Inference
-
POEM: Output-Relative Block-Sparse Attention for Long-Context Prefilling
2026-11-10 04:52:58Haoyi Wu, Yunkai Dang, Wanyu Zhang, Lei Wang, Wenbin LiAbstract
Large language models (LLMs) have shown strong capabilities across diverse applications, making both safety and utility essential for reliable deployment. Jailbreak attacks use diverse forms of adversarial prompting to bypass alignment safeguards and induce LLMs to generate harmful responses. Some representation-based defenses regulate internal activations using predefined steering directions or learned safety regions. However, adapting intervention to each input without a predefined representational target while limiting over-refusal remains a challenge. In this paper, we propose Target-free Entropy-guided Residual Modulation (TERM), an inference-time defense that uses prompt-calibrated attention entropy deviations to guide adaptive modulation of the model's own residual updates. Attention patterns vary across prompts and decoding steps, making raw entropy values difficult to interpret as a consistent signal for intervention. We therefore calibrate attention entropy against each prompt's own prefill baseline to establish an input-specific reference for reducing unnecessary intervention on benign requests. Adaptive scale normalization and temporal accumulation then account for differences in deviation scale and persistence to determine intervention strength. The resulting signal controls bounded scaling of the model's own residual updates, without relying on a predefined safety direction. We compare our method with seven defenses on seven jailbreak attacks and two over-refusal benchmarks across Llama, Qwen, and Gemma models, including Qwen3 models from 0.6B to 32B. Results show our method improves jailbreak robustness while maintaining low over-refusal on benign safety-sensitive requests with modest inference overhead.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13578
PDF
-
TERM: Target-Free Jailbreak Defense via Entropy-Guided Residual Modulation
2026-11-10 04:52:10Yunkai Dang, Wanyu Zhang, Meiyi Zhu, Qi Fan, Tianyu Ding, Wenbin LiAbstract
Large language models (LLMs) have shown strong capabilities across diverse applications, making both safety and utility essential for reliable deployment. Jailbreak attacks use diverse forms of adversarial prompting to bypass alignment safeguards and induce LLMs to generate harmful responses. Some representation-based defenses regulate internal activations using predefined steering directions or learned safety regions. However, adapting intervention to each input without a predefined representational target while limiting over-refusal remains a challenge. In this paper, we propose Target-free Entropy-guided Residual Modulation (TERM), an inference-time defense that uses prompt-calibrated attention entropy deviations to guide adaptive modulation of the model's own residual updates. Attention patterns vary across prompts and decoding steps, making raw entropy values difficult to interpret as a consistent signal for intervention. We therefore calibrate attention entropy against each prompt's own prefill baseline to establish an input-specific reference for reducing unnecessary intervention on benign requests. Adaptive scale normalization and temporal accumulation then account for differences in deviation scale and persistence to determine intervention strength. The resulting signal controls bounded scaling of the model's own residual updates, without relying on a predefined safety direction. We compare our method with seven defenses on seven jailbreak attacks and two over-refusal benchmarks across Llama, Qwen, and Gemma models, including Qwen3 models from 0.6B to 32B. Results show our method improves jailbreak robustness while maintaining low over-refusal on benign safety-sensitive requests with modest inference overhead.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13577
PDF
-
Control-Aware Command Generation for Asynchronous Control and Action Inference with Vision-Based Policies towards Fast Execution
2026-11-10 04:14:23Takayuki Osa, Kazuki OtaAbstract
Vision-based control policies, including vision-language-action models, have enabled robots to perform increasingly complex tasks. However, their execution speed is often limited by the high computational cost of action inference. In this work, we investigate what can be achieved at the control level without modifying the underlying policy learning process. We introduce an asynchronous inference and control framework that enables fast task execution while maintaining smooth and stable robot motions. By formulating the generation of continuous target positions from discontinuous model predictions as a tracking control problem, our method makes asynchronous inference practical for real robots. We further accelerate execution through adaptive action skipping based on the variance of predicted positions. Experiments with Action Chunking Transformer and OpenVLA-OFT on a bimanual robot demonstrate substantial speedups while preserving high task success rates.
Abstract (translated)
URL
https://arxiv.org/abs/2611.11089
PDF
-
Mobile AI Factory: Building Specialized Language Models for Your Mobile Device
2026-11-10 03:29:29Evan Li, Krishna Deshpande, Wen Cheng, Shyamnath GollakotaAbstract
Small language models (SLMs) running on mobile devices can keep user data private and work without connectivity. But they perform well only when fine-tuned for the target task and sized for the target device, a process that today requires repeated expert tuning. We present {\it Mobile AI Factory}, an agentic system that builds a fine-tuned, quantized SLM for a given task and phone. Given a task specification and a target phone, an orchestrator LLM chooses whether to tune hyperparameters, mine real data, or generate synthetic examples, while fixed rules roll back changes that hurt accuracy. The factory searches from small to large models across base models and quantizations, adapts its accuracy goal as it searches, and uses real measurements of the target phone across inference engines and backends. We evaluate Mobile AI Factory on ten tasks and four Android phones. On an unseen testset, its on-device models outperform two five-shot frontier models on five tasks, by up to 0.34, and match them on three more. Its search comes within 0.03 of exhaustively training all 27 model variants on an entity extraction task, while using 19$\times$ less GPU time. Phone measurements also matter: the best configuration changes across phones. Without phone measurements, Claude Opus 5.5, given the full hardware and model specifications, misses the app's requirements in 25\% of easy and moderate cases and in 60\% of hard ones. Code is available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13509
PDF
-
Hand-Object Contact Transition Detection in Egocentric Video
2026-11-10 02:52:29Huy Anh Nguyen, Chang Dong, Feras Dayoub, Minh HoaiAbstract
This paper tackles the task of hand-object contact transition detection in egocentric video, which aims to localize the two temporal boundaries of a contact episode: the moment a hand first establishes contact with an object (touch) and the moment contact is released (release). We propose a unified framework that jointly models the interacting hand and object to accurately localize both transition types. The proposed framework augments hand-centric spatiotemporal representations with object-aware features learned directly from the video and introduces a transition-aware event spotting formulation tailored to contact transitions, without relying on external object or hand-object interaction detectors during inference. To support this task, we present ContactTransition, a dataset comprising 4,021 egocentric videos with 8,498 touch and 8,077 release annotations, together with object-of-interest supervision. Experiments demonstrate that the proposed method consistently outperforms strong two-stage and end-to-end event-spotting baselines on both transition types. Finally, we show that detected contact transitions provide effective temporal anchors for downstream egocentric hand-object reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13486
PDF
-
Sharp Sample Complexity of KL-Regularized Reinforcement Learning
Abstract
KL-regularized reinforcement learning, the objective behind maximum-entropy RL and RL from human feedback, is variational inference in the graphical model of "control as inference": the regularized optimal policy is a posterior over trajectories, and the suboptimality of a policy is $\beta$ times a KL divergence between path measures. However, it is not known how many samples it takes to learn this posterior, even with a generative model. Earlier $1/\epsilon$ guarantees scale with $H^5$ in the effective horizon $H$, and no lower bound for MDPs depends on the temperature $\beta$. In this work, we show that for a discounted MDP with $K$ state-action pairs, the plug-in estimator finds a policy that is $\epsilon$-optimal from every initial state with $\widetilde{O}(KH^3/(\epsilon\max\{\epsilon,\beta\}) + KH)$ samples, and that no algorithm, even one that chooses where to sample, can do with fewer when $\epsilon \lesssim \min\{H, H^2/\beta\}$. For $\epsilon < \beta$ this is a $1/\epsilon$ rate with the same horizon dependence as unregularized RL. We also find the exact asymptotic constant of the plug-in estimator, a Fisher-weighted variance of the estimated soft Q-function. The estimator is locally asymptotically minimax among methods that sample every pair equally often, and we give the allocation of samples that is optimal among adaptive designs. Simulations on small MDPs match the rates and the constants.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13480
PDF
-
BioMem: Agentic Memory for Biomedical LLM Agents
2026-11-10 01:09:11Mingchen Li, Yongkang Xiao, Rumeng Li, Rui Zhang, Hong YuAbstract
Large language models (LLMs) have demonstrated considerable potential in biomedical applications, while agentic memory systems have emerged as a promising approach to preserving and utilizing information across tasks and interactions. However, a fundamental question remains: how effectively and reliably do these systems retain, retrieve, update, and utilize biomedical information? In this study, we systematically investigate agentic memory in the biomedical domain, focusing on task effectiveness, retrieval quality, information fidelity, and long-term robustness. We evaluate five memory approaches across four LLMs in three representative settings: biomedical knowledge reasoning, clinical prediction, and long-term conversational memory. Our analyses reveal how memory construction, evidence relevance, and conversational history shape downstream biomedical performance, highlighting the distinct challenges of retrieving relevant information, preserving its fidelity, and effectively utilizing it for reasoning. Building on these findings, we introduce Hybrid Memory Retrieval and Utilization (HMRU), a training-free framework that jointly enhances evidence accessibility and task-aware utilization to improve biomedical reasoning and long-term conversational memory. HMRU achieves an average relative improvement of 8.6% across biomedical question-answering and conversational memory benchmarks, with additional gains in selected clinical prediction tasks. It further reduces conversational answer errors by 24.9% and closes 48.0% of the performance gap to full-context inference. Our findings provide a systematic characterization of biomedical agentic memory and practical insights into developing more effective and reliable memory-augmented LLM systems.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13426
PDF
-
Bursts That Outlast Themselves: Persistent Degradation in Prefix-Cached Agent Serving
Abstract
LLM agents drive inference engines with closed-loop sessions whose context grows every turn, and serving them economically depends on prefix caching: a hit costs an incremental prefill of about a thousand tokens, a miss recomputes a 10--40K-token context. We show that this makes prefix-cached agent serving metastable. With an identical base workload, a few minutes of extra arrivals leaves a vLLM server in a degraded regime--a ~10% hit ratio, about half the throughput, and a backlog that grows for the remaining 70 minutes--while its no-burst twin stays healthy (9 of 12 pairs; none in the reverse direction). The regime appears at loads the cache-warm server sustains, is absent without prefix caching, and also appears with Qwen3-32B on SWE-bench agent trace shapes and on SGLang, which tolerates larger triggers. Slower service keeps more sessions in the system, their working set outgrows the KV pool, and every turn becomes a recomputation; a first-order workload-balance condition, calibrated independently, brackets when the regime can drain. Getting out is the harder problem: throttling new admissions recovered 1 of 7 matched collapsed runs, while suspending admitted sessions against a capacity-based limit recovered all of them within minutes. A CPU offload tier delays the collapse but does not prevent it. A budgeter that bounds the resident KV demand of active sessions to the pool, with thresholds that need no per-workload tuning, prevented the failure in every run we tested.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13412
PDF
-
SteerDistill: Quantizing LLM Agents via Closed-Loop Teacher Steering
2026-11-10 00:45:58Genming Cui, Xiangyu Li, Zixu Hao, Xin Ding, Yunxin Liu, Ting CaoAbstract
Low-bit quantization reduces the inference cost of LLM agents but can compromise task success. Examining failed rollouts, we find that quantized agents overlook task requirements or environmental conditions, producing environment transitions that diverge from successful full-precision references. Correcting these behavioral divergences remains difficult: offline data may miss the student's failure contexts, while its own rollouts may provide few correct responses in those contexts. We introduce SteerDistill, a quantization-aware distillation method in which a full-precision teacher guides the student to revise failed responses and iteratively refines its guidance using feedback from student execution. This closed-loop teacher steering produces locally verified behavioral corrections. We internalize these corrections by training the student without guidance to match the steered student's predictions at corrected turns and the full-precision teacher's at other turns, enabling unassisted inference. Across five agentic benchmarks and three models, SteerDistill exceeds the strongest quantized baseline by 1.67--2.18 points in average score under W4A16 and stays within one point of BF16. On $\tau^2$-Bench, it outperforms QeRL by 1.84 percentage points in success rate using 67% fewer training GPU hours and produces shorter successful trajectories than the quantized baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13410
PDF
-
Stinging the Swarm: Extracting Attacker Intelligence from a Twin-Controller OT Honeypot
2026-11-10 00:38:48Canyon Grey Dell'Omo, Joao Pedro de Carvalho VoltaniAbstract
Autonomous language-model agents can drive industrial controllers over fieldbus protocols, probing a plant at machine speed and in coordinated swarms. We present Talos, an inline gate that judges every agent request to a controller in milliseconds and routes agents it flags as hostile to a device-faithful decoy -- a mirror twin of the real plant -- where their attack continues harmlessly and is read for intelligence. We evaluate the full pipeline (detect -> quarantine -> mirror -> extract) against 2,400 autonomous attacker agents, 600 in each of four tiers that escalate the attacker's effort to stay hidden, from no concealment to an explicit non-disclosure rule and a trained cover story. No write reached the real plant in any tier: the gate denies the damage path and a device-level envelope check backstops it, while unmapped registers are denied without exception and the gate still permits safe-direction stop commands. Decisions are model-driven in every tier with no inference timeouts, closing a common objection to small on-device judges. Beyond blocking, the pipeline reads the attacker. We find a behavioral structure along two axes -- how persistently an agent attacks and how much it discloses -- and show that the system has a capture channel for three of the four resulting regions: hardened, silent attackers escalate most and are read on the mirror; compliant, talkative attackers volunteer their identity to a diagnostic form before they are ever quarantined; only the paranoid, low-yield region resists both. Attacker identity fields are self-authored cover stories, but involuntary tells -- the self-reported toolchain fingerprint and the attacker's own list of targeted registers -- accumulate across the swarm into a high-confidence profile drawn from agents under explicit orders to stay silent. The gate, mirror, and harness are released under Apache 2.0 with a synthetic device family.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13406
PDF
-
Knowing When to Intervene: Causal Evaluation of AI Agents
2026-11-10 00:34:33Ayush Sawarni, Wenqian Xing, Tijana Zrnic, Ramesh Johari, Vasilis SyrgkanisAbstract
Current evaluations of agentic AI systems primarily rely on benchmarks. However, the static nature of benchmarks makes them uninformative about the value of auditing interventions at deployment time. For reliable deployment, we often need to determine within an agent's trajectory whether or not to intervene, e.g., by verifying the agent's current output or steering it toward different behavior, using either human review or more costly models or time-consuming agentic supervision. The value of such interventions is fundamentally a causal inference question, asking whether the causal effect of such an intervention is beneficial for the final outcome. Estimating this causal effect is particularly challenging due to the dynamic nature of the problem: the impact of an intervention depends on the current context and environment, as well as the agent's future behavior. We develop the first methodologically grounded framework for evaluating the causal effects of randomized interventions within agent trajectories. By leveraging a relatively small dataset of agent trajectories collected under randomized interventions such as verification or screening, we can estimate the dynamic causal effect of a rich class of (contextual) intervention policies. The structural parameters that we estimate can also be used to construct safety leaderboards that capture the risk of various agentic actions, which can be used by practitioners for audit prioritization. Applying our methods to tau-bench Retail, ToolSandbox, and ImpossibleBench, we find that intervention effects vary substantially across agent actions and states. More broadly, our work suggests a rich research agenda at the intersection of causal inference and agentic evaluation, which we believe is essential for the reliable and safe deployment of AI agents in the real world.
Abstract (translated)
URL
https://arxiv.org/abs/2611.09792
PDF
-
How Hyperbolic Are Hyperbolic Vision-Language Models?
2026-11-10 00:01:33Freek Byrman, Partha Das, Stijn Verdenius, Pascal MettesAbstract
Hyperbolic vision-language models (VLMs) have emerged as a rapidly growing area of research, reporting strong zero-shot performance alongside an interpretable embedding space in which radius orders representations by generality. But how hyperbolic are hyperbolic VLMs in practice? We investigate this at the exponential map, the single operation through which curvature enters an otherwise Euclidean network. We show that across MERU, HyCoCLIP, ARGENT, and PHyCLIP, the exponential map is well approximated by the identity function, i.e., pairwise distances and angles in the pre-map Euclidean space barely change under projection, and removing the map at inference leaves evaluation scores unchanged. Motivated by this observation, we train Euclidean VLMs on CC3M from scratch under the same hierarchy losses. Over roughly the final 90% of the training steps, the training statistics are nearly indistinguishable from those of their hyperbolic counterparts, and the resulting models match the evaluation scores and recover the same radial distributions. Our findings establish Euclidean space as a sufficient substrate for hierarchical vision-language learning as it is currently practiced, and motivate new paradigms in which hyperbolic geometry can deliver on its theoretical promise. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13384
PDF
-
F3-AGI v4.0: Bioenergetically-Gated Active Inference, Metaplastic Preconditioning, and Residual Program Synthesis for Sample-Efficient Abstract Reasoning
2026-11-09 22:47:43Henrique OliveiraAbstract
Few-shot abstract reasoning on ARC-AGI requires inducing algorithmic transformations from 2 to 5 demonstration pairs without task-specific pretraining. Because few-shot demonstrations under-constrain the hypothesis space, program synthesis suffers from the Rashomon effect (predictive multiplicity): heuristic search finds spurious programs with low training error that fail on test inputs, while unconstrained library growth degrades latency. We introduce F3-AGI v4.0, a CPU-native neuro-symbolic and active inference architecture comprising three mechanisms: (1) F3-Metabolic-Optim, combining mistake-gated plasticity, Fisher-EMA preconditioning, and virtual ATP gating; (2) Adaptive Complexity-Guided Program Synthesis (AACR) with a Cycle-3 ResidualPatchSynthesizer and smallest-pair early rejection; and (3) a 512D L2-normalized random projection driving Expected Free Energy (EFE) exploration with dead-signature pruning. Across three empirical studies: (i) on a synthetic 5-task class-incremental stream without replay, F3-Metabolic-Optim achieves 91.67% final accuracy with 9.17% forgetting, skipping 93.47% of updates, cutting L1 plasticity cost by 65.7%, and running 2.19x faster than EWC; (ii) on the 400-task ARC-AGI-1 public evaluation set (offline CPU, zero LLM calls), F3-AGI v4.0 solves 57/400 tasks (14.25% pass@2; 56/400 pass@1) with a mean latency of 1.62 s/task, decomposed into 19/50 (38.00%, 1.19 s/task, a 42.5x paired speedup over Horizon 2) on the 50-task calibration slice and 38/350 (10.86%) on the 350 strictly uninspected hold-out tasks (with 7 autonomous Cycle-3 patch solutions); and (iii) in a local 5-game (15-level) ARC-AGI-3-inspired interactive suite, our agent completes 15/15 levels with 89.44% level-weighted RHAE (90.72% unweighted).
Abstract (translated)
URL
https://arxiv.org/abs/2611.13325
PDF
-
A probabilistic model of visual segmentation explains early visual cortical dynamics
2026-11-09 22:35:26Tridib K. Biswas, Ruben Coen-CagliAbstract
Neural dynamics are a central feature of biological neural systems. In the visual cortex, the functional role of neural dynamics is poorly understood, particularly for static stimuli. The statistics of still natural images have long been used by models that successfully predict firing in early visual cortex; those models assume that neurons represent inferences about latent image features, but often ignore the dynamics of said inference. Here, we test if inferential dynamics in images explain visual-cortical dynamics. To do so, we present a biologically plausible model of cortical computation which assumes that the inference of features is coupled with inference about how those features are organized into meaningful parts, a function also known as segmentation. Given an input image, our model iterates between inferring the features and the segments, through recurrence and feedback, thus inducing dynamics in the neural representation of features. For these neural dynamics, we derive theoretical and exact predictions. Our model predicts both gain and variability in evoked responses to natural images, and we show that it captures classical single-neuron experimental findings such as gain dynamics and variability decay during stimulus presentation. The model also predicts that those dynamics are organized around inferred segment structure and more heterogeneous than previously thought, reflecting the complexity of inference for natural scenes. Finally, our analytical formulation provides a clear interpretation of our results. Insights from our normative model could generalize to segmentation problems in other experimental modalities, and help address the cost of inference in artificial networks with iterative computation.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13316
PDF
-
One Trajectory, Two Requirements: Accuracy and Local Stability in Euler Sampling for Flow Matching Policies
Abstract
Flow matching robot policies commonly use a fixed Euler step count selected from offline accuracy sweeps. At inference time, however, each policy input (visual observation, robot state, and language instruction) together with a source-noise draw defines a different ODE trajectory and sequence of local Jacobians. We ask whether a step count that accurately follows the nominal noise-to-action trajectory can still be too coarse for strongly contracting directions around it. An exact two-coordinate system and a controlled augmentation of six trained flow models show that trajectory accuracy and local Euler stability can impose different step requirements even when the original learned transport is unchanged. We then study a frozen $\pi_{0.5}$-LIBERO checkpoint without modifying its weights or action dynamics. Across 30 policy inputs from 10 LIBERO-10 tasks, the Jacobian exhibits strong contracting directions near the action endpoint, yet no sampled mode violates the Euler non-expansion condition. On five of those inputs, accuracy sweeps require 4--9 Euler steps at 5% terminal error and 87--112 at 1%. These five paired cases are therefore consistent with accuracy-limited rather than stability-limited sampling under this local criterion, while the controlled experiments show why endpoint accuracy alone cannot rule out a separate stability requirement.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13311
PDF
-
DUO: Dual Readouts of Diffusion Models for OOD Detection
2026-11-09 22:13:09Alireza Javid, Shirin Shoushtari, Nuria Gonz\'alez PrelcicAbstract
Diffusion models are powerful generative methods for learning and sampling from complex data distributions. Safely deploying these models requires detecting inputs that fall outside their training distribution. Because diffusion models recover clean samples from noisy inputs, reconstruction error is often used for out-of-distribution (OOD) detection. This approach assumes that in-distribution (ID) inputs are reconstructed more accurately than OOD inputs. However, OOD inputs may be reconstructed equally well or even better, making this score unreliable. We therefore propose the leading sensitivity spectrum of intermediate denoising features as a complementary OOD signal and demonstrate that it remains informative when reconstruction error is misleading. We introduce DUal-readout of diffusion models for OOD detection (DUO), a fully unsupervised, training-free OOD detector that combines reconstruction error and feature sensitivity. DUO improves average AUROC by approximately 6% points over the strongest baselines while substantially reducing inference cost, and achieves SOTA on near-OOD and high-resolution benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13304
PDF
-
Domain adaptation of a video Foundation model for Heart Failure Diagnosis from Echocardiography
2026-11-09 22:04:03Mahyar Bolhassani, Tijana Geroski, Narayana S. Singam, Amir AminiAbstract
The rapid advancement of foundation models has transformed computer vision, yet their adaptation to medical imaging, particularly purpose built foundation models for spatio temporal echocardiography videos, remains limited. In this work, we explore the feasibility of fine tuning a pretrained foundation model for video (TimeSformer) for automated diagnosis of reduced ejection fraction heart failure (HFrEF) from apical four chamber videos. The model is finetuned on the publicly available RVENet A4C dataset with a phase aware clip generation strategy that captures complementary systolic and diastolic dynamics. We employ divided space time attention, layer wise learning rate decay, and multi clip inference to enhance robustness under limited data. Experimental results show that full fine tuning of the proposed model outperforms classifier only tuning and a 3D CNN baseline. These findings highlight the potential of leveraging foundation video models for echocardiography based heart failure diagnosis and motivates further domain adaptation studies in medical imaging.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13297
PDF
-
STAR: Semantic-Criticality Tiered Allocation of Radio Resources via Zero-Shot Learning
2026-11-09 21:07:26Albert Shaju, Christo Kurisummoottil Thomas, Mingzhe ChenAbstract
In remote inference, edge devices transmit high-resolution images over wireless links to a receiver, where an artificial intelligence (AI) model answers task-specific questions about these images to enable reliable decisions. These answers are often determined by a small set of task-causal pixels, such as those of text, whose corruption changes the answer, so these pixels must be delivered with high fidelity. Conventional transmission protects every pixel equally, so it either consumes many resource elements (REs) or corrupts these regions at low signal-to-noise ratio (SNR). To overcome these limitations, in this paper, a zero-shot, domain-agnostic framework, termed semantic-criticality tiered allocation of resources (STAR), is proposed. In particular, a per-pixel semantic-criticality indicator (SCI) is derived from the attention of a frozen vision-language model, so new tasks and domains are handled by changing only the prompt, without retraining. The resulting task causality-aware resource allocation problem over protection tiers is solved exactly by a threshold rule on the SCI, realized by a coded tier for the task-causal pixels and an uncoded, downsampled base layer for the full image. Simulations over a 5G New Radio link demonstrate that STAR attains a semantic accuracy of at least 0.98 for $E_s/N_0 \geq -4$ dB and, at comparable semantic reliability, reduces the REs of robust coded transmission by 59.5% and 91.5% on factory- and vehicle-monitoring datasets, respectively, the latter without any change to the models. Although a deep joint source-channel coding baseline uses fewer REs at comparable semantic accuracy, it must be retrained with labeled data for every new task or domain.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13238
PDF
-
NCP: Verifier-Guided Optimization of Weight-Space Control Policies
Abstract
We present the Neural Control Plane (NCP), a closed-loop system that observes language-model execution, synthesizes candidate weight-space intervention rules, evaluates them, and maintains a versioned table of admitted policies. NCP separates a pretrained model's inference data plane from the control policy that selects temporary parameter interventions. W-ISA supplies transactional execution and parameter restoration; NCP supplies telemetry, candidate synthesis, admission criteria, priorities, and rule lifetime management. The optimization state consists of active rules and an archive of evaluated candidates, while base-model parameters are restored after each request. In a local SmolLM-135M-Instruct experiment, NCP generated three candidates from development telemetry and evaluated them on separate task examples and a 4,095-target WikiText-2 slice. One projection reduced validation token repetition from 0.4133 to 0.2191, with a perplexity change of -0.0574%. All candidates produced zero newly correct exact answers, so the configured admission gate archived all three and retained the original active policy. Fresh-process repetition and saved-table resumption reproduced the measured outcomes. NCP provides an executable framework for studying recursive self-improvement at the control-policy level through explicit synthesis, verification, and state transitions.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13236
PDF
-
Multimodal Road Closure Mapping via Cross-Modal Graph Attention
2026-11-09 20:13:18Izzeddin Teeti, Vaibhav Kango, Nidhi Sridhar, Mohamed MoustafaAbstract
Accurate and timely identification of road closures is critical for large-scale navigation and logistics systems, yet remains challenging due to the need to jointly reason over visual evidence, spatial context, and road network topology. Existing approaches either rely on manual map updates or focus on detecting closure-related objects without resolving which road segment is affected. In this work, we introduce a unified multimodal and multitask framework that jointly performs road closure classification (no, partial, complete) and road segment association within a single learning architecture. Our model integrates graph-structured map data, satellite imagery augmented with projected street-level detections, and street-view images using modality-specific encoders and cross-modal transformer attention, enabling explicit reasoning over visual cues and network topology. Evaluated on nearly 20K real-world scenarios collected from a large-scale commercial vehicle fleet, our approach achieves 72.7% closure classification accuracy and 60% road segment association accuracy, outperforming frontier vision-language models by over 28 percentage points on closure classification while being over 4,000x smaller and 100x faster at inference. Extensive ablations demonstrate the importance of cross-modal attention, edge-aware pooling, and graph message passing for accurate geospatial reasoning. This work establishes the first benchmark for joint road closure classification and segment-level attribution, and shows that task-specific architectural inductive biases substantially outperform general-purpose multimodal models for structured geospatial understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13192
PDF
