arXiv:2605.16738v1 Announce Type: cross Abstract: The rapid advancement of Vehicle-to-Everything (V2X) communications and Tele-Operated Driving (ToD) demands ultra-low-latency, 8K60 video telemetry. However, deploying modern hardware at the vehicular edge is frequently hindered by supply chain constraints, high power budgets, and growing e-waste concerns. This paper investigates a highly sustainable alternative: repurposing legacy NVIDIA Pascal GPUs for real-time 8K HEVC edge encoding. We demonstrate that triggering 2-Way Split Frame Encoding (SFE) on dual-NVENC GP104 and GP102 silicon successfully unlocks real-time 8K60 throughput with a negligible Rate-Distortion penalty of under 1%. Crucially, our micro-architectural analysis reveals that smaller GPU dies significantly outperform larger flagship models in both raw throughput and energy efficiency. Because fixed-function encoding forces general-purpose Streaming Multiprocessor (SM) cores to sustain maximum frequencies while remaining idle, GPUs with fewer CUDA cores waste drastically less power. While benchmarking against the state-of-the-art RTX PRO 6000 Blackwell highlights a generational compression efficiency gap, Pascal's functional HEVC architecture and native lack of B-frames align perfectly with ultra-low-latency V2X pipelines. Ultimately, repurposed mid-range Pascal GPUs present a highly capable, cost-effective, and e-waste mitigating solution for modern Intelligent Transportation Systems.
Science Journals
arXiv:2605.16694v1 Announce Type: cross Abstract: Open microcavities provide a powerful platform for studying cavity quantum electrodynamics in solid-state systems. However, operating open microcavities at cryogenic temperatures, as required for many solid-state quantum emitters, typically demands bulky and cryostat-specific vibration-mitigation setups. Here we report a compact, robust, and tunable mechanical host for an open microcavity. The complete mechanical assembly fits within a footprint of $1'' \times 1'' \times 0.5''$. Using this mechanical host, we observe no vibration-induced cavity broadening for an open microcavity with finesse exceeding 1,000 without cryostat customization or active locking. The assembly also enables in situ tuning of the cavity resonance over 3 nm, and the resonance of the same cavity remains within this range across multiple cooldowns. To further showcase the capability of this assembly, we demonstrate coupling between an InGaAs quantum dot and an open microcavity with a cooperativity exceeding unity. This platform provides a versatile testbed for fundamental cavity quantum electrodynamics and a scalable route to portable quantum light sources and spin-photon interfaces for quantum repeaters, quantum networks, and photonic quantum computing.
arXiv:2605.14787v2 Announce Type: replace Abstract: Composed Image Retrieval (CIR) is a multimodal retrieval task where a query consists of a reference image and a textual modification, and the goal is to retrieve a target image satisfying both. In principle, strong performance on CIR benchmarks is assumed to require multimodal composition, i.e., combining complementary information from reference image and textual modification. In this work, we show that this assumption does not always hold. Across four widely used CIR benchmarks and eleven Generalist Multimodal Embedding models, a large fraction of queries can be solved using a single modality (from 32.2% to 83.6%), revealing pervasive unimodal shortcuts. Thus, high CIR performance can arise from unimodal signals rather than true multimodal composition. To better understand this issue, we perform a two-stage audit. First, we identify shortcut-solvable queries through cross-model analysis. Second, we conduct human validation on 4,741 shortcut-free queries, of which only 1,689 are well-formed, with common issues including ambiguous edits and mismatched targets. Re-evaluating models on this validated subset reveals qualitatively different behaviour: queries can no longer be solved with a single modality, and successful retrieval requires combining both inputs. While accuracy decreases, reliance on multimodal information increases. Overall, current CIR benchmarks conflate shortcut-solvable, noisy, and genuinely compositional queries, leading to an overestimation of model capability in multimodal composition.
arXiv:2605.00264v2 Announce Type: replace Abstract: Offline multi-agent reinforcement learning in general-sum settings is challenged by the distribution shift between logged datasets and target equilibrium policies. While standard methods rely on manual pessimistic penalties, we demonstrate that KL regularization suffices to stabilize learning and achieve equilibrium recovery. We propose General-sum Anchored Nash Equilibrium (GANE), which recovers regularized Nash equilibria at an accelerated statistical rate of $\widetilde{O}(1/n)$. For computational tractability, we develop General-sum Anchored Mirror Descent (GAMD), an iterative algorithm converging to a Coarse Correlated Equilibrium at the standard rate of $\widetilde{O}(1/\sqrt{n}+1/T)$. These results establish KL regularization as a standalone mechanism for pessimism-free offline learning that achieves equivalent or accelerated rates in multi-player general-sum games.
arXiv:2604.23538v3 Announce Type: replace Abstract: In the digital era, personal data, particularly sensitive identifiers such as the Social Security Number and National Identification Number, has become a highly valuable asset, raising significant concerns regarding privacy and security. This study examines the risks associated with the online exposure of the Thai National Identification Number, a key element of identity verification in both governmental and commercial transactions. Similar to the Social Security Number in the United States, this unique identifier is crucial for various legal, financial, and welfare-related activities. However, the increasing digitization of personal records has heightened its vulnerability to unauthorized access and misuse, particularly through search engines that inadvertently index sensitive information. This research identifies publicly exposed Thai National Identification Numbers across major search engines, assessing the potential threats to individual privacy and national security. The study reveals the exposure of over 1.2 million unique National Identification Numbers, along with other highly sensitive personal data, e.g., addresses, contact details, employment status, disability status, and health information. Notably, the analysis indicates that a significant majority of these exposures originate from the Thai government sector websites, highlighting critical vulnerabilities in public data management practices. This widespread exposure not only increases the risk of identity theft and financial fraud but also underscores the urgent need for enhanced cybersecurity measures, stricter regulatory enforcement, and improved data governance within government agencies to prevent future breaches. Addressing these issues is essential to safeguarding citizens' personal information and ensuring compliance with Thailand's data protection laws in an increasingly digitized world.
arXiv:2604.06579v2 Announce Type: replace Abstract: The Ethereum state database uses Merkle Patricia Trie (MPT), which suffers from large witness proof sizes and high storage overhead. Verkle Tries have been proposed as a replacement, offering witness proofs below 150 bytes through vector commitments and Inner Product Argument aggregation. However, deploying a Verkle Trie in a high-throughput, short block-time blockchain such as Sonic, which produces a block every 300 milliseconds, introduces substantial engineering challenges related to storage efficiency, commitment computation costs, and the need to serve both live and historical state queries in real time. We present SonicDB S6, a production-grade Rust Verkle Trie database for the Sonic blockchain, which leverages its non-forking property to enable aggressive storage optimizations. Occupancy-aware node specializations, selected via an $\mathcal{O}(k n^2)$ dynamic program, reduce live storage by 97.8\%. Delta nodes that record only changed slots reduce archive storage by 95\%. Batched updates, multi-threaded commitment computation, and homomorphic Pedersen caching yield $3.2\times$ higher throughput than a persistent Geth Verkle baseline while sustaining production block-rate performance.
arXiv:2603.25723v2 Announce Type: replace Abstract: Agent performance is strongly shaped by the surrounding harness: the external execution system around a model that organizes a task run. Yet this logic is usually buried in tightly coupled controller code, which makes harnesses hard to inspect, compare, transfer, and ablate. This paper asks whether the reusable design pattern of an agent harness can be represented as an executable natural-language object. We introduce Natural-Language Agent Harnesses (NLAHs), editable documents that describe run-level harness policy, and Intelligent Harness Runtime (IHR), a shared runtime that interprets these documents into agent calls, handoffs, state updates, validation gates, and artifact contracts. Across coding, terminal-use, and computer-use benchmarks, IHR-executed NLAHs achieve comparable task outcomes to code and prompted realizations, while exposing much shorter static harness policies. Module ablations further show that explicit harness modules are analyzable. These results suggest that agent harnesses can be turned from incidental glue around models into scientific representation objects.
arXiv:2605.18466v1 Announce Type: new Abstract: Segmenting vocal tract articulators in real-time MRI (rtMRI) is a challenging dynamic image segmentation problem characterized by low contrast, rapid motion, and limited spatial resolution. However, while rtMRI acquisitions may provide synchronized acoustic signals, existing methods discard this information, and the few multimodal approaches that incorporate audio cannot be deployed when audio is unavailable. We propose a three-stage framework that leverages acoustic and phonological supervision during training while requiring only the rtMRI image at inference: phonological representations are converted into spatial bounding-box priors for articulator localization, visual and acoustic encoders are aligned via dual-level cross-modal contrastive pretraining, and the learned representations are fused through a cross-attention decoder, effectively transferring multimodal knowledge into a single-modality inference pipeline. Evaluated on 75-Speaker~Annot-16 and USC-TIMIT datasets, our method outperforms existing unimodal and multimodal methods, demonstrating that multimodal supervision provides transferable benefits for precise and clinically deployable vocal tract segmentation.
arXiv:2605.18423v1 Announce Type: new Abstract: As autonomous systems grow more advanced, objective metrics to evaluate their ethical and legal compliance are critical for informing end users of their limitations and ensuring accountability of those who misuse them. Current ethical embodied AI frameworks remain mostly qualitative, focusing on system design (through safety guardrails or targeted red teaming), and the realized guardrails often directly disallow unsafe behavior without providing the user with an override or interpretable reason. Instead, there is a need for computable metrics through rigorous testing that allow a user to determine the applicability of the system to the task. To address this gap, we introduce the Reference Ethical Benchmark for Autonomy Readiness (REBAR), a quantitative test and evaluation framework for autonomous systems. REBAR maps operating metrics into a computable Autonomy Readiness Level (ARL) rubric that can quantify ethical performance. Key innovations of the framework include a neuro-symbolic Large Language Model (LLM) approach to calculate and explain the ethical difficulty of scenarios, LLM-driven at-scale generation of test instances, and a versatile, photorealistic simulation environment. By evaluating white-box autonomy solutions through this rigorous testing pipeline, REBAR delivers an objective and repeatable benchmark score, bridging the gap between abstract principles and verifiable, accountable autonomy.
arXiv:2602.17831v2 Announce Type: replace Abstract: Evaluating the reasoning capabilities of Large Language Models is increasingly challenging as models improve. Human curation of hard questions is highly expensive, especially in recent benchmarks using PhD-level domain knowledge to challenge the most capable models. Even then, there is always a concern about whether these questions test genuine reasoning or if similar problems have been seen during training. Here, we take inspiration from 16th-century mathematical duels to design The Token Games (TTG): an evaluation framework where models challenge each other by creating their own puzzles. We leverage the format of Programming Puzzles - given a function that returns a boolean, find inputs that make it return True - to flexibly represent problems and enable verifying solutions. Using results from pairwise duels, we then compute Elo ratings, allowing us to compare models relative to each other. We evaluate 10 frontier models on TTG, and closely match the ranking from existing benchmarks such as Humanity's Last Exam, spending less than $200 USD and without involving any human effort in creating puzzles. We also find that creating good puzzles is still a highly challenging task for current models. Overall, our work suggests new paradigms for evaluating reasoning that avoid saturation by design, and that allow testing models for other skills like creativity and task creation alongside problem solving.
arXiv:2602.17684v2 Announce Type: replace Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based feedback from unit tests, but its scalability is fundamentally constrained by the availability and reliability of high-quality test cases. We propose CodeScaler, a reward model designed to scale both reinforcement learning training and test-time inference for code generation. CodeScaler is trained on carefully curated preference data derived from verified code problems and incorporates syntax-aware code extraction and validity-preserving reward shaping to ensure stable and robust optimization. Across four coding benchmarks, CodeScaler consistently outperforms execution-based RL by +1.55 points on Qwen3-8B-Base and +4.23 points on Qwen3-14B-Base. By further scaling to 44K problems with additional synthetic data, CodeScaler yields +14.64 points improvement over the base model without requiring any test cases. At inference time, CodeScaler serves as an effective test-time scaling method, achieving performance comparable to unit test approaches while providing a 10-fold reduction in latency. Moreover, CodeScaler surpasses existing reward models on RM-Bench not only in the code domain (+3.3 points), but also in general and reasoning domains (+2.7 points on average).
arXiv:2605.18387v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) and Graph Transformers (GTs) are now a fundamental paradigm for graph learning, combining the representation-learning capabilities of deep models with the sample efficiency induced by their inductive biases. Despite their effectiveness, a large body of work has shown that these models still face fundamental limitations in tasks that require capturing correlations between distant regions of a graph. To address this issue, we introduce Graph Hierarchical Recurrence (GHR), a novel framework that operates jointly on the input graph and on a hierarchical abstraction obtained through pooling. We also show that the limitations of existing models are even more pronounced in out-of-range generalization, where test instances involve interactions over distances longer than those observed during training. By contrast, despite its simple design, GHR provides three key advantages: strong performance on long-range dependencies, improved out-of-range generalization, and high parameter efficiency. To corroborate these claims, we show that across a broad set of long-range benchmarks, GHR consistently outperforms existing graph models while using as little as 1% of the parameters of current state-of-the-art models. These results suggest a complementary direction to the current trend of scaling architectures to obtain graph foundation models, indicating that increased model capacity alone may not be sufficient for generalization.
arXiv:2602.12871v2 Announce Type: replace Abstract: Large language models (LLMs) have attracted growing interest as supportive tools for psychiatric assessment and clinical decision support. However, existing mental health benchmarks largely rely on social media data or supportive dialogue settings, limiting their ability to assess whether models can apply formal diagnostic criteria and differential diagnostic rules. In this paper, we introduce MentalBench, a benchmark for evaluating whether LLMs can make DSM-grounded psychiatric diagnostic decisions under varying levels of clinical ambiguity. At the core of MentalBench is MentalKG, a psychiatrist-built and validated knowledge graph encoding DSM-5 diagnostic criteria and differential diagnostic rules for 23 psychiatric disorders. Using MentalKG as an expert-curated logical backbone, we generate 24,750 synthetic clinical cases that systematically vary in information completeness and diagnostic complexity, enabling DSM-grounded evaluation. Our experiments show that although state-of-the-art LLMs perform well on noise-free queries that probe DSM-5 knowledge, they struggle to calibrate their confidence when distinguishing between disorders with overlapping symptoms. These findings raise concerns about the reliability of LLMs as psychiatric decision-support tools and highlight the need for more evaluation that reflects the diverse challenges in real-world psychiatric diagnosis.
arXiv:2602.05114v2 Announce Type: replace Abstract: Traditional synchronous STEM assessments face growing challenges including accessibility barriers, security concerns from resource-sharing platforms, and limited comparability across institutions. We present a framework for generating and evaluating large-scale isomorphic physics problem banks using Generative AI to enable asynchronous, multi-attempt assessments. Isomorphic problems test identical concepts through varied surface features and contexts, providing richer variation than conventional parameterized questions while maintaining consistent difficulty. Our generation framework employs prompt chaining and tool use to achieve precise control over structural variations (numeric values, spatial relations) alongside diverse contextual variations. For pre-deployment validation, we evaluate generated items using 17 open-source language models (LMs) (0.6B-32B) and compare against actual student performance (N>200) across three midterm exams. Results show that 73% of deployed banks achieve statistically homogeneous difficulty, and LMs pattern correlate strongly with student performance (Pearson's $\rho$ up to 0.594). Additionally, LMs successfully identify problematic variants, such as ambiguous problem texts. Model scale also proves critical for effective validation, where extremely small (<4B) and large (>14B) models exhibit floor and ceiling effects respectively, making mid-sized models optimal for detecting difficulty outliers.
arXiv:2605.18314v1 Announce Type: new Abstract: The emergence of Ambient IoT signals a paradigm shift toward massive batteryless networking. However, the absence of an agile physical layer substrate remains a fundamental barrier to research and standardization. Current testbeds are hindered by decoupled radio paths, high static power, and cumbersome control methods, which stifle rapid protocol prototyping. In this paper, we present Janus, the first hybrid active-passive configurable radio architected for agile Ambient IoT networking. Janus introduces a parameterized architecture that unifies passive and active transmission into a single RF front end, abstracting complex physical layer behaviors into concise parameters. This design enables a system-level control plane for dynamic mode transitions and an energy management plane for fine-grained harvesting across multiple sources. We implement a compact PCB prototype and evaluate its performance across diverse protocol landscapes, including 3GPP A-IoT, IEEE 802.11 AMP, and Bluetooth SIG. Our experimental results demonstrate that Janus achieves communication performance on par with dedicated radios while significantly reducing configuration overhead. Ultimately, Janus serves as a versatile enabler for validating emerging protocols and accelerating the standardization of next-generation low-power networks.
arXiv:2605.18261v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has demonstrated promising potential to enhance the reasoning capabilities of large language models (LLMs) in domains such as mathematics and coding. However, its applications on knowledge-intensive domains have not been effectively explored due to the scarcity of high-quality verifiable data. Furthermore, current RLVR focuses solely on the correctness of final answers, leading to the limitations of flawed reasoning and sparse reward signals. In this work, we propose Knowledge-to-Verification (K2V), a framework that extends RLVR to knowledge-intensive domains through automated verifiable data synthesis, while enabling verification of the LLM's reasoning process. Extensive experiments demonstrate that K2V enhances the reasoning of LLM in knowledge-intensive domains without significantly compromising the model's general capabilities. This study also suggests that integrating automated data synthesis with reasoning verification is a promising direction to enhance model capabilities in these broader domains. Code is available at https://github.com/SeedScientist/K2V.
arXiv:2601.21170v3 Announce Type: replace Abstract: Emergent phenomena -- onset of epileptic seizures, sudden customer churn, or pandemic outbreaks -- often arise from hidden causal interactions in complex systems. We propose a machine learning method for their early detection that addresses a core challenge: unveiling and harnessing a system's latent causal structure despite the data-generating process being unknown and partially observed. The method learns an optimal feature representation from a one-parameter family of estimators -- powers of the empirical covariance or precision matrix -- offering a principled way to tune in to the underlying structure driving the emergence of critical events. A supervised learning module then classifies the learned representation. We prove structural consistency of the family and demonstrate the empirical soundness of our approach on seizure detection and churn prediction, attaining competitive results in both. Beyond prediction, and toward explainability, we ascertain that the optimal covariance power exhibits evidence of good identifiability while capturing structural signatures, thus reconciling predictive performance with interpretable statistical structure.
arXiv:2602.10503v2 Announce Type: replace Abstract: Pretrained on large-scale and diverse datasets, VLA models demonstrate strong generalization and adaptability as general-purpose robotic policies. However, Supervised Fine-Tuning (SFT), which serves as the primary mechanism for adapting VLAs to downstream domains, requires substantial amounts of task-specific data and is prone to catastrophic forgetting. To address these limitations, we propose LifeLong-RFT, a simple yet effective Reinforcement Fine-Tuning (RFT) strategy for VLA models independent of online environmental feedback and pre-trained reward models. By integrating chunking-level on-policy reinforcement learning with the proposed multi-dimensional process reward mechanism, LifeLong-RFT quantifies the heterogeneous contributions of intermediate action chunks across three dimensions to facilitate policy optimization. Specifically, (1) the Quantized Action Consistency Reward (QACR) ensures accurate action prediction within the discrete action space; (2) the Continuous Trajectory Alignment Reward (CTAR) aligns decoded continuous action chunks with reference trajectories to ensure precise control; (3) the Format Compliance Reward (FCR) guarantees the structural validity of outputs. Comprehensive experiments across SimplerEnv, LIBERO, and real-world tasks demonstrate that LifeLong-RFT exhibits strong performance in multi-task learning. Furthermore, for continual learning on the LIBERO benchmark, our method achieves a 22% gain in average success rate over SFT, while effectively adapting to new tasks using only 20% of the training data. Overall, our method provides a promising post-training paradigm for VLAs. The project page is available at .
arXiv:2601.19667v3 Announce Type: replace Abstract: We present SynCABEL (Synthetic Contextualized Augmentation for Biomedical Entity Linking), a framework that addresses a central bottleneck in supervised biomedical entity linking (BEL): the scarcity of expert-annotated training data. SynCABEL leverages large language models to generate context-rich synthetic training examples for all candidate concepts in a target knowledge base, providing broad supervision without manual annotation. We demonstrate that SynCABEL, when combined with decoder-only models and guided inference, establishes new state-of-the-art results across three widely used multilingual benchmarks: MedMentions for English, QUAERO for French, and SPACCC for Spanish. Evaluating data efficiency, we show that SynCABEL reaches the performance of full human supervision using up to 60% less annotated data, substantially reducing reliance on labor-intensive and costly expert labeling. Finally, acknowledging that standard evaluation based on exact code matching often underestimates clinically valid predictions due to ontology redundancy, we introduce an LLM-as-a-judge protocol. This analysis reveals that SynCABEL significantly improves the rate of clinically valid predictions. Our synthetic datasets, models, and code are released to support reproducibility and future research.
arXiv:2605.18221v1 Announce Type: new Abstract: Real-time magnetic resonance imaging (rtMRI) of speech production enables non-invasive visualization of dynamic vocal-tract motion and is valuable for speech science and clinical assessment. However, rtMRI is fundamentally constrained by trade-offs among spatial resolution, temporal resolution, and acquisition speed, often leading to undersampled k-space measurements and degraded reconstructions. We propose SIREM, a speech-informed MRI reconstruction framework that uses synchronized speech as a cross-modal prior. The central idea is that vocal-tract configurations during speech are correlated with the produced acoustics, making part of the image content predictable from audio. SIREM models each frame as a fusion of an audio-driven component and an MRI-driven component through a spatial weighting map. The audio branch predicts articulator-related structure from speech, while the MRI branch reconstructs complementary content from measured k-space data. We further introduce a learnable soft weighting profile over spiral arms, enabling a differentiable study of how k-space arm usage interacts with speech-informed fusion. This yields a unified multimodal formulation that combines audio-driven prediction, MRI reconstruction, and sampling adaptation. We evaluate SIREM on the USC speech rtMRI benchmark against standard baselines, including gridding, wavelet-based compressed sensing, and total variation. SIREM introduces a speech-informed reconstruction paradigm that operates in a substantially higher-throughput regime than iterative methods while preserving anatomically plausible vocal-tract structure. These results establish an initial benchmark for multimodal speech-informed rtMRI reconstruction and highlight the potential of synchronized speech as an auxiliary prior for fast reconstruction. The source code is available at https://github.com/mdhasanai/SIREM
arXiv:2601.17887v2 Announce Type: replace Abstract: Long-term memory enables large language model (LLM) agents to support personalized and sustained interactions. However, most work on personalized agents prioritizes utility and user experience, treating memory as a neutral component and largely overlooking its safety implications. In this paper, we reveal intent legitimation, a previously underexplored safety failure in personalized agents, where benign personal memories bias intent inference and cause models to legitimize inherently harmful queries. To study this phenomenon, we introduce PS-Bench, a benchmark designed to identify and quantify intent legitimation in personalized interactions. Across multiple memory-augmented agent frameworks and base LLMs, personalization increases attack success rates by 15.8\%--243.7\% relative to stateless baselines. We further provide mechanistic evidence for intent legitimation from internal representations space, and propose a lightweight detection-reflection method that effectively reduces safety degradation. Overall, our work provides the first systematic exploration and evaluation of intent legitimation as a safety failure mode that naturally arises from benign, real-world personalization, highlighting the importance of assessing safety under long-term personal context. Our code is available at: https://github.com/MuyuenLP/PS-Bench. WARNING: This paper may contain harmful content.
arXiv:2605.18168v1 Announce Type: new Abstract: The integration of audio modality into Large Audio Language Models (LALMs) significantly expands their attack surface. Existing jailbreak paradigms predominantly treat audio as a carrier for malicious payloads, relying on semantic optimization, acoustic parameter control, or additive perturbation to embed harmful content into the audio signal. In this work, we challenge this necessity and propose a new paradigm in which the role of audio shifts from content injection to safety alignment interference. We reveal that LALM safety alignment can be compromised solely by specific Acoustic Latent Semantics (ALS), the underlying paralinguistic features intrinsic to the priors of audio generative models. Distinct from previous works that leverage explicit acoustic parameters to merely style malicious audio, we demonstrate that interference audio, benign in content but infused with specific ALS, can serve as a universal jailbreak trigger. Leveraging this insight, we propose the Acoustic Interference Attack (AIA), which decouples the attack payload from the audio. Specifically, AIA employs a set of universal, instruction-neutral interference audio, enabling standard malicious text queries to bypass safety alignment without instance-specific optimization. Extensive experiments on 10 LALMs across five datasets demonstrate that AIA achieves the state-of-the-art attack success rate. Furthermore, our interpretability analysis uncovers the inference path drift induced by AIA and identifies the inherent effective patterns within ALS, revealing the fundamental vulnerability of cross-modal alignment in LALMs.
arXiv:2512.08089v2 Announce Type: replace Abstract: Real-time, energy-efficient inference on edge devices is essential for graph classification across a range of applications. Hyperdimensional Computing (HDC) is a brain-inspired computing paradigm that encodes input features into low-precision, high-dimensional vectors with simple element-wise operations, making it well-suited for resource-constrained edge platforms. Recent work enhances HDC accuracy for graph classification via Nystr\"om kernel approximations. Edge acceleration of such methods faces several challenges: (i) redundancy among (landmark) samples selected via uniform sampling, (ii) storing the Nystr\"om projection matrix under limited on-chip memory, (iii) expensive, contention-prone codebook lookups, and (iv) load imbalance due to irregular sparsity in SpMV. To address these challenges, we propose HyperX, the first end-to-end FPGA accelerator for Nystr\"om-based HDC graph classification at the edge. HyperX integrates four key optimizations: (i) a hybrid landmark selection strategy combining uniform sampling with determinantal point processes (DPPs) to reduce redundancy while improving accuracy; (ii) a streaming architecture for Nystr\"om projection matrix maximizing external memory bandwidth utilization; (iii) a minimal-perfect-hash lookup engine enabling $O(1)$ key-to-index mapping; and (iv) sparsity-aware SpMV engines with static load balancing. Implemented on an AMD Zynq UltraScale+ (ZCU104) FPGA, HyperX achieves $6.85\times$ ($4.32\times$) speedup and $169\times$ ($314\times$) energy efficiency gains over optimized CPU (GPU) baselines, while improving classification accuracy by $3.4\%$ on average across TUDataset benchmarks, a widely used standard for graph classification.
arXiv:2605.18163v1 Announce Type: new Abstract: Hallucination correction is not a one-direction problem. We show that intermediate layers are neither uniformly more truthful than final layers nor uniformly less trustworthy. Yet hallucination reduction is usually instantiated through one fixed intervention form: contrast one layer against another, steer along a truthfulness direction, or defer to external evidence. This framing is structurally incomplete. Cross-layer factual evidence does not evolve uniformly: in some failures truthful support is present internally and later suppressed, whereas in others candidate competition remains genuinely multi-directional across depth, so no single signed scalar family is generally sufficient. We introduce Trajectory Correction from Cross-layer Evidence for Hallucination Reduction (TRACE), a deterministic, training-free algorithm which corrects hallucinations at inference time by deriving both the corrective layer and the appropriate correction operator from each input's cross-layer candidate trajectory inside the LLM's own forward pass. Under one frozen hyperparameter setting, TRACE selects among scalar reversal, earlier-state recovery, and candidate-space correction using only model-internal evidence. Evaluated as a single universal algorithm across 15 models, 8 model families, and 3 factuality benchmarks, TRACE improves every evaluation cell, yielding mean gains of +12.26 MC1 points and +8.65 MC2-style points with no regressions, with gains reaching +47.20 MC1 and +43.38 MC2-style points. The method uses no labels, retrieval, pretraining, finetuning, or per-model calibration.
arXiv:2605.18144v1 Announce Type: new Abstract: Nanomedicine research spans delivery chemistry, immunology, imaging, biomaterials, and disease-specific translational science, yet its conceptual design space remains fragmented across a large and heterogeneous literature. To date, artificial intelligence in nanomedicine has focused primarily on property prediction and formulation optimization, with much less attention to evidence-grounded discovery support at the level of research direction selection. We introduce pArticleMap, a literature-mapping and research-hypothesis-generation system that combines article embeddings, similarity-graph analysis, sparse frontier extraction, structured evidence-pack retrieval, and an audited large-language-model (LLM) workflow for grounded ideation. Rather than forecasting future concept co-occurrence, pArticleMap targets low-density article-level bridge regions and cluster interfaces, then generates and scores citation-grounded hypotheses with large language models in an agentic setup. We evaluate the system with a retrospective realization benchmark (generate later literature under a historical cutoff) and a blinded human reader assessment layer across cue-conditioned nanomedicine tasks. Across 4 selected retrospective bundles, pArticleMap generated ideas and selected task-retained hypotheses (winner ideas) under the benchmark protocol. For task-level retained hypotheses, a pooled gold recovery rate of 10.8% was obtained, with a recall@10 of 15.9% and a future-neighborhood rate of 61.0%, indicating that the system often reached the correct forward-looking neighborhood (paper ideas) even without exact paper-level recovery. Human-agent agreement is modest overall, indicating that internal scoring is useful as a support signal but does not replace expert judgment. These results position pArticleMap as a conservative, evidence-grounded research assistant for nanomedicine.