Artificial Intelligence
Inference-Time Projection for Physically Valid Biomolecular Diffusion Models
Qurat-ul-ain, Yee Whye Teh, Charlotte M. Deane et al. (+1 more)
AlphaFold 3-style cofolding models predict biomolecular complexes with high structural accuracy, yet a large fraction of their outputs are physically invalid: chains overlap at interfaces, ligand bond lengths and angles are distorted, rings are non-planar, and stereocentres are inverted. Current approaches either steer the sampler with physics-informed potentials, which multiplies sampling cost and
memory overhead making inference impossible on large complexes, or finetune the model, costing time and tying the fix to one architecture. We observe that, unlike structural accuracy, physical validity is fully verifiable at inference time from quantities the sampler already holds. We therefore treat physical validity as a constrained inference problem and introduce two closed-form projection operators applied to the
diffusion model's denoised clean-coordinate estimate, $\hat{x}_0$: an inter-chain van der Waals projection that pushes apart the most severely clashing atom pairs, and a ligand distance-geometry projection that restores bond lengths, angles, internal contacts, planarity and chirality. Both operators are local, sparse and displacement-capped, require no network evaluations, gradients or importance sampling, and leave the denoiser and its weights untouched, so they can be dropped into any AF3-style sampler without retraining. Applied to two independently developed models, Boltz-2 and OpenFold-3, across five
benchmarks (CASP15, CASP16, the PoseBusters monomer and complex sets, and the Boltz physical-validity test set), our method recovers perfect physical validity while preserving structural-accuracy and ligand-placement metrics. These gains are achieved with negligible runtime and
memory overhead, providing a practical, model-agnostic route to physically valid all-atom structure prediction.
Read the full abstract ▾
All authors Qurat-ul-ain, Yee Whye Teh, Charlotte M. Deane, Matteo Cagiada
Artificial Intelligence
JIVEAdapter: A Multi-Task Additive Low-Rank Adapter via Joint and Individual Variation Explained (JIVE)
Sara Abdali and Pashmina Cameron
Parameter-efficient fine-tuning adapts pretrained models at a fraction of the cost of full fine-tuning, yet most low-rank adapters are single-task and represent each weight update multiplicatively, leaving no explicit account of what is shared across tasks and what is task-specific. We introduce JIVEAdapter, a multi-task "additive" low-rank adapter inspired by statistical Joint and Individual Variation Explained (JIVE). JIVEAdapter decomposes every weight update into a Joint structure shared across all tasks plus a per-task Individual structure, penalizes the Individual structures to be near-orthogonal to the Joint so shared and task-specific signal stay "interpretable" and separated, and allocates rank adaptively across a shared Joint pool and a per-task Individual pool. The Joint is learned once, jointly over a task group or incrementally, one task at a time, then frozen and reused as a prior for new tasks without retraining the shared part. On GLUE and SuperGLUE with DeBERTaV3-base, JIVEAdapter is competitive with strong single-task and multi-task low-rank baselines at a matched per-task effective rank, without extra modules such as MoE, and when a related held-in task exists its frozen Joint serves a held-out task by reusing that task's Individual with only a cheap per-direction scale, otherwise training a small new one.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Investigating Model Compression for Neural Machine Translation in the Biomedical Domain
Maria Zafar, Souhail Bakkali and Rejwanul Haque
Large-scale pretrained
transformer models have achieved state-of-the-art performance across diverse machine translation tasks, including multilingual settings. Knowledge
distillation has emerged as a sustainable approach for model compression, transferring knowledge from large teacher models to smaller, more efficient student models. Similarly, quantization, which reduces the numerical precision of model weights and activations (e.g., from 32-bit to 8-bit representations) is widely used to accelerate inference, enabling models to run several times faster during deployment. However, both techniques face limitations when applied to specialized domain data, particularly under low-resource conditions. In knowledge
distillation, the effectiveness of transfer is often constrained by the scarcity of domain-specific parallel data, while quantization can lead to performance degradation as bit precision decreases. In this work, we investigate the combined application of knowledge
distillation and quantization for French-to-English biomedical translation, a domain characterized by specialized terminology and limited parallel resources. We develop and compare multiple fine-tuning strategies to adapt compressed student models to this challenging setting. Our experiments demonstrate that a collaboratively distilled and quantized student model achieves a 69% reduction in size, a 98.21% increase in inference speed, and a 98.46% reduction in CO2 emissions compared to the original baseline all without sacrificing translation quality. These results indicate that jointly optimized compression techniques can yield efficient, high-performance models suitable for translation service providers operating under resource constraints.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.AR
An Empirical Fault Vulnerability Exploration of ReRAM-based Process-in-Memory CNN Accelerators
Aniseh Dorostkar, Hamed Farbeh and Hamid R. Zarandi
Resistive random-access
memory (ReRAM)-based Processing-in-
Memory (PIM) accelerator is a promising platform for processing massively
memory intensive
matrix-vector multiplications of neural networks in parallel domain, due to its capability of analog computation, ultra-high density, near-zero leakage current, and non-
volatility. Despite many advantages, ReRAM-based accelerators are highly error-prone due to limitations of technology fabrication that lead to process variations and defects. These limitations degrade the accuracy of Deep Convolutional Neural Networks (Deep CNNs) running on PIM accelerators. While these CNNs accelerators are widely deployed in safety-critical systems, their vulnerability to fault is not well explored. In this paper, we have developed a fault injection framework to investigate the vulnerability of large-scale CNNs at both software- and hardware-level of inference phases. Faulty ReRAM devices are another reliability challenges due to significant degradation of classification accuracy when CNN parameters are mapped to the accelerators. To investigate this challenge, we map the CNN learning parameter to the ReRAM crossbar and inject faults into crossbar arrays. The proposed framework analyzes the impact of stuck-at high (SaH) and stuck-at low (SaL) fault models on different layers and locations of CNN learning parameters. By performing extensive fault injections, we illustrate that the vulnerability behavior of ReRAM-based PIM accelerator for CNNs is greatly impressible to the types and depth of layers, the location of the learning parameter in every layer, and the value and types of faults. Our observations show that different models have different vulnerabilities to faults. Specifically, we show that SaL further reduces classification accuracy than SaH.
Read the full abstract ▾
Artificial Intelligence
Offline AI Modules: Voice-First Offline Architecture, Hardware Reference Stack, Quantization and Benchmarking
Sunday Afariogun, Odunolaoluwa Jenrola and Zeinab Nezami
The Offline AI Modules workstream enables practical, low-power, and community-accessible deployment of voice-first AI systems that operate fully offline. Designed for African
language communities where
speech is the dominant mode of interaction and internet connectivity is unreliable or absent, the workstream delivers three reinforcing components: a modular voice-first offline architecture, a low-cost hardware reference bill of materials, and a reproducible quantization and a reproducible quantization and benchmarking pipeline for instruction-tuned
language models in the 2-5B parameter class. This paper presents the first end-to-end
benchmark evaluation of the stack across two hardware tiers: an NVIDIA Jetson Orin NX (TierB) and a Raspberry Pi5 (TierA). Three instruction-tuned models are evaluated across four quantization formats, assessed for deployment metrics (decode throughput, chat latency,
memory, power) and multilingual quality (topic classification accuracy on MasakhaNEWS across English, Hausa, Igbo, Nigerian Pidgin, and Yoruba; per-
language perplexity drift).
Speech recognition is evaluated using Ethio-ASR on Amharic and Oromo across both tiers. The principal finding is that Q4_K_M quantization represents the best size-to-quality trade-off for deployment on both tiers: gemma-4-E2B-it achieves 28.8t/s decode throughput and 89.2% topic classification accuracy at Q4_K_M on TierB, while all three models run within the 16GB
memory budget on TierA.
Read the full abstract ▾
Artificial Intelligence
Beyond Refusal Patterns: Safe-Role Internalization for Robust and Generalizable LLM Safety Alignment
Jinghao Pang, Jitai Hao, Qiang Huang et al. (+2 more)
Large
Language Models (LLMs) have achieved remarkable capabilities but remain vulnerable to jailbreak attacks that elicit harmful or unsafe outputs. Existing safety
alignment approaches, including Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), often require substantial attack-specific supervision and computational resources, while remaining susceptible to shallow safety
alignment and over-refusal. To address these challenges, we introduce SSRFT(Supervised Safe-Role Fine-Tuning), the first framework that reformulates safety
alignment as the internalization of a predefined safe role. SSRFT constructs a Safe-Role Question-Answer (SRQA)
dataset from psychometric questions, limited jailbreak
prompts, and a safe-role description. Role-consistent responses are synthesized, validated, and expanded into diverse scenarios, enabling models to internalize safety-oriented values and principles rather than explicit refusal patterns. Experiments across multiple Base and Instruct models show that SSRFT achieves more robust and generalizable safety
alignment than standard SFT. SSRFT shows substantially greater robustness to prefilling attacks and better generalization to unseen jailbreak domains, while reducing over-refusal on benign queries and preserving the model's general capabilities. These results establish safe-role internalization as an effective alternative to refusal-centric safety
alignment. Warning: This paper contains examples of harmful and toxic
language.
Read the full abstract ▾
All authors Jinghao Pang, Jitai Hao, Qiang Huang, Zhaochun Ren, Jun Yu
Artificial Intelligence
When to Rethink: Learning Multi-Perspective Self-Verification for Vision-Language Models
Ziquan Zhu, Hanruo Zhu, Si-Yuan Lu et al. (+10 more)
Vision-
language models (VLMs) have achieved strong performance in
multimodal reasoning, yet they remain prone to generating plausible but incorrect answers. Self-verification offers a practical way to improve answer reliability without relying on external judges, but existing methods typically depend on a single verification criterion or fixed
prompt, resulting in incomplete and unstable reliability estimates. We first systematically analyze how verifier capability and
prompt design affect verification performance. Our findings show that stronger verifiers provide more reliable judgments, while verification performance is highly sensitive to
prompt choice, with no single
prompt consistently dominating across tasks. Guided by these findings, we propose MOTIVE, a Multi-View Self-VerificatiOn wiTh RelIability-Guided SelectiVE Rethinking framework for reliable
multimodal reasoning. MOTIVE evaluates each candidate answer from complementary verification perspectives and learns a correctness-aligned reliability score through correctness-grounded multi-view verification learning. During inference, this score governs an accept-or-rethink decision, allowing reliable answers to be returned directly while uncertain ones trigger history-guided rethinking. Extensive experiments across diverse
multimodal benchmarks and VLM backbones demonstrate that MOTIVE consistently outperforms strong self-verification and self-correction baselines. Further results show that reliable verification improves accept-or-rethink decisions and reduces unnecessary
reasoning turns, enabling more reliable and efficient self-verification without an external judge.
Read the full abstract ▾
All authors Ziquan Zhu, Hanruo Zhu, Si-Yuan Lu, Morris Yu-Chao Huang, Yicheng Lin, Wei Han, Tianlong Chen, Mingyuan Wu, Hanchao Yu, Gaojie Jin, Lu Liu, Bo Sun, Tianjin Huang
Artificial Intelligence · Cross-listed from cs.CV
Anchor and Adapt: Asymmetric Prompt Adaptation for Few-Shot Industrial Anomaly Detection
Mengyang Zhao, Teng Fu, Haiyang Yu et al. (+3 more)
In few-shot industrial anomaly detection, the few normal target images provide no direct defect supervision, making anomaly
prompts difficult to learn from these samples alone. Some
vision-
language methods therefore use manually specified descriptions to supply explicit anomaly semantics. However, constructing these descriptions requires product-specific effort, and their effectiveness depends on
prompt selection. We propose Anchor and Adapt, a two-stage
prompt learning framework that separates the acquisition of anomaly semantics from adaptation to target normal appearance. Stage I learns transferable normal and abnormal anchors from annotated auxiliary data. Stage II keeps these anchors fixed and adapts an additional normal branch using the few target normal samples. The inherited and adapted normal branches jointly characterize target normality, with text-anchor regularization encouraging consistency with the generic normal prior and separation from the abnormal anchors. This design retains learned anomaly knowledge while reducing dependence on category-specific anomaly templates, without requiring synthetic anomaly generation. Cross-
dataset experiments between MVTec-AD and VisA under 1-, 2-, and 4-shot settings demonstrate competitive detection and localization performance. Controlled ablations assess the roles of transferred anchors, asymmetric adaptation, dual-normal representations, and anchor regularization.
Read the full abstract ▾
All authors Mengyang Zhao, Teng Fu, Haiyang Yu, Ke Niu, Bin Li, Xiangyang Xue
Artificial Intelligence · Cross-listed from cs.CR
Which Image Property Carries the Jailbreak? A Controlled Dissection of Image-to-Text Jailbreaks
Boyuan Chen, Yehia Dawoud, Hailemariam Mersha et al. (+4 more)
Image-to-text jailbreaks place harmful intent in text, image content, or the relationship between them. We examine image-side factors across four published attack families on a 313-
prompt StrongREJECT slice, using five
multimodal models and an additional appendix evaluation of InternVL3.5-8B. The harmful instruction is held constant across conditions; the baseline
matrix uses one draw per
prompt, and paired ablations use three draws with an automated rubric judge. A bare harmful query, with or without a benign unrelated image, produces little attack success on most victims, while attack images substantially increase it. First, per-tile
entropy and JPEG size do not reliably distinguish attack tiles from size-matched benign distractors, limiting density-only screening. Second, earlier tile-count ladders were confounded by payload visibility. A corrected region-count test found no detectable effect, so the role of tile-count structure remains unresolved. Third, on Qwen3-VL-8B, the E4 manipulation that removes query-specific relatedness lowers ASR by about 0.12. This supports a bounded attribution to the relatedness manipulation, although image-text congruence remains unmeasured. A within-category control reproduces the direction on overlapping stimuli. Five tests survive the global statistical correction, but only E4 supports attribution to one measured descriptor; the within-category result is a robustness check, not a separate attribution. These conclusions remain conditional on the rubric judge.
Read the full abstract ▾
All authors Boyuan Chen, Yehia Dawoud, Hailemariam Mersha, Minghao Shao, Siddharth Garg, Ramesh Karri, Muhammad Shafique
Artificial Intelligence · Cross-listed from cs.SD
Where Does the Audio Jailbreak Live? A Controlled Frequency-Depth Audit of AdvWave-P on Qwen2-Audio
Boyuan Chen, Minseok Kim, Sohaila Abdulsattar et al. (+4 more)
We audit frequency and decoder-depth claims for AdvWave-P, an additive audio jailbreak, on Qwen2-Audio. The protocol masks frequency components of the perturbation in the short-time
Fourier transform (STFT) domain and measures attack success and audio-span representations. On 520 AdvBench
prompts, the primary judge labels 76.7% of
adversarial inputs as jailbreaks. A condition-blind, single-annotator validation yields a Rogan-Gladen sensitivity estimate of 0.87 for this condition (about 0.83-0.95 with validation-rate uncertainty); this correction is not applied to masked conditions. The apparent frequency ranking depends on the partition: energy share alone predicts the standard eight-band ranking (Spearman's rho = 0.95), and equal-Hz and equal-energy partitions show that masking any tested band can sharply reduce attack success. At a finer 16-band equal-energy resolution, however, masking the narrow 7520-7960 Hz band leaves ASR at 0.10, which remains unresolved without a matched control. Matched-energy scattered-removal tests show that contiguous removal is more damaging in lower bands, while both forms approach the floor in upper bands. Global rescaling leaves ASR near baseline but tests amplitude sensitivity rather than frequency location. In a re-optimization pilot (n = 20), tested single- and two-band supports reach ASRs of 0.00, 0.25, and 0.40, while random supports covering about half the STFT bins reach a mean of 0.86. In a
prompt- and energy-adjusted model, audio-span divergence is associated with band necessity, with the coefficient rising from +0.63 at the projector output to +0.93 at layer 30 (contrast +0.293, 95% CI [0.11, 0.51]). This association is not a causal localization, and single-layer patching does not establish a causal layer. The results support partition-aware auditing of frequency claims, leaving the fine-resolution top-band result and broader generality open.
Read the full abstract ▾
All authors Boyuan Chen, Minseok Kim, Sohaila Abdulsattar, Minghao Shao, Siddharth Garg, Ramesh Karri, Muhammad Shafique
Artificial Intelligence
Topology-Consistent Task Planning over Cellular Workflow Complexes for LLM-based Agents
Sen Zhao, Jia Tang, Ruiqi Kong et al. (+6 more)
Task planning for LLM
agents requires workflows that satisfy both user intent and complex sub-task dependencies. While existing planners work well for sequential or directed acyclic graph (DAG)-like structures, they struggle with workflow patterns such as verification-correction loops, convergent branch merging, and reusable intermediate states that arise naturally in real-world tool orchestration. We present TopoPlanner, a
topology-consistent planning framework that lifts tool dependency graphs into cellular workflow complexes and uses them as topologyaware context for LLM tool planning. TopoPlanner retrieves a request-relevant closed subcomplex through cosheaf-consistent cellular
retrieval, performs multidimensional structural
reasoning over the retrieved
topology, and interfaces the resulting cellular representation with the planner LLM for tool-sequence generation. Experiments on four tool-planning
benchmarks with
topology-guided loop, merge, and loop-merge workflows show consistent improvements over
prompt-based and graph-enhanced baselines across different local LLM backbones.
Read the full abstract ▾
All authors Sen Zhao, Jia Tang, Ruiqi Kong, Zuyu Zhang, Lifeng Shen, Ding Zou, Xinyu He, Xu Zhang, Junwei Han
Artificial Intelligence · Cross-listed from cs.LG
Mask-Guided KV Cache Eviction in Block Diffusion Language Models
Gleb Molodtsov, Ekaterina Alimaskina, Evgeny Uskov et al. (+2 more)
Block
diffusion language models keep a large key-value (KV) cache throughout generation and attend to it at every denoising step, limiting both
memory capacity and generation speed. Reducing these costs requires deciding which past
tokens to use for denoising the current block (selection) and which to keep in
memory for future blocks (eviction). We propose MaskAhead, a training-free method that solves both tasks with a single mask-query-based ranking mechanism. Current-block masks guide selection, while probes of upcoming masked blocks guide eviction. Both rank KV entries by their estimated contribution to the
attention output. Our quantized variant, Q-MaskAhead, computes selection and
attention directly from low-bit KV, largely preserving the selected entries. Experiments on Fast-dLLM-v2, DreamReasoner, and LLaDA2.0-mini cover long-generation
reasoning, long-
prompt question answering, and needle-in-a-haystack
retrieval. On long-
prompt QA, MaskAhead reduces KV
memory by $9.5\times$ on average with a 1.2-point mean F1 loss relative to dense inference. Q-MaskAhead increases the reduction to $20.1\times$ with a 2.3-point mean F1 loss. In a batch-32 systems profile, MaskAhead achieves $1.23\times$ end-to-end and $1.68\times$ decode-stage speedups over dense inference.
Read the full abstract ▾
All authors Gleb Molodtsov, Ekaterina Alimaskina, Evgeny Uskov, Artur Zagitov, Aleksandr Beznosikov
Artificial Intelligence
Joint upper-bound coverage and route-choice utility: an empirical evaluation on two urban proxy tasks
Jianing Long, Xiaobin Li, Wuming Lei et al. (+1 more)
Whether more accurate traffic forecasts or higher uncertainty coverage improve route decisions is unclear. We evaluate this question with a frozen protocol that separates speed error, joint candidate path upper bound coverage, route selection, and realized loss. Using processed road speed data from Beijing and Chengdu, we construct offline proxy tasks with 150 origin destination pairs, three candidate paths, and 14 test days per city. We compare raw 90th percentile path time bounds with jointly calibrated upper bounds under minimum bound route choice. Joint coverage rises from 83.19% to 92.26% in Beijing M1, from 75.14% to 88.33% in Chengdu M1, and from 74.01% to 90.64% in Chengdu M2. Yet C2 increases lateness by 0.1633, 0.7848, and 0.9200 percentage points, respectively, and mean travel time by 0.588, 3.082, and 4.418 seconds. In a separate Chengdu predictor comparison, a 14.91% reduction in speed mean absolute error accompanies a 1.4571 percentage point reduction in lateness under C0. Joint coverage is therefore not a surrogate for downstream route utility in these frozen tasks the offline results do not establish online or causal benefits.
Read the full abstract ▾
All authors Jianing Long, Xiaobin Li, Wuming Lei, Weiguang Wang
Artificial Intelligence · Cross-listed from cs.CR
TARE: Weigh a Never-Poisoned Twin Before Reading Backdoor-Defense Costs
Ruizhi Xu, Wei Xu and Sibo Zhu
Backdoor-defense leaderboards print a clean-accuracy drop and read it as removal cost. Measured on the poisoned victim alone, the drop cannot separate removal from what the defense does to any model, and inherits the victim's start, which for three of BackdoorBench's sixteen attacks is a configuration file: WaNet, BPP and Input-Aware ship a MultiStepLR that never fires, so their victims never anneal and are the least accurate in 30/31 public CIFAR
cells at $\leq$5%. On PreAct-ResNet18, fine-tuning-family defenses return a low start to their own level, so there the published cost is negative, the
benchmark's rating clips the "gain" to zero, and 2 of 48 citing defense papers we read rest a no-cost claim on those
cells; TSBD and CGD, re-run with their code, "gain" on a never-poisoned model too. A $2\times2$ editing only that scheduler line isolates the cause, its swapped arms self-registered before they ran: the sign of the fine-tuning family's clean-model cost reverses both ways while its published gain on the annealed victim only shrinks toward zero, 44/44 seeds following the schedule, replicated on BPP, FT-SAM, CIFAR-100 and VGG19-BN and induced in a second toolkit. TARE runs the same defense on a never-poisoned twin of the same recipe, schedule and seed (on BackdoorBench, $\leq$10 poisoned images, admitted only below 5% attack success); what the twin loses is the tare. On the BadNets grid seven of eight defenses charge the twin (Neural Cleanse only where its detector fires), +0.13 (fine-tuning) to +5.70 points (I-BAU); the eighth, ABL, destroys it. Within an attack the start cancels from rankings, so the tare re-orders nothing there; what poisoning adds beyond it is printed under two
estimators and not corrected, its removal share unidentified. We ship the three-key patch, a signed tare column (7 attacks $\times$ 8 defenses) and TARE-Z, a twin-free
estimator for seed-stable defenses.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
DART-ES: Difficulty-Aware Reweighting and Targeted Replay for Fine-Tuning LLMs with Evolution Strategies
Zhishen Sun, Hongzhan Wang, Sizhe Dang et al. (+2 more)
Evolution Strategies (ES) enable
memory efficient full parameter fine-tuning of large
language models (LLMs) using only forward computation. However, standard ES uniformly averages rewards across problems and compresses problem level population feedback into a single scalar, making it difficult to capture how the learning value of each problem changes with model capability. To address this limitation, we propose Difficulty-Aware Reweighting and Targeted Replay for
Evolution Strategies (DART-ES). DART-ES estimates the local solvability of each problem from its pass rate across the perturbation population and aggregates historical observations to construct a dynamic difficulty state. This shared state jointly guides continuous difficulty reweighting and rare solvable sample replay, thereby improving perturbation direction evaluation and training data allocation without introducing an additional difficulty model or backpropagation. Extensive experiments show that DART-ES achieves good fine-tuning performance. DART-ES outperforms ES on all five base models and improves the average accuracy from 72.07% to 73.53%, exceeding the 73.26% achieved by GRPO on GSM8K. Across five challenging mathematical
reasoning benchmarks, DART-ES achieves an average accuracy of 49.20%, compared with 48.34% for ES and remains competitive with strong 7B models trained with RL. Further experiments show consistent gains in instruction tuning, code generation and the Countdown task with a 14B model, demonstrating strong generalization across tasks and scalability to larger models. Beyond performance gains, DART-ES also shows clear advantages in system efficiency. It reduces runtime per step by 15.2%–50.2% and peak
memory usage per GPU by 21.1%–51.1% compared with GRPO. Despite performing full parameter fine-tuning, DART-ES also requires less runtime and GPU
memory than GRPO+LoRA.
Read the full abstract ▾
All authors Zhishen Sun, Hongzhan Wang, Sizhe Dang, Guang Dai, Haishan Ye
Artificial Intelligence
When better traffic forecasts fail to improve signal control: a layered diagnostic study of forecast-to-decision value
Jianing Long, Xiaobin Li, Wuming Lei et al. (+1 more)
Improved traffic forecasts do not necessarily yield better signal-control decisions. We investigate this gap through a layered diagnostic study using 29 days of reconstructed demand from Xuancheng, China, with seven dates reserved for testing. The framework evaluates point forecasts, conformal intervals, dependence-aware scenarios, and matched closed-loop controllers. Entry-level and movement-level forecasts reduce mean absolute error by 4.03% and 3.92%, respectively, relative to historical means. A nominal 90% conformal interval achieves 90.72% marginal coverage but only 75.66% on an ex-post high-demand subset. Interface audits identify decision-time leakage and reveal that only two of nine controlled intersections offer multiple effective actions. We correct the temporal interface and compare causal forecasts with a five-second event oracle using exhaustive joint-action search. A synthetic positive control demonstrates that future information can reduce the internal rollout cost by 61.5%. On the frozen test dates, however, causal forecasts and the event oracle increase queue vehicle?seconds by 6.09% and 3.39% relative to the matched no-future rollout, while the oracle reduces spillback exposure by 3.78%; paired-day bootstrap intervals cross zero. These findings indicate that forecast value depends on temporal observability, action identifiability, dynamics consistency, and objective
alignment. The proposed protocol provides a practical way to diagnose where predictive improvements fail to translate into operational benefits.
Read the full abstract ▾
All authors Jianing Long, Xiaobin Li, Wuming Lei, Weiguang Wang
Artificial Intelligence
EPOCH: Reliable Discovery through Evidence-Governed Search
Binjie Guo, Aisheng Mo, Ruitong Li et al. (+1 more)
AI research
agents are increasingly used to search over programs, mathematical constructions, and proofs. However, existing systems typically optimize evaluator feedback without adequately governing how that feedback is interpreted, challenged, and reused. As a result, promising but fragile candidates can be promoted as discoveries, while
benchmark improvements, finite certificates, and
theorem-level claims are too easily conflated. We introduce EPOCH, an evidence-governed architecture designed to close this gap. EPOCH implements an evidence-governed discovery loop by combining explicit task contracts, typed
memory, active falsification, admission checks, and independent replay, so that each candidate is evaluated against the strength and scope of the claim it supports. EPOCH achieves state-of-the-art aggregate performance on AlgoTune, substantially exceeding the strongest baseline in mean normalized score (0.65 vs. 0.53), and attains the highest mean score on the internal Math14 suite (0.57). It further shows favorable held-out behavior under official-test replay and leads the descriptive aggregate on AgentHPO. Across ten discovery problems, EPOCH delivers substantial task-specific advances, including improved executable constructions, optimized
algorithms, counterexamples, and proof-supported results. These advances demonstrate its ability to convert search into concrete progress across mathematical and computational domains. Together, the results suggest that evidence governance is a necessary step toward AI research
agents that produce not only stronger solutions, but also more trustworthy scientific discoveries.
Read the full abstract ▾
All authors Binjie Guo, Aisheng Mo, Ruitong Li, Xinle Deng
Artificial Intelligence · Cross-listed from cond-mat.mtrl-sci
CrystalJev: calibrated foundation-model probabilities decide what to compute next in materials discovery
Peng Kang, Yaxuan Sun, Zhen Li et al. (+3 more)
Atomistic foundation models screen hypothetical
crystals by thresholding predicted energies, an output that states neither how likely a candidate is to be stable nor whether more computation would change the decision. CrystalJev reads one forward pass of a frozen potential on the unrelaxed structure and returns calibrated probabilities, conformal guarantees and a rule for escalating candidates to relaxation or density-functional theory (DFT). Across 65 Matbench Discovery models, threshold calls hide cost assumptions, and ordering slower computation by its value for the decision, rather than by probability, recovers most of its benefit at a tenth of its cost. In a registered prospective test with 2,100 DFT calculations on ionic substitutions, forecasts calibrated on existing data over-stated the stable fraction of new candidates by 0.9–2.2 percentage points, because the population had shifted, not the labelling protocol; a few hundred labels from the new pool removed this bias more reliably than label-free corrections.
Read the full abstract ▾
All authors Peng Kang, Yaxuan Sun, Zhen Li, Yu Liu, Lei Zheng, Huibin Xu
Artificial Intelligence · Cross-listed from cs.CV
Visual-Invariance-Augmented Feature Optimal Alignment for Transferable Adversarial Attacks against Closed-Source MLLMs
Xiaojun Jia, Simeng Qin, Yiming Li et al. (+5 more)
Multimodal large
language models (MLLMs) remain vulnerable to transferable
adversarial examples, especially in black-box settings where only open-source surrogate models are accessible. Existing targeted transfer attacks mainly align
adversarial and target samples using global image-level features, such as encoder [CLS]
embeddings. However, such coarse
alignment insufficiently exploits patch-level visual structures, limiting transferability across heterogeneous closed-source MLLMs. We propose IAU-FOA, a visual-invariance-augmented feature optimal
alignment attack with adaptive unbalanced transport, to improve targeted transferability against closed-source MLLMs. IAU-FOA aligns
adversarial and target samples at both global and local levels: a cosine-based objective narrows their global semantic gap, while patch
tokens are clustered into compact local patterns and matched through optimal transport for fine-grained feature
alignment. Balanced optimal transport enforces fixed marginal masses even for local clusters without reliable counterparts, potentially introducing misleading
alignment gradients. We therefore introduce confidence-adaptive unbalanced transport to relax these constraints for weakly matched clusters, aiming to reduce unreliable local
alignment and improve
adversarial transferability. We further study the effect of input transformations and propose visual-invariance augmentation, which applies bidirectional pixel-intensity rescaling and per-channel white-balance adjustment to simulate exposure, contrast, illumination, and color-temperature variations. This strategy encourages
adversarial perturbations to generalize across different visual encoders. Extensive experiments on open-source and closed-source MLLMs show that IAU-FOA consistently outperforms state-of-the-art transferable attack methods. Code is available at https://github.com/jiaxiaojunQAQ/IAU-FOA.
Read the full abstract ▾
All authors Xiaojun Jia, Simeng Qin, Yiming Li, Jie Liao, Sensen Gao, Ke Ma, Yang Liu, Xiaochun Cao
Artificial Intelligence
The GenAI4IDN Benchmark 3.0 - a Public Tool to Assess Generative AI Tools for the Design of Interactive Digital Narratives
Hartmut Koenitz, Jonathan Barbara and Mirjam Palosaari Eladhari
This paper presents GENAI4IDN
Benchmark 3.0, the third iteration of an evaluation framework to assess Generative AI tools for creating Interactive Digital Narratives (IDNs). Moving beyond manual testing, this iteration introduces AI-assisted evaluation through a publicly accessible web application (https://genai4idn.com), enabling the community to run
benchmarks on demand, add new models, and propose new tasks. The revised evaluation framework is "blinded" to avoid model-bias, and can handle complex media such as music,
videos, and full IDNs that previously required human raters. A significant addition - responding to concerns raised during ICIDS 2025 - is the addition of fact-checking and bias detection with dedicated tasks and rubrics, validated by human raters with lived experience in the depicted contexts. Findings from a diverse range of models report on maturing creative capabilities while observing runaway thinking and overzealous safety filters as limitations. Fact-checking reliably caught subtle historical inaccuracies, anachronisms, and fabricated claims while the bias rater consistently exposed structural assumptions, tropes, and marginalized group erasures.
Read the full abstract ▾
Artificial Intelligence
A Framework for Automated Multi-Source Satellite Data Analytics and LLM-Based Report Generation
Hind Yousif Alhammadi and Isam Mashhour Al Jawarneh
This paper presents the workflow for building an automated ArcGIS Pro tool using ArcPy to extract the Land Surface Temperature (LST) from Landsat 7, 8 and 9
datasets. The tool eliminates the need for manual band selection and repetitive raster computations by automating the multi-step workflow of radiometric calibration, NDVI-based emissivity correction, and thermal conversion. In addition to supporting batch and single-scene processing, the tool has an optional Large
Language Model (LLM) for statistical result interpretation and reporting. Depending on batch size, the tool reduced the processing time from around 11-58 minutes when done manually to around 4-11 minutes using the tool. We tested the tool with data from Ras Al Khaimah (RAK) in the UAE, and the LST obtained for Ras Al Khaimah ranged from approximately 25C to 50C, demonstrating an accurate LST mapping compatible with the weather conditions of RAK. In summary, our tool reduces human errors and improves processing accuracy and efficiency for thermal and environmental remote sensing applications, in addition to providing an interactive LLM-based interface for result interpretation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI Agents
Dolly Sah, Tanmay Sah, Harshul Jain et al. (+1 more)
Tool-using AI
agents are increasingly deployed across enterprise software systems, yet widely used
benchmarks primarily evaluate nominal task completion, conflating baseline planning competence with operational fault recovery. We introduce UndoBench, a
benchmark spanning 36 base workflows and 36 fault scenarios across 8 enterprise domains, decoupling task competence from recovery capability via counterfactual paired trials under identical seeds alongside wire-level effect-history and environment-state oracles. On 12 held-out TEST workflows across two open-weight models, two frameworks, and three recovery paradigms (5,760 executions / 2,880 paired trials) in the frozen lost-acknowledgment study, nominal competence reached 83.54% while conditional recovery success rate (CRSR) fell to 46.72%, with naive retry producing duplicate external effects in 53.33% of trials. Extensions to commercial API models reproduced this competence-recovery separation. Evaluations across complementary execution boundaries show that recovery is phase-dependent: before mutation, methods perform similarly without duplicate effects among capable trials; during partial mutation, naive retry, per-call idempotency, and zero-privilege journaling collapse on the evaluated composite workflows; after commit but before acknowledgment, verification and server-side idempotency substantially improve safety. These findings demonstrate that evaluating nominal completion alone masks critical, phase-dependent recovery vulnerabilities in autonomous
agents.
Read the full abstract ▾
All authors Dolly Sah, Tanmay Sah, Harshul Jain, Tanya Sah
Artificial Intelligence
DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate
Khanh-Binh Nguyen, Van Dai Do, Tien Anh Nguyen et al. (+2 more)
Multi-
agent debate (MAD) has emerged as an effective paradigm to improve the
reasoning capabilities of large
language models (LLMs) and is increasingly being extended to
multimodal settings. However, existing
multimodal MAD frameworks typically expose
agents to the same fixed visual input, ignoring substantial variation in the visual scale needed across samples and
agents. In addition, these frameworks frequently suffer from groupthink, a phenomenon where
agents prematurely abandon correct deductions to conform with confident but hallucinated peer responses. To address these bottlenecks, we introduce DREAM (Dynamic Resolution Assignment For
Multimodal Multi-
Agent Debate), which operates via two core components: (1) Dynamic Resolution Assignment, a zero-shot probe round where
agents test multiple resolutions, quantify uncertainty using Average Normalized Log-Likelihood (ANLL), and use an adaptive threshold to assign each
agent to its empirically optimal resolution; (2) Uncertainty-Guided Rollback Aggregation counters groupthink by tracking each
agent's uncertainty over rounds and restoring early low-uncertainty answers overridden by group pressure. On six
multimodal datasets, DREAM improves the accuracy-
token trade-off over multi-
agent debate baselines by 1.5-3.2% accuracy without
dataset-specific tuning.
Read the full abstract ▾
All authors Khanh-Binh Nguyen, Van Dai Do, Tien Anh Nguyen, Svetha Venkatesh, Hung Le
Artificial Intelligence · Cross-listed from cs.SD
SEA-LM: Egocentric Spatial Audio Understanding for Wearable Microphone Arrays
Sonal Kumar, Sinan Hersek, Artem Dementyev et al. (+6 more)
Embodied, ego-centric intelligence fundamentally requires the ability to comprehend spatial audio within complex environments. While large audio-
language models excel at mono-channel
reasoning, they lack spatial awareness, discarding critical spatial cues that enable sound localization and that can improve the disentanglement of overlapping sound sources. To address this, we present SEA-LM, a Spatial Audio Understanding model. First, we introduce FOACODER, a layout-flexible spatial audio encoder trained on source localization and ego-centric voice activity detection objectives to encode First Order Ambisonics derived from variable-count, variable-position smart-glasses arrays via beamforming. We train a
Multimodal Large
Language Model (MLLM) to understand these spatial audio
embeddings through a two-stage curriculum spanning six tasks, including sound localization and spatially selective transcription in settings with multiple speakers and overlapping sounds. To prevent the transcription outputs from dominating the next
token prediction loss and overwhelming the direction predictions, we introduce a Spatio-temporal Weighted Cross-
Entropy Loss. On our evaluation set, SEA-LM achieves lower azimuth and elevation MAE, higher temporal IoU, lower external-source
hallucination and missing-source rates, and lower WER on most transcription tasks than compared baselines, while remaining robust across 1,211 smart-glasses array configurations with 4 to 9 microphones.
Read the full abstract ▾
All authors Sonal Kumar, Sinan Hersek, Artem Dementyev, Mengzhen Pan, Ishan Chatterjee, Anurag Kumar, Ramani Duraiswami, Dinesh Manocha, Andrea Colaco
Artificial Intelligence · Cross-listed from cs.CV
Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation
Team Kandinsky, Julia Agafonova, Bulat Akhmatov et al. (+85 more)
We present Kandinsky 6.0
Video, a family of foundation
diffusion models for synchronized text-to-audio-
video generation, comprising Kandinsky 6.0
Video Lite (3B parameters) and Kandinsky 6.0
Video Pro (29B parameters). Both models generate 5-second
video clips with synchronized 44 kHz audio, including lip-sync, in text-to-audio-
video (T2AV) and image-to-audio-
video (I2AV) modes; a built-in super-resolution model raises the output resolution to Full-HD (1920$\times$1080). Building on the
video generation capabilities of Kandinsky 5.0, Kandinsky 6.0
Video employs a dual-stream CrossDiT architecture that connects a pretrained
video stream and a newly trained audio stream through bidirectional cross-
attention for temporal and semantic
alignment. Our continuous pretraining strategy first trains the audio stream from scratch on large-scale audio corpora and then trains both streams jointly on paired audio-
video data while preserving unimodal fidelity; pretraining is followed by supervised fine-tuning, reinforcement-learning-based post-training, and
distillation. In side-by-side human evaluation, Kandinsky 6.0
Video Pro clearly outperforms its predecessor, Kandinsky 5.0
Video Pro, and remains competitive with leading audio-
video generation models, particularly in
speech quality. To accelerate open research and deployment in multimedia generation, we release the code, model checkpoints, and diffusers integration under the MIT license.
Read the full abstract ▾
All authors Team Kandinsky, Julia Agafonova, Bulat Akhmatov, Mikhail Aksyutin, Grigorii Alekseenko, Anastasia Aliaskina, Olga Androsova, Vladimir Arkhipkin, Anna Averchenkova, Alexander Belykh, Serafima Bocharova, Sofiya Bogakovskaya, Anton Bukashkin, Mark Bulygin, Kirill Buzygin, Irina Cheremnykh, Kirill Chernyshev, Mikhail Chernyshov, Vladimir Chernyy, David Chikovani, Georgy Daniltsev, Denis Dimitrov, Anna Dmitrienko, Vladimir Dokholyan, Sergey Emelyanov, Dmitry Ermilov, Georgii Fedorov, Polina Gavrilova, Nikolai Gerasimenko, Aleksandr Gordeev, Andrey Inozemtsev, Andrei Ivaniuta, Alexander Ivanov, Mikhail Karaev, Anastasiia Kargapoltseva, Ivan Kirillov, Nikita Kiselev, Valeria Kobenko, Yury Kolabushin, Denis Koposov, Anatoly Korobov, Vladimir Korviakov, Kirill Kozlov, Denis Krzhivokolskiy, Konstantin Kuklev, Alexander Kunitsyn, Sergey Kuzin, Vladislav Lakhtionov, Alexey Letunovskiy, Maxim Litvinov, Alexander Lyulkov, Georgy Makarov, Kirill Malakhov, Egor Malykh, Mikhail Mamaev, Dmitrii Mikhailov, Polina Mikhailova, Ivan Mikheev, Elizaveta Muromtseva, Nikolai Nazarkin, Tatiana Nikulina, Lev Novitskiy, Stanislav Onuchin, Nikita Osterov, Denis Parkhomenko, Anatoliy Parpara, Vladimir Polovnikov, Konstantin Reznikov, Azat Saginbaev, Nikita Samsonov, Alexander Sentsov, Nikita Shaimov, Artem Sherstyuk, Andrey Shutkin, Egor Silvestrov, Bulat Suleimanov, Matvey Suprunov, Sergey Taranov, Irina Tolstykh, Tatiana Trofimuk, Ilya Trushkin, Aleksandra Tsybina, Olga Varlashina, Viacheslav Vasilev, Ilya Vasiliev, Eugeny Vilisov, Sergey Yakubson, Konstantin Zakharov
Artificial Intelligence · Cross-listed from cs.LG
Your Unlearning Gives You Away: Identifying Erased Concepts in Diffusion Models
Kaiyuan Deng, Yuchen Li, Yang Xiao et al. (+3 more)
Existing attacks on unlearned
diffusion models assume that the erased concepts are known in advance and focus on recovering them. In practice, however, model providers may not disclose which concepts have been removed, and even with access to the original base model, an adversary may still lack a clear target to attack. In this paper, we aim to answer the following critical but overlooked questions: which concepts have been erased from the model, and how many have been erased in total? To this end, we present Tracer, a framework that rapidly and accurately identifies erased concepts and estimates their number. Tracer efficiently identifies erased concepts without generating and classifying images. By combining lightweight spectral analysis of weight footprints, it enables efficient search over large candidate vocabularies. To distinguish multiple erased concepts, we introduce a footprint coverage objective that guides sequential discovery. Tracer estimates the number of erased concepts by detecting a sharp decline in candidate confidence as the selected concepts account for the erasure footprint, without requiring labeled examples for calibration. The framework requires only lightweight linear
algebra and limited forward probes, with no prior knowledge of the unlearning
algorithm. Experiments across text-to-image and text-to-
video backbones and diverse unlearning methods demonstrate that Tracer identifies erased concepts and estimates their number in seconds, achieving 150 to 137,000 times and 133 to 20,000 times speedups over MIA and brute-force search on image and
video models, respectively, with substantially higher identification accuracy.
Read the full abstract ▾
All authors Kaiyuan Deng, Yuchen Li, Yang Xiao, Bo Hui, Geng Yuan, Xiaolong Ma
Artificial Intelligence · Cross-listed from cs.LG
An LLM-in-the-loop RL Framework for Bioinformatics Feature Selection
Xinyuan Wang, Deepti Agrawal and Yanjie Fu
High-dimensional bioinformatics data, characterized by a large number of features relative to the number of samples, pose major challenges such as the “curse of dimensionality,” leading to overfitting, high computational cost, and poor generalization. Traditional feature selection methods often suffer from limited scalability and adaptability in such domains. We propose an LLM-in-the-loop reinforcement learning (RL) framework for bioinformatics feature selection, where the RL
agent formulates feature selection as a sequential decision-making task, while the large
language model (LLM) enhances the process in two ways: (1) guiding exploration through domain-informed advice, and (2) providing hybrid rewards that integrate data-driven performance with knowledge-driven evaluation. The LLM also produces explanations to improve interpretability for human experts without altering the RL policy update. Experiments on diverse bioinformatics
datasets show that the LLM-in-the-loop framework outperforms baselines, achieves stable performance across downstream models, and converges faster than pure RL.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
When the Cross-Silo Federation Goes Offline: Continual Learning for Site Onboarding with Limited Unlabeled Data
Ahmadreza Eslaminia, Klara Nahrstedt and Chenhui Shao
An organization often holds too little labeled data to train a model that generalizes, and the records that would supply the rest sit with organizations that cannot release them. Cross-silo
federated learning offers a way through, since participants exchange model parameters rather than records, but it ordinarily settles two aspects of the arrangement in advance, the participating sites and the classes the model can predict, and deployment can breach both. A new site joins after training, once the established sites have finished their engagement and gone offline, and its records arrive unlabeled, mixing conditions the model already recognizes with conditions no participant has observed. We present an autonomous three-stage procedure that expands the model entirely at the joining site: reconstruction experts screen for novelty, clustering separates the flagged records into candidate conditions, and class means describe the old classes, all inside one shared representation. Those classes were learned from records that never leave their owners, so the usual defenses against forgetting are unavailable, and the procedure supplies the evidence they would have carried from either of two dissimilar sources, prototypes held by the federation or records held by the joining site. On a real industrial condition-monitoring
dataset, run end to end with no label consulted, either source holds old-class accuracy at 0.868 or above with forgetting at most 0.063, and the two differ by 0.021, so a configuration can be chosen by the disclosure it permits rather than the accuracy it delivers. Both keep old- and new-class accuracy in balance where every alternative we measure gives up one for the other, and both retain more of the old classes than
distillation- and regularization-based baselines. The balance still holds with only 6 labeled records per arriving condition and 3 retained per old class.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
AgentDoxx: Agentic Re-identification of Anonymized Text with Web Search
Jianing Wen and Tianshi Li
As Large
Language Models (LLMs) gain tool use capabilities such as web search, they can retrieve and cross-reference public information, creating
privacy risks beyond memorization. One manifestation is re-identification: linking an anonymized interview transcript to a named individual. Yet without ground-truth identities, the coverage of such attacks and the protection offered by a defense cannot be reliably measured. We introduce AgentDOXX, an evaluation suite of 822 synthetic interview transcripts grounded in public information about real individuals with known identities. We evaluate fifteen configurations of open-weight and proprietary models, isolating the effect of web search, and analyze their search trajectories to distinguish
retrieval-driven from parametric identifications. Ground-truth identities reveal that re-identification risk is distributed across an
agent's execution:
retrieval and parametric recall both contribute, with open-weight models identifying 15-28% of transcripts without search; identification succeeds in over 88% of cases once the target appears in a retrieved result; entity masking leaves at least one attacker successful on 85.3% of a stratified sample; and
privacy instructions suppress naming but not
retrieval, with configurations scoring 0% accuracy yet retrieving the subject in up to 62% of transcripts. We further show that observed attack trajectories can provide supervision for localizing identifying spans, offering a path toward attack-informed anonymization.
Read the full abstract ▾