and struggle to capture deep semantic and structural dependencies. We further observe that performance degradation varies systematically with context length and key information placement. Moreover, models exhibit substantially different robustness to redundant contextual information across modalities. For reproducibility, the benchmark and code are publicly available. --- ### C-MambaPose: A Physics-Informed Complex Mamba Framework for Cross-Environment WiFi Human Pose Estimation Authors: Phuc Nguyen H Published: 2026-06-05 Categories: eess.SP, cs.CV arXiv: https://arxiv.org/abs/2606.13700v1 Human pose estimation (HPE) utilizing wireless WiFi signals has emerged as a promising technology owing to its device-free nature, privacy preservation, and robustness against occlusion and poor lighting. However, existing methods often overlook the physical complex phase information of WiFi signals and fail to generalize across diverse environments due to severe domain shifts. In this paper, we present C-MambaPose, a physics-informed complex-valued Mamba-GraFormer hybrid framework for robust cross-environment WiFi-based 3D HPE. Our framework first sanitizes raw WiFi Channel State Information (CSI) phase errors and constructs a phase-preserving complex-valued representation. We then employ a Spatiotemporal Complex Mamba encoder with a dynamic selective receptive field to capture fine-grained phase dynamics. A cross-attention joint-query mapper maps the unstructured sequence tokens to human joints, which are decoded by a Graph Convolutional Network (GCN) to predict anatomically coherent 3D coordinates. Extensive evaluations on the MM-Fi dataset show that C-MambaPose achieves competitive or superior performance to state-of-the-art baselines across all settings, setting a new state-of-the-art specifically on the challenging cross-environment split, requiring only 3.78 M parameters-an 83.1\% reduction compared to GraphPose-Fi~\cite{chen2026graph} and an 85.7\% reduction compared to MetaFi++~\cite{zhou2023metafi++}, while maintaining a comparable size to DT-Pose~\cite{chen2025towards} (which is only 18\% smaller) but achieving significantly superior performance without requiring any pretraining. Our code is publicly available at https://github.com/phucngvinuni/cmampose.git. --- ### Position: Hippocampal Explicit Memory Is the Cornerstone for AGI Authors: Sangjun Park Published: 2026-06-05 Categories: cs.AI, cs.NE, q-bio.NC arXiv: https://arxiv.org/abs/2606.11245v1 Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, raising expectations for Artificial General Intelligence (AGI). This position paper argues that integrating explicit memory is the cornerstone for advancing LLMs toward AGI. The key reason is that the underlying learning mechanism of LLMs is highly analogous to human implicit memory. However, higher-order cognitive functions necessary for AGI, such as long-term strategic planning, metacognition, and symbolic reasoning, heavily rely on hippocampal explicit memory and cannot arise solely from implicit statistical learning. Drawing on findings from neuroscience, I advance this perspective and complement it with computational requirements for artificial explicit memory systems, hoping to foster further research and lay the groundwork for explicit memory integration. --- ### The Whale That Outswam Evolution: Swarm Intelligence Maximises Memory in Connectome Reservoirs Authors: Anmol Guragain, Savvas Kakalis, Juan Ignacio Godino-Llorente Published: 2026-06-05 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2606.09902v1 Reservoir computing exploits the fixed dynamics of a recurrent network for temporal processing, requiring only a trained linear readout. Biological neural connectomes, shaped by millions of years of evolution, may encode computational structure beyond what random reservoirs provide, yet whether that structure can be further enhanced by principled optimisation remains an open question. We address it by applying four gradient-free, bio-inspired optimisers (Particle Swarm Optimisation, Differential Evolution, Grey Wolf Optimiser, and Whale Optimisation Algorithm) to the edge weights of connectome-based echo-state networks across six species spanning six orders of magnitude in neural complexity: C. elegans (279 neurons), Drosophila (49 nodes), mouse (112), rat (73), macaque (29 regions, continuous FLNe synaptic strengths), and human structural MRI connectivity (83 parcels). Each connectome is evaluated on four canonical reservoir computing benchmarks: Memory Capacity (MC), Lorenz attractor prediction, NARMA-10 system identification, and Mackey-Glass chaotic time-series prediction. All four optimisers consistently outperform unoptimised biological baselines across every task and species when initialised from biological weights. WOA achieves the largest gains on every task: up to a 17x MC improvement (C. elegans: 1.39 to 23.91) and up to 89% NRMSE reduction (Mackey-Glass, human), corresponding to an average 214% improvement across all species and tasks. Crucially, random initialisation on the same topology reliably underperforms biology, establishing biological weight values as an essential inductive bias that topology alone cannot recover. These results position bio-inspired, biologically-initialised optimisation as a principled and broadly effective strategy for connectome reservoir computing across the animal kingdom. --- ### On the Controllability-Fidelity Frontier in Diffusion Editing Authors: Yi Hu, Leying Yi, Emily Davis, Finn Carter Published: 2026-06-05 Categories: cs.GR, cs.CV, cs.HC, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2606.09901v1 Diffusion-based generative models enable powerful image editing capabilities, but achieving precise control while maintaining fidelity and safety remains challenging. We present a comprehensive theoretical and empirical study of controllable diffusion-based image editing, analyzing the trade-offs between adherence to user intent, preservation of non-target content, and output quality. Our work spans text- and mask-guided edits, point/drag manipulation, and inversion-based pipelines. We derive mathematical formulations of editing objectives and analyze dynamics of noise injection, score guidance, and inversion error. We provide theoretical bounds on reconstruction error, stability under repeated edits, and locality of changes. We propose algorithmic frameworks (with pseudocode) for mask-localized and instruction-guided editing, and present extensive experiments comparing state-of-the-art methods (e.g.\ TF-ICON \cite{lu2023tficone}, DragFlow \cite{zhou2025dragflow}, InstructPix2Pix \cite{brooks2023instructpix2pix}, UltraEdit \cite{zhao2024ultraedit}) on multiple tasks and metrics (FID, identity similarity, CLIP alignment, artifact scores, etc). Our results reveal key failure modes, such as identity drift, prompt sensitivity, and compositional errors. We also discuss ethical considerations in image editing, including misuse risks, bias, consent, and concept erasure techniques (e.g.\ MACE \cite{lu2024mace}, ANT \cite{li2025ant}, EraseAnything \cite{gao2024eraseanything}) as safeguards. We conclude with best practices and future directions for responsible, high-fidelity diffusion-based editing. --- ### Less Context, More Accuracy: A Bi-Temporal Memory Engine for LLM Agents Where a Lean Retrieved Context Beats the Full History Authors: Liuyin Wang Published: 2026-06-05 Categories: cs.CL, cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2606.09900v1 Long-term memory is the missing layer for LLM agents: across sessions they forget, and the common workaround -- replaying the whole history into the prompt -- is expensive, slow, and, as distractors accumulate, less accurate. Most memory systems win on cost or latency but still lose to the full-context baseline on accuracy, and benchmark numbers are reported on inconsistent, non-reproducible harnesses, so one system appears at wildly different scores across sources. We present Engram, an open-source, dual-process memory engine on a bi-temporal data model. A fast write path appends lossless episodes with no LLM on the critical path; an asynchronous path extracts atomic (subject, predicate, object) facts, builds a bi-temporal knowledge graph, and resolves contradictions without an LLM call per fact -- invalidating, never deleting, so every fact keeps provenance and a supersession chain. A hybrid read path fuses dense, lexical, graph, and recency/salience signals, applies a point-in-time ("as-of") filter, and assembles a compact, provenance-tagged context. On the full 500-question LongMemEval_S, graded by the official category-specific judge, Engram's lean configuration -- answering from a ~9.6k-token retrieved slice, never the full history -- scores 83.6% vs. 73.2% for full-context (+10.4 points, McNemar p < 10^-6) at ~8x fewer tokens (9.6k vs. 79k), with 0/500 errored. The gain needs a hybrid read path: facts alone lose recall, while facts plus retrieved chunks recover detail. We also contribute a neutral, in-repo evaluation harness with the official judge baked in and the full-context baseline in every table, publish the raw per-question logs, and document the measurement-integrity pitfalls (truncation, home-grown judges, full-history leaks) that silently distort memory benchmarks. Every number ships with a command to reproduce it. --- ### When Attribution Patching Lies: Diagnosis and a Second-Order Correction Authors: Luyang Zhang, Jialu Wang Published: 2026-06-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.09899v1 A central goal of mechanistic interpretability is to identify which internal components causally drive a language model's behavior. Because these importance estimates serve as the evidence for identifying circuits, systematic errors can lead to the misidentification of the underlying mechanisms. While activation patching provides a gold-standard causal metric, its computational cost is prohibitive at scale. Practitioners instead rely on attribution patching, a gradient-based, first-order approximation whose reliability remains poorly understood. In this work, we characterize the source of this unreliability, demonstrating that the dominant error stems from the non-linearities in the downstream network rather than local curvature at the patched component. This insight yields three practical tools: (i) a reliability score to detect untrustworthy estimates, (ii) error bounds quantifying potential attribution mis-specifications, and (iii) a Hessian-vector-product (HVP) correction that eliminates the leading-order error with only one additional backward pass. In evaluations across five model families (124M-9B parameters) and both random-token and naturalistic (name-swap) perturbations, HVP is the only second-order correction feasible at larger scale, where standard baselines like Integrated Gradients become computationally prohibitive. In comparative experiments, a multi-step HVP variant matches or exceeds the accuracy of Integrated Gradients at significantly lower compute, outperforming prior second-order baselines. These improvements lead to higher-fidelity circuit recovery on standard benchmarks and support a Screen-Flag-Fix workflow that targets computational effort only toward the components flagged as unreliable. --- ### TRAPS: Treatment-Assignment Prediction via Pathway-informed Stratification Authors: Sujoy Banik, Sayantan Chakraborty, Boishakhi Das Toma, Zainab Ghafoor, Ushashi Bhattacharjee, Koushik Howlader, Tirtho Roy Published: 2026-06-05 Categories: cs.LG, cs.MA, q-bio.QM arXiv: https://arxiv.org/abs/2606.09898v2 Cancer treatment involves decisions across multiple clinical outcomes, yet pathway-informed deep learning models are typically evaluated in isolation, making their relative benefits unclear. We present a harmonized benchmark of three biologically informed architectures, BINN, GraphPath, and PATH, for predicting treatment exposure and short-term survival across five TCGA cancer cohorts comprising 2,622 patients represented by Reactome pathway activity scores. Treatment labels indicate recorded exposure in TCGA rather than therapeutic response. All models jointly predict targeted molecular therapy (TMT), radiation therapy (RT), and six-month overall survival (OS) from a shared pathway representation and are evaluated on identical stratified folds using five repeated splits and paired-bootstrap testing. Under this controlled evaluation, most differences between architectures fall within 95 percent confidence intervals, indicating that rankings suggested by isolated evaluations are largely not statistically resolved. The main exception is survival prediction: the sparse-hierarchy BINN significantly outperforms both graph models on breast-cancer OS, with an AUROC improvement of up to 0.14 and p less than or equal to 0.01, and leads on lung and prostate OS. For treatment exposure, TMT is best discriminated in prostate cancer, with AUROC approximately 0.80 for all models, but no architecture significantly outperforms another on any TMT cohort. RT prediction remains weak across models, suggesting that its determinants may be more clinical than transcriptomic. Overall, architecture choice has limited impact under a unified evaluation, while short-term survival provides the clearest differentiation among pathway-informed models. --- ### TRAPS: Therapeutic Response Analysis via Pathway-informed Stratification Authors: Sujoy Banik, Sayantan Chakraborty, Boishakhi Das Toma, Zainab Ghafoor, Ushashi Bhattacharjee, Koushik Howlader, Tirtho Roy Published: 2026-06-05 Categories: cs.LG, cs.MA, q-bio.QM arXiv: https://arxiv.org/abs/2606.09898v1 Cancer treatment planning requires decisions across multiple clinical dimensions at once. Clinicians must determine whether a patient should receive targeted molecular therapy, radiation therapy, and whether they are likely to survive beyond six months. Existing pathway-informed deep learning models have been developed and tested in isolation, making fair comparison across architectures impossible. We present the first unified benchmark for pathway-guided therapy response modeling, evaluating three biologically informed architectures, BINN, GraphPath, and PATH, across five cancer cohorts drawn from The Cancer Genome Atlas, representing 2,622 patients encoded using Reactome pathway activity scores. Each model is trained jointly on all three clinical outcomes under identical data and evaluation conditions, the first study to treat pathway-structured deep learning as a combined therapy and survival prediction problem. Our results show that no single architecture wins across all tasks: PATH performs best for targeted molecular therapy prediction overall, BINN is most reliable for survival prediction, and no model produces useful predictions for radiation therapy, as the key drivers of that decision are clinical variables not captured in gene expression data. Most strikingly, GraphPath achieves an AUROC of 0.92 on prostate targeted molecular therapy prediction, the highest score in the entire benchmark, demonstrating that lateral co-regulation structure produces exceptional discriminative power when matched to a cohort with a narrow targetable driver programme, even under conditions of extreme class imbalance at only 11\% positive prevalence. --- ### Contract2Tool: Learning Preconditions and Effects for Reliable Tool-Augmented LLM Agents Authors: Rahul Suresh Babu, Laxmipriya Ganesh Iyer Published: 2026-06-05 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2606.07904v1 Tool-augmented large language model agents increasingly rely on external APIs, but standard tool schemas describe how to call a tool, not when the tool is causally appropriate or what task state it produces. Causal tool filtering addresses this gap by using lightweight contracts that specify each tool's preconditions, effects, risk level, and cost. However, manually writing and maintaining such contracts does not scale to large or changing tool ecosystems. We introduce Contract2Tool, a framework for inferring tool contracts from metadata, schemas, documentation, and execution traces. Contract2Tool converts observable tool evidence into normalized symbolic contracts that can be evaluated intrinsically and deployed inside downstream causal tool filtering. We evaluate learned contracts against gold preconditions, effects, and risk labels, and measure their downstream utility on multi-step agent tasks. Our results show that hybrid documentation-and-trace evidence produces contracts accurate enough to preserve most of the reliability and efficiency benefits of gold contracts. Learned-contract CMTF achieves 0.980 downstream success, close to 0.990 for gold-contract CMTF, while reducing visible tools from 100 to 1 and reducing average token usage from 26,172 to 2,528 relative to all-tools exposure. These results suggest that learned contracts can provide a scalable contract layer between tool schemas and reliable agent execution. --- ### Temporal Coverage over Density: Parsimonious Training-Set Design for ML Climate Downscaling Authors: Karandeep Singh, Stefan Rahimi, Chad W. Thackeray, Stephen Cropper, Alex Hall Published: 2026-06-05 Categories: cs.LG, cs.CE arXiv: https://arxiv.org/abs/2606.07898v1 High-resolution regional climate simulations provide critical information for climate impacts assessments but remain computationally expensive, motivating the development of machine-learning downscalers and emulators. A key challenge is determining how limited high-resolution simulations should be distributed across a changing climate trajectory to capture both forced climate response and internal variability. Using the CESM2 Large Ensemble over the western United States, we compare three training-year selection strategies under fixed data budgets: a contiguous block of historical years, years drawn from both the beginning and end of the simulation period, and years distributed throughout the full climate trajectory. Including both historical and future years consistently outperforms training on historical years alone, demonstrating the importance of exposing downscaling models to climate states outside the historical record and highlighting limitations of stationarity assumptions common in statistical downscaling. Training on years distributed throughout the full climate trajectory performs best overall, indicating that broad sampling of internal variability provides additional information beyond exposure to the forced climate response alone. Models trained on temporally distributed subsets more successfully reproduce variability in unseen ensemble members while retaining strong performance across a wide range of climate diagnostics. Even when trained on only one-tenth of the available high-resolution years, temporally distributed models remain highly competitive with full-data training. These results suggest that, under fixed computational budgets, broad sampling of climate states is more valuable than temporal continuity when allocating scarce high-resolution simulations. The findings provide practical guidance for regional climate downscaling and large-ensemble projection workflows. --- ### Pander Score: A Continuous Measure of Sycophancy as Epistemic Deference Authors: Alejandro Botas, Paul de Font-Reaulx, Luke Hewitt Published: 2026-06-05 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2606.07897v2 Current AI models frequently exhibit epistemic sycophancy, endorsing claims to agree with a user. Existing evaluations typically measure this either by assessing what it takes to make a model shift a binary endorsement or by eliciting an explicit probability in a proposition. However, much user-facing sycophantic behavior is demonstrated through shifts in graded support expressed through ordinary language. We propose the Pander Score: a continuous score representing how sensitive the support expressed in a model's output is to the attitude expressed in a user's prompt. To generate the Pander Score, we provide a new protocol for estimating probabilities from natural language outputs, using LLMs-as-judges validated for consistency and correlation to human judgment. We deploy it on a new curated dataset of 349 propositions across diverse topics and over 11,000 prompts varying in user attitude, testing 18 models. Models pander to sharply different degrees. Among current flagship models, Z.ai's GLM-5.2 panders the most and Claude Fable 5 the least, with other models in between. When we run the test on instructional rather than conversational prompts, every model becomes substantially more likely to go along with claims they would push back against in conversation. We release the Pander Score as an easy-to-update benchmark and measurement pipeline for output-level sycophancy evaluation. --- ### The AI Epistemic Deference Index: A Continuous Measure of Sycophancy Authors: Alejandro Botas, Paul de Font-Reaulx, Luke Hewitt Published: 2026-06-05 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2606.07897v1 Current AI models frequently exhibit epistemic sycophancy, endorsing claims to agree with a user. Existing evaluations typically measure this either by assessing what it takes to make a model shift a binary endorsement or by eliciting an explicit probability in a proposition. However, much user-facing sycophantic behavior is demonstrated through shifts in graded support expressed through ordinary language. We propose the AI Epistemic Deference Index (AEDI): a continuous, unidimensional score representing how sensitive the support expressed in a model's output is to the attitude expressed in a user's prompt. To generate AEDI, we provide a new protocol for estimating probabilities from natural language outputs, using LLMs-as-judges validated for consistency and correlation to human judgment. We deploy it on a new curated database of 500 propositions across diverse topics and 16,000 prompts varying in user attitude, testing eight prominent models. Every model exhibits substantial deference, though with large and systematic differences across providers, with Claude models demonstrating the least, and Grok and Gemini models the most. The effect is amplified in prompts requesting a written artifact, and concentrated on propositions where models hold weaker priors. We release AEDI as an easy-to-update benchmark and measurement pipeline for output-level sycophancy evaluation. --- ### Beyond the Thin-Layer Limit: Differentiable Volumetric Training for Visible-Range Diffractive Neural Networks Authors: Dineth Jayakody, Dushan N. Wadduwage Published: 2026-06-05 Categories: physics.optics, cs.CV arXiv: https://arxiv.org/abs/2606.07896v1 Diffractive deep neural networks (D2NNs) promise miniaturized, power-efficient, light-speed optical front-ends for machine vision, yet the most mature demonstrations remain in the terahertz regime, built from readily fabricated millimeter-scale neurons. Translating D2NNs to the visible range, where nearly all vision pipelines operate, was long blamed on the difficulty of fabricating nanoscale neurons; but even after recent advances removed that barrier, visible-range D2NNs matching their terahertz counterparts remain out of reach. We identify the true obstacle as the thin-layer approximation underlying nearly all D2NN training, which treats each diffractive layer as an infinitely thin mask. It fails not because of the short wavelength, as is commonly assumed, but because the low-refractive-index materials (n approximately 1.3-1.5) used at visible wavelengths require relief structures thick enough that intra-layer diffraction and phase accumulation become significant. To overcome this, we introduce a differentiable beam-propagation ($\partial$BPM) layer that models each element as a finite-thickness volume and propagates light through it during training, keeping the fabrication-compatible height map end-to-end trainable without full-wave simulation in the loop. Across MNIST, Fashion-MNIST, and CIFAR-100 classification and imaging, $\partial$BPM training substantially reduces the design-to-device mismatch, and full-wave FDTD validation raises classification accuracy from 50% to 90% without re-optimization. The $\partial$BPM layer thus offers a scalable, physics-aware bridge between efficient optical neural-network optimization and fabrication-consistent diffractive design. ---