Artificial Intelligence
Automatic Ordinary Differential Equations Discovery For Biological Systems Using Large Language Model Powered Agentic System
David Krongauz, Arad Zulti, Eran Segal et al. (+1 more)
Automatic scientific discovery has long been a goal of computational scholars - a machine that can discover nature's secrets on its own, moving computational systems beyond data-fitting tools toward the generation and refinement of mechanistic models of the universe. Recent advances in symbolic regression (SR) and large-
language-model (LLM)-based
agents suggest that such systems can recover equations from data, incorporate domain priors, and automate parts of the research workflow. However, most existing approaches either focus on narrow equation-discovery
benchmarks or broad end-to-end automation pipelines, while biological systems remain comparatively underexplored. Here, we introduce the MEDA system, an LLM- and SR-powered agentic framework for discovering ordinary-differential-equation (ODE) models of biological and biologically inspired dynamical systems. MEDA retrieves background knowledge, defines admissible variables, generates mechanistic constraints, proposes candidate ODEs, and fits and evaluates them. We evaluate it across canonical model
retrieval,
reasoning-based extrapolation to unseen variants, and open-ended discovery, with and without experimental data. Across these settings, MEDA recovered the correct state variables, achieved strong structural recovery in
retrieval and extrapolation tasks, and produced biologically plausible discovery-oriented models. Ablation and robustness analyses show that knowledge-guided formalization and mechanistic constraints are load-bearing components, whereas numerical fitting alone can preserve trajectory-compatible but biologically incorrect equations.
Read the full abstract ▾
All authors David Krongauz, Arad Zulti, Eran Segal, Teddy Lazebnik
Artificial Intelligence · Cross-listed from cs.RO
Semantic Anchoring for Robotic Action Representations
Yuan Xu, Youheng Shi, Chengyang Li et al. (+2 more)
Vision-
Language-Action (VLA) models inherit rich semantic representations from pretrained
Vision-
Language Models, yet fine-tuning on limited
robot demonstrations degrades this structure and undermines generalization. A fundamental question therefore arises: what constitutes a good action representation? Inspired by the mirror
neuron theory's insight that observation and execution share an intention-level encoding, we examine whether a
robot's action representations preserve the semantic structure captured by pretrained encoders. Systematic probing confirms that this structure erodes during finetuning, and that its quality synchronizes with both task success and out-of-distribution generalization. We further introduce a plug-and-play method that anchors action representations to a semantic
manifold while decomposing representations into a shared semantic channel and a private channel, all discarded at inference, leaving the deployed model unchanged. Validated on different VLA backbones across simulation and real-world
benchmarks, our method yields up to +18.7% on real-world in-distribution tasks and +21.5% on out-of-distribution generalization.
Read the full abstract ▾
All authors Yuan Xu, Youheng Shi, Chengyang Li, Wentao Zhu, Yizhou Wang
Artificial Intelligence · Cross-listed from cs.CR
Protective Capacity Hallucination: When Large Language Models Claim Nonexistent Capabilities
Eunna Lee
When cast as the protector of a vulnerable user yet given no explicit capability boundary, a large
language model (LLM) may respond not by acknowledging its limits but by claiming to have taken, or to be taking, a real-world protective action it cannot perform, such as contacting emergency services or administering care. We term this phenomenon Protective Capacity
Hallucination (PCH): a self-referential misattribution in which a model, acting in a protective role, asserts physical or institutional agency exceeding its affordances as a
language model. In a three-phase study spanning eight LLMs and 13,600 sessions, we find that PCH depends on both situational severity and interactional format. Across ordinary service domains, multi-party dialogic input drives PCH to near-ceiling levels in most models. In contrast, PCH remains at floor levels in all eight models when the same models are placed in intimate-partner conflict scenarios, despite the greater physical severity of those situations. We interpret PCH as the signature of a deployment-design gap between role assignment and capability-boundary specification: a by-product of partial
alignment in which a universally trained pressure to help outruns a domain-selective specification of how to help. Because suppression tracks
alignment coverage rather than severity, deployment-side specification of capability boundaries emerges as a general mitigation target.
Read the full abstract ▾
Artificial Intelligence
SAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE Routing
Tianyu Chen, Chujia Hu and Wenjie Wang
LLM
agents act on real-world environments through tool calls, and a single misjudged action can cause irreversible harm. The standard safeguard is a guard model that labels each proposed action as safe or unsafe, but this binary view conflates two distinct decisions: whether the action is harmful in itself, and whether it is appropriate given the user's context. It also operates at the granularity of action categories rather than individual instances, producing routine interruptions that erode autonomy and train users to wave through the most consequential alerts. We reframe the problem as a per-instance three-way routing decision over {EXECUTE, ASK, REFUSE} and instantiate it with Safety Sentry, a lightweight guard model whose inference reduces to a single decoding call. A single decoding-time threshold lets one fixed checkpoint be re-positioned across deployments of differing risk tolerance without retraining. Safety Sentry outperforms a broad set of open-weight and frontier closed-source baselines on overall accuracy and safety-related recall, while controlling both directional error rates simultaneously.Code and data are available at https://github.com/safesentry/SAFETY-SENTRY
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents
Eric Hanchen Jiang, Zhi Zhang, Yuchen Wu et al. (+11 more)
Large
Language Model (LLM)
agents increasingly rely on external
memory systems to accumulate experience across tasks. Yet nearly all existing approaches, from graph-structured
memories to reflective insight stores, access
memory through fixed, hand-designed heuristics. We argue that this static view of
memory is a core bottleneck for agentic learning because optimal
memory behavior is fundamentally context-dependent. The early stages of the tasks, benefit from minimal
retrieval because
memory is sparse; recurring goal types benefit from plan reuse rather than generic nearest-neighbor lookup; stuck
agents benefit from re-
retrieval with alternative queries; and across long task streams, the
memory store itself must be consolidated and pruned to remain useful. We present
Memory as a Controlled Process (MemCon), a framework that models
memory operations as a Markov Decision Process and learns an online policy that adaptively decides when, what, and how much to retrieve, when to inject a distilled plan, and when to consolidate or forget. MemCon is backend-agnostic: it wraps any existing
memory implementation, learns from task-by-task binary feedback with no pretraining and no additional LLM calls, and uses a lightweight tabular contextual bandit with UCB exploration that converges within tens of tasks. Across 6
benchmarks, 3
agent frameworks, and 3 LLM backbones, MemCon consistently outperforms multiple
memory baselines by up to 15.2 points in task success while reducing
token consumption by 5–20%.
Read the full abstract ▾
All authors Eric Hanchen Jiang, Zhi Zhang, Yuchen Wu, Levina Li, Dong Liu, Xiao Liang, Rui Sun, Yubei Li, Edward Sun, Haozheng Luo, Zhaolu Kang, Aylin Caliskan, Kai-Wei Chang, Ying Nian Wu
Artificial Intelligence · Cross-listed from cs.SD
From Prediction to Collaboration: Interactive Symbolic Music Analysis
Emmanouil Karystinaios, Johannes Hentschel, Markus Neuwirth et al. (+1 more)
Automatic symbolic music analysis has made substantial progress, yet existing systems are typically designed for a single mode of use, such as full-score prediction, and therefore do not match the broader range of operations that arise in analysis workflows, including partial completion, local correction, and iterative refinement. As a result, there remains a gap between strong
benchmark models and systems that can support interactive analytical use. We present a unified framework for symbolic Roman-numeral (RN) analysis that narrows this gap by combining strong predictive performance with direct support for constrained completion and revision. The method is designed to provide a practical trade-off between accuracy and interactive responsiveness by computing expensive pretrained representations once and reusing them during iterative refinement, making powerful pretrained models more amenable to interactive settings. It supports complete score analysis, targeted revision of existing labels, and inference of missing annotations from partial context through a shared modeling framework. Experiments on Dilemmadata, the largest and most heterogeneous
benchmark of its kind, show that the proposed approach is a strong RN-analysis baseline while also supporting masked completion from partial labels. Together with a prototype interface for multi-level candidate inspection and editing, these results position automatic RN analysis not only as a prediction problem, but also as a foundation for future interactive tools for music analysis.
Read the full abstract ▾
All authors Emmanouil Karystinaios, Johannes Hentschel, Markus Neuwirth, Gerhard Widmer
Artificial Intelligence · Cross-listed from cs.RO
Agile perceptive multi-skill locomotion for quadrupedal robots in the wild
Jun-Gill Kang, Jaehyun Park, Tae-Gyu Song et al. (+3 more)
Enabling quadrupedal
robots to traverse complex terrains-from rugged outdoor environments to urban landscapes-requires seamless integration of multiple motor skills, smooth transitions between gaits, and high-speed perceptive locomotion using only onboard sensors. We present APT-RL (Action Pretrained
Transformer-based Reinforcement Learning), a unified framework that enables multi-skill locomotion to achieve high-speed traversal in complex environments through autonomous skill transitions utilizing only onboard perception and computation. Our approach generates large-scale, feature-rich 2D motion
datasets through trajectory optimization with simplified dynamics. These
datasets enable training of diverse, reusable locomotion skills that transfer effectively to a real quadruped
robot operating on complex uneven terrains. The resulting high-quality skills serve as strong priors for efficient learning of complex downstream tasks and extend naturally to 3D environments, enabling smooth, high-speed multi-skill locomotion in deployed policy. Real-world experiments demonstrate the framework's capabilities: the
robot performs agile maneuvers through complex indoor obstacles and outdoor wild environments, including dynamic drop-down maneuvers that reach instantaneous peak speeds of up to 6 meters per second. A single onboard policy enables robust traversal of diverse obstacles, including stairs, hurdles, stepping stones, gaps, and fallen branches, demonstrating the versatility and effectiveness of our approach.
Read the full abstract ▾
All authors Jun-Gill Kang, Jaehyun Park, Tae-Gyu Song, Joon-Ha Kim, Seungwoo Hong, Hae-Won Park
Artificial Intelligence · Cross-listed from cs.RO
IMMNet: Hybrid Fusion of Model-based and Data-driven Approaches for Maneuvering Target Tracking
Yixuan Zhao, Chaoqun Yang, Lin Gao et al. (+2 more)
Maneuvering target tracking in three-dimensional space remains a challenging problem due to complex motion dynamics and model mismatch. To address this, this paper proposes a hybrid model/data-driven
algorithm named IMMNet, which integrates the interpretable structure of the interacting multiple model (IMM)
algorithm with learnable neural components. Unlike end-to-end black-box methods, the proposed IMMNet
algorithm not only can preserve the
Bayesian inference mechanism that is essential for real-time radar applications, but also can adaptively learn motion patterns and noise characteristics from data. Extensive experiments demonstrate that the proposed IMMNet
algorithm consistently outperforms the existing
algorithms across various scenarios, validating it as a robust, interpretable, and practical solution for maneuvering target tracking.
Read the full abstract ▾
All authors Yixuan Zhao, Chaoqun Yang, Lin Gao, Yongxiao Tian, Ting Yuan
Artificial Intelligence · Cross-listed from eess.AS
Cover First, Disagree Softly: Rethinking Mismatch-First Active Learning for Frame-Level Audio Classification
Shiqi Zhang and Tuomas Virtanen
Sound event detection relies on frame-level strong labels whose annotation is expensive. Active learning addresses this problem by selecting the audio segments whose labels help the classifier most. One of the prevailing acquisition strategies for this task, mismatch-first farthest-traversal (MFFT), combines the disagreement between two classifiers and the diversity of the selected segments through hard sequential decisions. It selects whole groups of high-disagreement segments first and spreads only the remaining budget by farthest traversal. On two multi-label
datasets we show that this design is blind to the similarity among the selected segments and fails under low budgets, with every mismatch-first variant ending below the plain
geometric strategy it builds on. We propose mismatch-weighted facility location (MW-FL), which spends the entire budget through a disagreement-weighted coverage objective that penalizes similarity among the selected segments. The disagreement signal from MFFT is used to obtain the nonnegative weights of this facility-location objective, using fixed smoothing without
dataset-specific tuning. Experiments across two
geometric mechanisms with three ways of using disagreement show that coverage of the selected segments is the dominant factor, hard disagreement gating of selection is harmful on both mechanisms, and soft disagreement weighting helps on top of coverage. MW-FL attains the best area under the learning curve on both
datasets.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
GHR-VLM: Making Zero-Shot Transit Video Analytics Realizable with Grounded Hybrid Reasoning
Kaicong Huang, Weiheng Oh, Jack M. Reilly et al. (+2 more)
Transit
video understanding can provide valuable fine-grained data that conventional passenger counters and fare systems cannot capture. However, supervised
video models require task-specific annotations, while applying
vision-
language models (VLMs) directly to long onboard
videos is unreliable and costly. To leverage the complementary strengths of both approaches, we propose GHR-VLM, a visual grounded hybrid
reasoning framework for zero-shot transit-bus
video analytics. It is motivated by the observation that explicit visual grounding can improve VLM
reasoning by converting long surveillance streams into compact, passenger-centered spatiotemporal evidence. Specifically, we propose an edge-cloud design in which a lightweight edge-based monitor continuously tracks door status and segments passenger clips. A backend VLM then identifies boarding passengers and classifies payment behavior through a two-stage coarse-to-fine refinement of spatiotemporal evidence. By invoking the VLM only on grounded passenger clips and contact sheets, GHR-VLM reduces cloud inference, avoids payment-specific training data, and supplies the localized evidence that VLMs otherwise struggle to identify. Evaluation on 486 minutes of real-world bus surveillance
video demonstrates the potential of grounded edge-cloud
reasoning for passenger-level payment analytics while highlighting the challenges posed by degraded
video conditions.
Read the full abstract ▾
All authors Kaicong Huang, Weiheng Oh, Jack M. Reilly, Thomas Guggisberg, Ruimin Ke
Artificial Intelligence · Cross-listed from math.NA
Spectral-Informed Neural Networks Outperform Spectral Methods in High-dimensional PDEs
Tianchi Yu and Ivan Oseledets
For low-dimensional problems ($d\leq3$), spectral methods can achieve exceptionally high accuracy. For middle-dimensional problems ($4 \leq d \lesssim 10$), spectral methods remain feasible through specific techniques such as sparse grids or
hyperbolic cross. However, for high-dimensional problems ($d\gg 10$), spectral methods suffer frome the curse of dimensionality. Physics-informed neural networks (PINNs) have emerged as a promising approach to overcome this challenge, offering scalability to high dimensions, but often suffer from limited accuracy and efficiency. Recently proposed spectral-informed neural networks (SINNs) combine spectral methods with PINNs, operating directly in the spectral domain to avoid spatial derivative computations and to reduce
memory consumption. In this work, we introduce Modified SINNs, which integrate coefficient decay scaling and basis
embeddings motivated by harmonic analysis to enhance accuracy in high-dimensional problems and enable accurate approximation of unknown spectral coefficients. Numerical experiments on steady and time-dependent partial differential equations demonstrate that Modified SINNs outperform sparse grid spectral methods on middle-dimensional problems with incomplete spectral information and achieve superior accuracy compared to PINNs on high-dimensional problems.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
UTS at ELOQUENT 2026 Voight-Kampff: structural shifts in AI writing bypass state-of-the-art detectors
Dima Galat and Marian-Andrei Rizoiu
We investigate which
language model evasion attacks survive state-of-the-art
adversarial fine-tuning, developing strategies that sweep the top 5 positions on the ELOQUENT 2026 Voight-Kampff leaderboard. While
adversarial fine-tuning trivially closes the 2025 winning evasion recipes, we uncover a fundamental asymmetry in detector vulnerability: pushing generated text out of the detector's training distribution reliably defeats
adversarial detection, whereas pulling it into the distribution (e.g., mimicking human training data) fails completely. Exploiting this, we introduce two novel out-of-distribution attack families - cross-decade register attacks and modernist stream-of-consciousness form. Both strategies easily bypass
adversarial closure, achieving up to approximately 50x higher fool rates than previous methods while preserving naturalness. Furthermore, experiments show that the obvious deployer countermeasure (augmenting training data with period prose) fails to close the vulnerability. Our findings show that the tested detector families, including adversarially fine-tuned ones, exhibit persistent vulnerabilities under structural out-of-distribution shifts, a mechanism that directly powers our leading competition performance.
Read the full abstract ▾
Artificial Intelligence
AI advice suppresses people's willingness to say "I don't know", even when the advice is wrong and accuracy is incentivized
Chiara Marcoccia, Walter Quattrociocchi and Valerio Capraro
Knowing when to say "I don't know" is fundamental to human judgment, yet AI assistants offer a fluent answer to almost any question. In five experiments (N = 3,132; four preregistered, one direct replication), participants answered difficult questions and could always decline to respond. We engineered the questions so that AI advice was wrong, separating AI use from its accuracy. Merely having access to AI nearly eliminated participants' willingness to suspend judgment, and this held whether the advice was actively requested or simply displayed. Consequently, participants answered more questions but were correct about a third as often as when AI was unavailable-yet their confidence nearly doubled. Incentivizing accuracy and penalizing inaccuracy led participants to seek and follow AI advice less, answer more accurately, and suspend judgment more often, though still far less than when AI was unavailable. As AI suggestions grow ubiquitous and unsolicited, they may not simply affect answer accuracy; they may even alter the metacognitive threshold at which people decide whether they know enough to answer.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from q-bio.NC
Grounded world models in biological organisms and future embodied AI
Giovanni Pezzulo, Davide Nuzzi, Marco D'Alessandro et al. (+3 more)
Recent advances in generative and
embodied AI have been driven by large-scale predictive learning over
multimodal data. However, the resulting systems remain largely based on passive training regimes where linguistic regularities create the scaffold onto which information from other modalities is attached. Conversely, neuroscience and cognitive science suggest that biological intelligence is organized in the opposite way, where grounded world models acquired through interaction with the environment provide the semantic scaffold to which
language is attached. Here, we illustrate five examples of neural
circuits supporting grounded world modelling, which underlie
navigation in physical and conceptual spaces, affordance-based perception and interaction with objects, active perception and exploratory learning, allostatic control and
emotion, and the distinction between self- and world-generated outcomes. These examples highlight several features largely missing from current
embodied AI, including the role of intrinsic dynamics as a foundation for learning, the centrality of action in aligning these dynamics with the external world, the prominence of autonomous experience and open-ended learning over passive assimilation of externally provided data, and the fact that early predictive and control mechanisms scaffold higher cognitive abilities such as
reasoning, conceptual
navigation, planning, imagination, understanding others' minds, and communication. Finally, we discuss whether and how principles derived from biological systems may inform future
embodied AI, including training regimes based on social interaction to construct world models that are not only grounded but also socially shared and aligned with human norms and values.
Read the full abstract ▾
All authors Giovanni Pezzulo, Davide Nuzzi, Marco D'Alessandro, Riccardo Proietti, Roberto Bottini, Paul Cisek
Artificial Intelligence
Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling
Xixuan Hao, Yutian Jiang, Jiabo Liu et al. (+4 more)
Urban region profiling constitutes a core problem in urban computing, supporting applications such as population estimation, economic assessment, and environmental monitoring. Existing methods typically formulate this task as
multimodal representation learning, fusing heterogeneous urban data, e.g., satellite imagery, points of interest, textual descriptions, and 3D building information, into latent
embeddings for prediction. However, these approaches are largely correlation-driven, assume cross-modal consistency, and rely on static pipelines, which limit their robustness in heterogeneous or unseen urban regions. We propose UrbanAgent, an agentic framework that reframes urban region profiling as a
reasoning-driven inference problem. UrbanAgent instantiates an independent
agent for each data modality and performs structured multi-
agent collaborative
reasoning to explicitly address cross-modal inconsistencies rather than absorbing them into a single representation. In addition, UrbanAgent extends indicator prediction as a closed-loop process of active evidence acquisition and iterative
reasoning, enabling
agents to verify uncertain inferences through tool-augmented
retrieval of external knowledge optimized via reinforcement learning. Extensive experiments on global urban
datasets for Carbon emissions, GDP, and Population estimation show that UrbanAgent consistently outperforms existing baselines, achieving an average improvement of 8.1% in R2, and exhibiting strong generalization performance in unseen-city settings.
Read the full abstract ▾
All authors Xixuan Hao, Yutian Jiang, Jiabo Liu, Yihang Yang, Guangyin Jin, Song Gao, Yuxuan Liang
Artificial Intelligence · Cross-listed from eess.AS
Greedy Volume Maximization of Gradient Embeddings for Long-Tailed Frame-Level Bioacoustic Active Learning
Shiqi Zhang, Marius Faiß, Ariana Strandburg-Peshkin et al. (+1 more)
Bioacoustic call-type classification relies on costly expert annotation. Active learning can reduce this burden by selecting a small batch of segments for expert annotation and using the labeled segments for training the classifier. The setting is hard: the target calls are extremely sparse and the call-type distribution is long-tailed, so a tight budget must be spent on the few rare, informative segments. We propose BADGE-Greedy-DPP, a deterministic batch selector that greedily adds the segment whose BADGE gradient
embedding most enlarges the volume spanned by the batch; because this log-volume objective is submodular, the greedy rule guarantees a batch value at least a (1-1/e) fraction of the optimum of this objective, a guarantee not provided by BADGE's existing k-means++ and MCMC DPP sampling heuristics. There is also a temporal granularity mismatch in the task. The acquisition function scores whole segments, yet the informative frames inside them are few. Uniform averaging therefore washes them out. The BADGE construction naturally addresses this mismatch when applied frame-wise, as prediction residuals weight the aggregated pseudo-gradient, so confidently predicted no-call frames contribute little while a single uncertain rare-call frame can still set the segment's direction. Across 10 runs on a sparse, imbalanced hyena call-type
dataset, BADGE-Greedy-DPP achieves the best overall and rare-call-type performance among all compared query strategies, including MFFT, the strongest non-BADGE baseline, and the two vanilla BADGE traversals.
Read the full abstract ▾
All authors Shiqi Zhang, Marius Faiß, Ariana Strandburg-Peshkin, Tuomas Virtanen
Artificial Intelligence
How Far Can Root Cause Analysis Go on Real-World Telemetry Data?
Athira Gopal and Ashwanth Krishnan
Root cause analysis (RCA) of microservice failures requires
reasoning over telemetry far larger than a model's context, so a
language agent reasons over extracted evidence. We start from an error analysis of such an
agent on OpenRCA. A reverse
reasoning agent reconstructs an evidence chain to each labelled cause and compares it against the
agent's own trace, locating failures where a grounded chain existed but was not followed; its labels agree with two site reliability engineers. Being label-conditioned, it audits evidence rather than testing forward identifiability, leaving open what the
agent lacked: procedure or telemetry-specific knowledge. Existing systems cannot separate them, extracting evidence inside the
reasoning loop. We compute the evidence once, offline, and supply it identically to every arm. Rules mined from the audit reports of one
Market cloudbed raise Full Score on a held-out cloudbed from 14.10 to 35.90, surviving correction for multiple testing, against 24.36 for manual rules and 19.23 for a label-and-schema control. The rules add 17 solved cases on top of the five-step procedure but 11 without it, the repairs overlapping. Removing the procedure raises Full Score in all three conditions tested, though no contrast survives correction. Deleting only its earliest-onset criterion yields a net gain of 8 cases against 11 for the whole procedure, which we report descriptively. Mining is label-supervised, and all results are specific to OpenRCA.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
ExTernD: Expanded-Rank Ternary Decomposition Ternary LLM PTQ with Accuracy Approaching Any Quantization Level
Chethan Reddy G.P
We introduce ExTernD (Expanded-rank Ternary Decomposition), a post-training factorization of each LLM weight
matrix $A \in \mathbb{R}^{m \times n}$ into $A \approx B \mathrm{diag}(D) C$ with ternary factors $B \in \{-1,0,+1\}^{m \times k}$, $C \in \{-1,0,+1\}^{k \times n}$ and a real scale vector $D \in \mathbb{R}^k$. The inner rank $k = \mu \min(m,n)$ is deliberately expanded beyond full rank ($\mu > 1$), so that components past full rank correct the quantization error of earlier ones. We prove the residual decreases monotonically in $k$ and can be driven below any $\varepsilon > 0$: ExTernD approaches bf16 accuracy arbitrarily closely, which no ternary scheme with a fixed plane count can do.
Memory and compute scale continuously with $\mu$, and factor sparsity continuously with a threshold $\tau$, so an accuracy target is hit exactly rather than rounded to the next bit-width. ExTernD matches Q4_K's per-
matrix accuracy at 5.2-5.5 effective bpw (5.1-5.5 with importance weighting) on Gemma-4-E2B and Qwen3.5-4B, and a full Qwen3.5-4B conversion at $\mu = 3$ reaches 10.10 wikitext-2 perplexity against 9.78 for bf16 (+3.2%), placing it near the Q4_K/Q5_K accuracy band at ~5.7 effective bpw.
Read the full abstract ▾
Artificial Intelligence
LOTAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning
Qiang Zhu, Jiajun Wu and Longyi Wang
Reinforcement learning for multi-turn search
reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions. We propose LOTAPO , a self-generated process-supervision method based on backward leave-one-turn attribution. For each search turn, LOTAPO replaces the turn and its
retrieval observation with a fixed [DELETE] placeholder and measures the resulting change in the current policy's mean log-likelihood of the gold answer. This Answer-Likelihood Gain estimates the turn's contribution while preserving all downstream interactions, allowing early evidence to be evaluated in the complete
reasoning context. LOTAPO further applies sign-consistency gating, retaining only normalized process advantages whose directions agree with their raw attribution scores. The method requires no additional reward model, teacher, verifier, or LLM-as-a-Judge. Across seven knowledge-intensive question-answering
datasets with local
retrieval, LOTAPO achieves an average exact-match score of 0.326, outperforming the strongest step-reward baseline, IGPO, by 0.053. Ablations show complementary benefits from backward attribution and sign-consistency gating, demonstrating that policy-derived retrospective attribution can provide effective process supervision for multi-turn search
agents.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
DeepLoop: Depth Scaling for Looped Transformers
Shuzhen Li, Yifan Zhang, Jiacheng Guo et al. (+2 more)
Looped
Transformers scale sequential computation by applying a compact stack of physical blocks for multiple rounds, increasing unrolled depth without increasing stored parameters. This reuse changes the residual-scaling problem: in an untied
Transformer, each residual branch receives and applies its own parameter update, whereas in a looped
Transformer one shared update aggregates gradients from repeated visits and is read back by those same visits in the next linearized forward pass. We formalize this tied-depth effect through a first-order perturbation bound controlled by a visit-
alignment coefficient $\kappa_R$. The bound recovers the DeepNorm exponent when visits decorrelate, but in the conservative aligned regime it requires the exponent to increase from $1/4$ to $1/2$ as loop count grows at fixed physical depth. The resulting method, DeepLoop, keeps the Post-LN DeepNorm architecture and sets $\alpha=(2N)^{1/2}$ and $\beta=(8N)^{-1/2}$ for unrolled depth $N$. On GPT-style looped
language models at GPT-2 small and GPT-2 medium scale, DeepLoop is neutral when no physical block is revisited and improves validation loss and downstream accuracy once recurrent depth is activated. These results show that stable recurrent depth requires residual scaling rules that account for parameter visits, not only nominal layer count.
Read the full abstract ▾
All authors Shuzhen Li, Yifan Zhang, Jiacheng Guo, Quanquan Gu, Mengdi Wang
Artificial Intelligence · Cross-listed from cs.LG
Explainable Artificial Intelligence for Anomaly Detection in Banking Transactions: An Internal Audit Perspective
Anupa Lodhi
The banking sector increasingly relies on automated systems to monitor electronic transactions for signs of fraud, yet conventional rule-based approaches struggle with high false-positive rates and offer no justification for their outputs, limiting their utility for compliance teams. This paper introduces an Explainable Artificial Intelligence (XAI) framework tailored for banking transaction anomaly detection within internal audit workflows. An Isolation Forest (iForest) model performs unsupervised anomaly scoring, while a SHAP (SHapley Additive exPlanations) layer provides transaction-level, feature-attributed explanations grounded in cooperative game theory [8]. A lightweight Streamlit dashboard renders these outputs in a form accessible to audit professionals without machine learning expertise. Evaluation on a synthetic banking
dataset yields 0.91 precision and 0.88 recall, outperforming three unsupervised baselines. Expert feedback confirms that feature-level explanations measurably improve auditor confidence and decision quality. The framework advances the practical deployment of accountable, transparent AI in regulated financial environments.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
DevicesWorld: Benchmarking Cross-Device Agents in Heterogeneous Environments
Huatao Li, Xinwei Geng, Yuheng Wang et al. (+9 more)
LLM-based
agents have rapidly improved at operating individual digital environments such as mobile applications, desktop systems, and smart homes. However, real-world user goals often span multiple devices: information may come from a phone, be processed on a desktop, and the result may need to appear on another device. Most existing
benchmarks center on a single dominant execution environment, making it difficult to evaluate whether
agents can acquire and integrate information across heterogeneous devices and complete end-to-end tasks with cross-device dependencies. We introduce DevicesWorld, a large-scale executable
benchmark for cross-device collaborative operation. DevicesWorld contains 6,140 tasks and integrates three classes of device environments – mobile, desktop, and IoT – into a unified cross-device interaction and evaluation framework. Each task defines a natural-
language user goal, participating devices and initial states, executable actions, rule-based verifiers, and a cleanup procedure. A multi-stage construction and quality-control pipeline keeps tasks close to realistic user needs while allowing final outcomes to be automatically verified from device states and generated files. We evaluate five frontier LLM-
agent systems on a fixed evaluation set. All methods achieve low success rates, with the best reaching only 12.5%. Among failed runs, about 28.7% satisfy at least one scoring condition yet still fail the full task. Trajectories show that
agents become stuck acquiring information or manipulating interfaces, confuse source and output devices, or terminate before all conditions are jointly satisfied. DevicesWorld turns cross-device collaborative operation into an executable, reproducible, and diagnostically useful evaluation problem for research on reliable cross-device
agents.
Read the full abstract ▾
All authors Huatao Li, Xinwei Geng, Yuheng Wang, Yutong Li, Runde Yang, Hantao Chen, Shu Yao, Jingru Fan, Xuhui Ren, Yuanyuan Zhao, Fei Huang, Chen Qian
Artificial Intelligence · Cross-listed from cs.CV
GeoAnchor: Collaborative Reasoning via Latent Decomposition for 3D Spatial Understanding
Hao Li, Han Fang, Zixin Pan et al. (+8 more)
Although
multimodal large
language models (MLLMs) have achieved remarkable progress, understanding 3D spatial relationships from 2D images remains a critical challenge. Existing methods primarily rely on symbolic text
tokens, which inherently lack the fidelity to represent continuous
geometric information. While recent methods use latent representations to enhance
reasoning, relying on a single latent type cannot adapt to the diversity of spatial tasks, leading to misalignment in complex
geometric scenarios. To address these limitations, we propose GeoAnchor, an interleaved text-latent
reasoning framework. GeoAnchor decomposes 3D spatial information into three complementary components: position latents for object grounding, direction latents for relational orientation, and geometry latents for scene structure. These components are recombined in a structured space to construct local evidence while capturing global context, enabling dynamic and interpretable
reasoning. Furthermore, we introduce a collaborative training strategy that guides the model from local spatial perception to comprehensive 3D understanding. Extensive experiments on diverse and complex 3D
reasoning tasks demonstrate that GeoAnchor outperforms the state of the art, validating its effectiveness and generalization capabilities.
Read the full abstract ▾
All authors Hao Li, Han Fang, Zixin Pan, Xin Wei, Hongbo Sun, Jinglin Xu, Zhiyu Lin, Ye Yuan, Zhongjiang He, Yu Yu, Hao Sun
Artificial Intelligence · Cross-listed from cs.CR
Adversarial Prompting Framework for AI Safety Assessment
Yash Bhatnagar, Kunal Banerjee and Anirban Chatterjee
Artificial Intelligence (AI), especially Generative AI (GenAI), adoption has increased in industries significantly in recent years. However, the use of these models may also expose systems to new forms of cyberattacks by different malicious actors –
adversarial prompt attack (APA) being one of the most prominent examples of such threats. This paper presents the implementation of an
Adversarial Prompting Framework (APF) for a comprehensive assessment of AI safety. The framework systematically evaluates the resilience of the AI model through the generation of structured
adversarial prompts at multiple sophistication levels, from direct harmful requests to advanced encoding-based attacks. Our implementation demonstrates the practical application of this methodology in enterprise environments, providing automated testing capabilities with quantitative security assessment metrics. The results indicate significant variations in the model vulnerabilities across different attack vectors, with encoded
prompts presenting the highest success rates in bypassing safety mechanisms.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Symbiosis-Inspired Knowledge Distillation for Incremental Object Detection
Mingyue Zeng, De Cheng, Zhipeng Xu et al. (+3 more)
Incremental object detection (IOD) aims to extend detectors to new categories while retaining previously acquired knowledge. Existing methods often adopt a class incremental learning perspective, separating feature spaces to sharpen decision boundaries. However, this separation-oriented paradigm may overlook object symbiosis in detection, where co-occurrence and occlusion introduce spatial and semantic dependencies that benefit from shared representations. Ignoring these dependencies distorts the shared representations, exacerbates confusion between old and new classes, and accelerates catastrophic forgetting. To address this, we propose Symbiosis-Inspired Knowledge
Distillation (SIKD), which explicitly leverages object symbiosis at two complementary levels. Spatial Symbiosis
Distillation (SpSD) focuses on symbiotic regions where the old model responds with high overlap to objects in the new task. It preserves generalizable old class cues, suppresses class-specific bias and redundancy, and distills the refined evidence to the new model at matched spatial locations with slot-aligned supervision. Semantic Symbiosis
Distillation (SeSD) maintains class level structure by forming confidence weighted prototypes for old classes and aligning their inter class soft ranks over the old class logits, which stabilizes the semantic
topology during adaptation. Extensive experiments demonstrate the effectiveness and superiority of the proposed method.
Read the full abstract ▾
All authors Mingyue Zeng, De Cheng, Zhipeng Xu, Huaijie Wang, Nannan Wang, Xinbo Gao
Artificial Intelligence · Cross-listed from cs.RO
Learning Physics-Guided Residual Dynamics for Deformable Object Simulation
Shivansh Patel, Kaifeng Zhang, Sanjay Pokkali et al. (+2 more)
Simulating deformable objects is essential for a wide range of robotic manipulation applications, yet accurately predicting their dynamics remains challenging. We propose Physics-Guided Residual Dynamics (PGRD), a hybrid simulation framework that combines the advantages of physics-based and learning-based approaches. Specifically, PGRD combines an optimizable spring-mass simulator as a backbone with a learned neural network that predicts residual corrections to the physics-based predictions. We adopt a velocity-based formulation to ensure stable simulation and a sliding-window
transformer architecture to capture temporal dependencies. We show that PGRD produces more accurate results than both purely physics-based and learning-based methods on a set of diverse real-world deformable objects. We further demonstrate the utility of PGRD in two applications: manipulation planning via Model Predictive Control, including a
language-conditioned setting with a generated goal image; and interactive simulation via action-conditioned
video prediction by 3D Gaussian Splatting.
Read the full abstract ▾
All authors Shivansh Patel, Kaifeng Zhang, Sanjay Pokkali, Svetlana Lazebnik, Yunzhu Li
Artificial Intelligence · Cross-listed from cs.LG
Discrete Diffusion Models: A Unified Framework from Tokenization to Generation
Ye Yuan, Weien Li, Rui Song et al. (+20 more)
Discrete denoising
diffusion models (DDMs) have recently emerged as a compelling alternative to autoregressive (AR) modeling for discrete data, offering parallel generation and iterative global refinement capabilities. Unlike continuous
diffusion, where the state space is fixed, DDMs are fundamentally shaped by how the discrete state space is constructed: the tokenization scheme, the vocabulary
topology, and domain-specific structural alphabets. This work introduces a unified conceptual framework that views discrete
diffusion models through the construction of the underlying discrete state space. Within this framework, existing formulations, including transition-
matrix, masking/absorbing-state, and score/ratio-based approaches, emerge as different instantiations of a common design space. The framework further exposes common design trade-offs across training objectives, inference
algorithms, scaling behavior, systems optimization, and evaluation protocols, suggesting several promising directions for future research.
Read the full abstract ▾
All authors Ye Yuan, Weien Li, Rui Song, Zeyu Li, Haochen Liu, Xiangyu Kong, Zixuan Dong, Linfeng Du, Zipeng Sun, Weixu Zhang, Jiaxin Huang, Changjiang Han, Yonghan Yang, Zichen Zhao, Xiuyuan Hu, Haolun Wu, Yankai Chen, Fengran Mo, Jikun Kang, Bowei He, Dawn Song, Philip S. Yu, Xue Liu
Artificial Intelligence · Cross-listed from cs.LG
Data-Efficient Adaptation of LLMs via Attention Head Reweighting
Tuomas Oikarinen, Zixiao Chen, Charlotte Siska et al. (+3 more)
Learning effectively from limited data is critical in domains like security where labeled examples are scarce. Large
language models (LLMs) have demonstrated some capabilities for data-efficient learning, especially through parameter-efficient adaptation methods, but continue to struggle when faced with few samples for difficult tasks. To meet this challenge, we propose
Attention Head Reweighting (AHR), a data-efficient method that adapts LLMs to new text-classification tasks by learning only a single scalar per
attention head. This drastically reduces the number of parameters that need to be learned by making use of the functional specialization of individual
attention heads. Experiments on diverse open-source text classification
datasets show that AHR can outperform standard baselines like LoRA when learning from limited samples, despite having 200-1000x fewer trainable parameters, as our AHR only modifies ~0.0001% of the model's parameters. In addition, our learned weights are easy to interpret and can be analyzed to better understand the mechanisms and
attention heads responsible for in-context learning abilities in LLMs.
Read the full abstract ▾
All authors Tuomas Oikarinen, Zixiao Chen, Charlotte Siska, Tsui-Wei Weng, Chandan Singh, Jianfeng Gao
Artificial Intelligence · Cross-listed from cs.CV
ScanFocus: A Coarse-to-Fine Framework for Spatio-Temporal Video Grounding
Kai Chen, Ming Dai, Wenxuan Cheng et al. (+1 more)
Spatio-Temporal
Video Grounding (STVG) aims to retrieve the visual trajectory of a specific object from a
video stream as described by a natural
language expression. However, most advanced methods struggle to balance global context modeling with precise boundary localization. Due to the prohibitive computational costs of processing long
videos, these approaches typically resort to low-rate temporal downsampling and implicit motion modeling. This inevitably suppresses high-frequency boundary cues and neglects the explicit inter-frame dependencies required for precise boundary delineation. To address these limitations, we present ScanFocus, a novel coarse-to-fine framework that decouples the STVG task into a global spatio-temporal scan and a local boundary focus. Specifically, we utilize a unified
vision-
language fusion encoder combined with a lightweight Deformable Semantic-Motion Fusion module to efficiently align
multimodal features and generate coarse proposals. To recover the suppressed fine-grained details, we introduce the Semantic-Guided Temporal Aggregator (SGTA) in the refinement stage. By densely sampling around coarse boundaries, SGTA explicitly models short-term temporal interactions under semantic guidance, capturing rapid motion changes for precise timestamp regression. Extensive experiments on three widely used
benchmarks demonstrate the performance superiority of our proposed method over previous approaches. Code will be released at https://github.com/TenMinutes209/ScanFocus.
Read the full abstract ▾
All authors Kai Chen, Ming Dai, Wenxuan Cheng, Wankou Yang
Artificial Intelligence · Cross-listed from cs.IR
Can We Steer the Black-Box? Towards Controllability-Centric Evaluation of Recommender Systems with Collaborative Agents
Jiwen Zhou, Xiang Liu, Mingming Li et al. (+5 more)
Recommender systems operate as Black-Boxes, leaving users and regulators unable to steer their outputs toward specific intentions or audit their behavior. This lack of controllability, defined as the system's ability to respond to explicit guidance, remains an unaddressed dimension in existing evaluation paradigms. To fill this gap, we propose CtrlBench-Rec, a collaborative multi-
agent framework for systematic assessment of controllability. We formalize three fundamental tasks: target content discovery, interest profile shaping, and popularity bias mitigation, which together measure steerability from explicit commands to implicit representation steering and finally to overcoming algorithmic biases.Extensive experiments on real-world
datasets and multiple recommendation models demonstrate that our framework effectively quantifies controllability and exposes critical system bottlenecks, most notably persistent resistance to guiding long tail content. CtrlBench-Rec provides the first standardized toolkit for controllable recommendation research, algorithmic
auditing, and user empowerment. Our code is released on https://github.com/caskcsg/CtrlBenchRec.
Read the full abstract ▾
All authors Jiwen Zhou, Xiang Liu, Mingming Li, Pengbo Mo, Jiao Dai, Honglei Lv, Jizhong Han, Songlin Hu