HyperLens: Quantifying Cognitive Effort in LLMs with Fine-grained Confidence Trajectory

While Large Language Models (LLMs) achieve strong performance across diverse tasks, their inference dynamics remain poorly understood because of the limited resolution of existing analysis tools. In this work, we identify an intrinsic magnification mechanism in transformer architectures: deeper layers inherently magnify the small changes of layer-wise confidence, providing a fine-grained confidence trajectory. Building on this insight, we introduce HyperLens, a high-resolution probe designed to trace confidence trajectories and quantify the cognitive effort during inference. Across LLMs and datasets, HyperLens reveals a consistent divergence in confidence trajectories that separates complex from simple tasks. We abstract this pattern into a quantitative cognitive effort metric. Our analysis reveals a fundamental principle: complex tasks consistently require higher cognitive effort. Finally, we provide a mechanistic diagnosis of a common side effect of standard Supervised Fine-Tuning (SFT): it can reduce cognitive effort and consequently degrade performance on in-domain tasks.

How Far Are Video Models from True Multimodal Reasoning?

Despite remarkable progress toward general-purpose video models, a critical question remains unanswered: how far are these models from achieving true multimodal reasoning? Existing benchmarks fail to address this question rigorously, as they remain constrained by straightforward task designs and fragmented evaluation metrics that neglect complex multimodal reasoning. To bridge this gap, we introduce CLVG-Bench, an evaluation framework designed to probe video models' zero-shot reasoning capabilities via Context Learning in Video Generation. CLVG-Bench comprises more than 1,000 high-quality, manually annotated metadata across 6 categories and 47 subcategories, covering complex scenarios including physical simulation, logical reasoning, and interactive contexts. To enable rigorous and scalable assessment, we further propose an Adaptive Video Evaluator (AVE) that aligns with human expert perception using minimal annotations, delivering interpretable textual feedback across diverse video context tasks. Extensive experiments reveal a striking answer to our central question: while state-of-the-art (SOTA) video models, such as Seedance 2.0, demonstrate competence on certain understanding and reasoning subtasks, they fall substantially short with logically grounded and interactive generation tasks (achieving success rates <25% and ~0%, respectively), exposing multimodal reasoning and physical grounding as critical bottlenecks. By systematically quantifying these limitations, the proposed method provides actionable feedbacks and a clear roadmap toward truly robust, general-purpose video models. CLVG-Bench and code are released here.

GraSP: Graph-Structured Skill Compositions for LLM Agents

Skill ecosystems for LLM agents have matured rapidly, yet recent benchmarks show that providing agents with more skills does not monotonically improve performance -- focused sets of 2-3 skills outperform comprehensive documentation, and excessive skills actually hurt. The bottleneck has shifted from skill availability to skill orchestration: agents need not more skills, but a structural mechanism to select, compose, and execute them with explicit causal dependencies. We propose GraSP, the first executable skill graph architecture that introduces a compilation layer between skill retrieval and execution. GraSP transforms flat skill sets into typed directed acyclic graphs (DAGs) with precondition-effect edges, executes them with node-level verification, and performs locality-bounded repair through five typed operators -- reducing replanning from O(N) to O(d^h). Across ALFWorld, ScienceWorld, WebShop, and InterCode with eight LLM backbones, GraSP outperforms ReAct, Reflexion, ExpeL, and flat skill baselines in every configuration, improving reward by up to +19 points over the strongest baseline while cutting environment steps by up to 41%. GraSP's advantage grows with task complexity and is robust to both skill over-retrieval and quality degradation, confirming that structured orchestration -- not larger skill libraries -- is the key to reliable agent execution.

Rapid LoRA Aggregation for Wireless Channel Adaptation in Open-Set Radio Frequency Fingerprinting

Radio frequency fingerprints (RFFs) enable secure wireless authentication but struggle in open-set scenarios with unknown devices and varying channels. Existing methods face challenges in generalization and incur high computational costs. We propose a lightweight, self-adaptive RFF extraction framework using Low-Rank Adaptation (LoRA). By pretraining LoRA modules per environment, our method enables fast adaptation to unseen channel conditions without full retraining. During inference, a weighted combination of LoRAs dynamically enhances feature extraction. Experimental results demonstrate a 15% reduction in equal error rate (EER) compared to non-finetuned baselines and an 83% decrease in training time relative to full fine-tuning, using the same training dataset. This approach provides a scalable and efficient solution for open-set RFF authentication in dynamic wireless vehicular networks.

FAITH: Factuality Alignment through Integrating Trustworthiness and Honestness

Large Language Models (LLMs) can generate factually inaccurate content even if they have corresponding knowledge, which critically undermines their reliability. Existing approaches attempt to mitigate this by incorporating uncertainty in QA prompt during training, but these numerical scores lack the semantic richness for LLM to properly understand its internal states of trustworthiness and honestness, leading to insufficient factuality alignment. We introduce FAITH (Factuality Alignment through Integrating Trustworthiness and Honestness), a post-training framework for factuality alignment that integrates natural-language uncertainty signals with external knowledge. Specifically, we augment training datasets by computing confidence scores and semantic entropy from LLM outputs and mapping them into a knowledge state quadrant that describes the model's internal knowledge possession (trustworthiness) and answering behaviors (honestness) in natural language. Based on this enhanced data, we design a reward function that considers both correctness and uncertainty signals, and fine-tune the LLM using the Proximal Policy Optimization (PPO) algorithm. To further mitigate weakly grounded responses, we design a retrieval-augmented module that retrieves relevant external passages, improving the consistency between internal and external knowledge representations. Extensive experiments on four knowledge-intensive benchmarks demonstrate that FAITH enhances the factual accuracy and truthfulness of LLMs.

CRB-Based Waveform Optimization for MIMO ISAC Systems With One-Bit ADCs

This paper studies the transmit waveform optimization for a quantized multiple-input multiple-output (MIMO) integrated sensing and communication (ISAC) system, where one-bit analog-to-digital converters (ADCs) are employed to enable a low-cost and power-efficient hardware implementation. Focusing on the parameter estimation task, we propose two novel Cramér-Rao bounds (CRBs) for both point-like target (PT) and extended target (ET) to characterize the impact of quantization distortion on the estimation accuracy, where associated estimation methods are also developed to approach these theoretical CRBs. Moreover, with the goal of jointly enhancing the sensing and communication performances, we formulate the bi-criterion ISAC waveform optimization problem by minimizing the derived CRB objectives subject to a communication symbol error probability (SEP) constraint and a total power constraint, which, due to the high nonlinearity of the one-bit CRBs, are extremely nonconvex. To yield a high-quality suboptimal solution, we develop an efficient alternating direction method of multipliers (ADMM) framework which exploits the majorization-minimization (MM) technique to address the nonconvex issue. Simulation results verify that the one-bit CRBs are tight for characterizing the quantized estimation performance and the proposed estimation methods also show clear performance advantages over the existing benchmark schemes. Furthermore, a flexible trade-off between the CRB and the SEP performance can be achieved by the developed ADMM framework, demonstrating the effectiveness of the optimized ISAC waveform.

This Treatment Works, Right? Evaluating LLM Sensitivity to Patient Question Framing in Medical QA

Patients are increasingly turning to large language models (LLMs) with medical questions that are complex and difficult to articulate clearly. However, LLMs are sensitive to prompt phrasings and can be influenced by the way questions are worded. Ideally, LLMs should respond consistently regardless of phrasing, particularly when grounded in the same underlying evidence. We investigate this through a systematic evaluation in a controlled retrieval-augmented generation (RAG) setting for medical question answering (QA), where expert-selected documents are used rather than retrieved automatically. We examine two dimensions of patient query variation: question framing (positive vs. negative) and language style (technical vs. plain language). We construct a dataset of 6,614 query pairs grounded in clinical trial abstracts and evaluate response consistency across eight LLMs. Our findings show that positively- and negatively-framed pairs are significantly more likely to produce contradictory conclusions than same-framing pairs. This framing effect is further amplified in multi-turn conversations, where sustained persuasion increases inconsistency. We find no significant interaction between framing and language style. Our results demonstrate that LLM responses in medical QA can be systematically influenced through query phrasing alone, even when grounded in the same evidence, highlighting the importance of phrasing robustness as an evaluation criterion for RAG-based systems in high-stakes settings.

Continual Vision-Language Learning for Remote Sensing: Benchmarking and Analysis

Current remote sensing vision-language models (RS VLMs) demonstrate impressive performance in image interpretation but rely on static training data, limiting their ability to accommodate continuously emerging sensing modalities and downstream tasks. This exposes a fundamental challenge: enabling RS VLMs to continually adapt without catastrophic forgetting. Despite its practical importance, the continual learning capability of RS VLMs remains underexplored, and no dedicated benchmark currently exists. In this work, we present CLeaRS, a comprehensive benchmark for continual vision-language learning in remote sensing. CLeaRS comprises 10 curated subsets with over 207k image-text pairs, spanning diverse interpretation tasks, sensing modalities, and application scenarios. We further define three evaluation protocols: long-horizon, modality-incremental, and task-incremental settings, to systematically assess continual adaptation. Extensive benchmarking of diverse vision-language models reveals catastrophic forgetting across all settings. Moreover, representative continual learning methods, when adapted to RS VLMs, exhibit limited effectiveness in handling task, instruction, and modality transitions. Our findings underscore the need for developing continual learning methods tailored to RS VLMs.

Hierarchy-Guided Multimodal Representation Learning for Taxonomic Inference

Accurate biodiversity identification from large-scale field data is a foundational problem with direct impact on ecology, conservation, and environmental monitoring. In practice, the core task is taxonomic prediction - inferring order, family, genus, or species from imperfect inputs such as specimen images, DNA barcodes, or both. Existing multimodal methods often treat taxonomy as a flat label space and therefore fail to encode the hierarchical structure of biological classification, which is critical for robustness under noise and missing modalities. We present two end-to-end variants for hierarchy-aware multimodal learning: CLiBD-HiR, which introduces Hierarchical Information Regularization (HiR) to shape embedding geometry across taxonomic levels, yielding structured and noise-robust representations; and CLiBD-HiR-Fuse, which additionally trains a lightweight fusion predictor that supports image-only, DNA-only, or joint inference and is resilient to modality corruption. Across large-scale biodiversity benchmarks, our approach improves taxonomic classification accuracy by over 14 percent compared to strong multimodal baselines, with particularly large gains under partial and corrupted DNA conditions. These results highlight that explicitly encoding biological hierarchy, together with flexible fusion, is key for practical biodiversity foundation models.

Scaling Sim-to-Real Reinforcement Learning for Robot VLAs with Generative 3D Worlds

The strong performance of large vision-language models (VLMs) trained with reinforcement learning (RL) has motivated similar approaches for fine-tuning vision-language-action (VLA) models in robotics. Many recent works fine-tune VLAs directly in the real world to avoid addressing the sim-to-real gap. While real-world RL circumvents sim-to-real issues, it inherently limits the generality of the resulting VLA, as scaling scene and object diversity in the physical world is prohibitively difficult. This leads to the paradoxical outcome of transforming a broadly pretrained model into an overfitted, scene-specific policy. Training in simulation can instead provide access to diverse scenes, but designing those scenes is also costly. In this work, we show that VLAs can be RL fine-tuned without sacrificing generality and with reduced labor by leveraging 3D world generative models. Using these models together with a language-driven scene designer, we generate hundreds of diverse interactive scenes containing unique objects and backgrounds, enabling scalable and highly parallel policy learning. Starting from a pretrained imitation baseline, our approach increases simulation success from 9.7% to 79.8% while achieving a 1.25$\times$ speedup in task completion time. We further demonstrate successful sim-to-real transfer enabled by the quality of the generated digital twins together with domain randomization, improving real-world success from 21.7% to 75% and achieving a 1.13$\times$ speedup. Finally, we further highlight the benefits of leveraging the effectively unlimited data from 3D world generative models through an ablation study showing that increasing scene diversity directly improves zero-shot generalization.