This paper proposes an adaptive group-accompaniment method for social robots based on Vision-Language Models (VLMs). It leverages VLM semantic reasoning to infer companion positions, maintain social distances, and understand group dynamics, combined with a Model Predictive Path Integral (MPPI) controller for stability. Experiments show a 15% improvement in success rate and a 25% reduction in collision rate, with user study perceiving behaviors as natural and socially appropriate.

This paper proposes WaveLander, a hierarchical reinforcement learning framework for autonomous UAV landing on wave-disturbed marine platforms. It decouples vertical landing decision-making from low-level flight stabilization, using an RL policy to output a vertical velocity reference while a conventional controller handles attitude and lateral tracking. Simulations show robust performance and generalization to unseen disturbances.

Researchers propose 'Sign in the Air to Unlock', an in-air signature interface for VR/AR authentication using a Point-Voxel Cross-Attention Network (PV-Net). It enables natural signing in 3D space without breaking immersion or requiring specialized sensors. PV-Net achieves 2.5% Equal Error Rate on DeepAirSig and 76% classification accuracy on a new Meta Quest 2 dataset, demonstrating the potential of 3D behavioral authentication.

G-CBM, a Graph-based Concept Bottleneck Model, performs unsupervised concept discovery and uses graph attention networks for interpretable visual explanations, achieving 3.7% average relative AUC improvement over ResNet-50 baselines across multiple benchmarks.

This study applies the YOLOv10 computer vision framework to automatically detect brown howler monkeys in camera trap videos, aiming to monitor canopy bridge usage and reduce the time conservationists spend reviewing false-positive images.

This dissertation aims to narrow the gap between machine visual tracking and human perception by enhancing target discrimination, robust adaptation, and geometric reasoning in tracking models.

Multi-subject personalized image generation requires the precise rendering of all requested reference identities and their specified interactions based on a guiding prompt. However, state-of-the-art models still struggle with this process, frequently omitting subjects, failing to preserve reference appearances, or misattributing interactions. Furthermore, existing metrics designed primarily for single-subject fidelity cannot reliably capture these errors, suffering severe degradation in ranking separability and failing to align with human preference as the subject count increases. To address this gap, we introduce Multi-subject Interaction Benchmark and Evaluator (MIBE), a unified framework comprising a Multi-subject Interaction Benchmark (MIB) and a Multi-subject Interaction Evaluator (M…

MapDreamer is a generative diffusion model that creates lane-level vector maps from a single aerial image, using latent diffusion and transformer-based graph prediction. It introduces a lane cardinality module and sliding-window aggregation for scalable map generation. Experiments show improved fidelity over baselines.

This paper introduces an input-aware extendable expert module to enhance fine-grained feature extraction for video-based person re-identification. Using input-aware expert selection and spatial-temporal selection mechanisms, the method achieves state-of-the-art performance on large-scale datasets.

KathaTrace is a generator-agnostic protocol for diagnosing semantic trajectory collapse, defined as the loss of transition meaning between scenes in visual narratives. The authors introduce KathaBench-25K, a dataset of 5,000 narratives from classical collections, and define the Semantic Trajectory Gap (STG) metric. Experiments show substantial STG (23.5±1.3) across state-of-the-art generators. Semantic Compass, an actionability probe, uses KathaTrace signals for post-generation repair and improves storyboard selection.

Proposes CPG-PAD, a framework that introduces model-level concept guidance into prompt learning for Presentation Attack Detection. It uses XAI to discover attack-relevant visual concepts and injects them into prompts, achieving state-of-the-art cross-domain performance on nine benchmarks.

AnchorSplat is a novel 3D-native refinement paradigm that operates directly on 3D structures, avoiding expensive optimization overhead of traditional pipelines. It enforces geometric consistency via a Point Anchor Mechanism and replaces iterative densification with single-pass multiplication, requiring no original multi-view images. Experiments show throughput up to 10^5 times faster than optimization methods with robust zero-shot generalization.

TurnNat is a likelihood-based framework for automatic evaluation of turn-taking naturalness in dyadic spoken dialogue. It uses a causal prediction model to compute negative log-likelihood of future voice activity, quantifying timing atypicality, and demonstrates effectiveness on a perturbation benchmark.

RuleChef is a framework that uses LLMs to generate executable rules for NLP tasks such as text classification, NER, and relation extraction. Rules are generated from task descriptions and labeled examples, then iteratively improved via additional examples and human feedback. LLMs are used only at learning time, resulting in a fast, deterministic, and inspectable rule system. Preliminary evaluation on classification and NER tasks shows promise, and the system is open-sourced under Apache 2.0.

The Office Comprehension Bench (OCB) is the first public benchmark to jointly evaluate LLM systems on Word, Excel, and PowerPoint comprehension over native file formats. It comprises two tracks: File Fidelity Q&A (structural/visual perception) and Domain Q&A (expert reasoning across 12 domains). Even the strongest frontier system achieves only 59.3% on Domain Q&A; increasing thinking depth within a tier yields no material improvement, while moving to a higher product tier offers modest gains. The dataset, evaluation tooling, judge prompt, and leaderboard are released.

Researchers propose RAGP, a novel prompt compression method that models text as a multiplex graph and uses Lévy walks for efficient pruning. It achieves a 49.3 average score on LongBench at 4x compression, outperforming existing LLM-based methods.

This paper reveals that count-based F1 can be artificially inflated by prompt framing without corresponding improvement in span localization—a gap termed F1 Inflation. It introduces ErrorBench, a controlled stress-test protocol. Experiments show anchored prompts cause up to 0.79 F1 Inflation. The findings recommend avoiding pre-populated error counts and reporting span-aware metrics alongside count-based ones.

A new study reveals that BPE tokenization fragments safety-critical words into subword units, creating exploitable gaps in LLM safety alignment. An optimization targeting this fragmentation flips refusal triggers on 80-100% of HarmBench prompts, with 48% producing genuinely harmful outputs. Defense attempts show DPO configurations fail to close ASR stably, while SFT leads to global collapse. The paper introduces Conv-Benign as a diagnostic tool.

Recent advances in speech synthesis have shifted to direct grapheme modeling, but grapheme-based models underperform in low-resource settings. SPARCLE is a speaker-aware grapheme representation model trained with contrastive learning to align graphemes with acoustic representations, reducing word error rates by half in extreme low-resource settings.

This paper proposes Kara, a sliding-window KV cache compression method that operates on recently generated context during decoding. It uses bidirectional attention to score and select informative KV pairs and a Token2Chunk module to flexibly preserve important semantic information. Experiments show Kara and the vLLM-based inference framework KvLLM significantly reduce KV cache memory and improve output throughput.

This paper proposes a provenance-based conceptual framework for detecting misalignment in LLM agents' tool invocations. The authors develop ProvenanceGuard, a multi-stage pipeline that analyzes three types of misalignment before tool execution. Evaluated on Agent-SafetyBench and WorkBench across 10 backbone LLMs, it reduces error rates from 42.9% to 1.8% and from 32.1% to 17.3%, respectively, while decreasing intervention burden on successful traces from 30.5% to 12.8%.

TokenScope is a new interactive tool that provides token-level explainability for LLMs during code generation, offering metrics, attention patterns, and counterfactual branching to explore model decisions.

This paper presents a proof-of-concept AI system that uses images and accident reports to assess railway crossing safety, achieving a macro F1 score of 0.757 for risk classification and an RMSE of 0.078 for safety scores.

A new attack called NightVision can estimate hidden dimension, depth, and parameter count of LLMs even when APIs are restricted to only single logit output, achieving low error rates.

A new monograph by Zhilin Zhao presents a unified, proof-oriented account of modern deep learning theory, bridging classical approximation, optimization, and generalization with contemporary topics like overparameterization, transformers, in-context learning, scaling laws, and emergence.

Researchers propose a method combining Sparse Random Projection and multinomial logistic regression for CNS tumor classification from DNA methylation data. It achieves 96% accuracy on a reference cohort and 86% (91-class) and 93% (family-level) on an independent clinical cohort, outperforming state-of-the-art by 4-5 percentage points.

IonSense-QKG enriches public lithium-ion battery datasets with quantum-relevant metadata, introducing a Quantum Readiness Score to help researchers select datasets suitable for hybrid quantum-classical machine learning. The framework provides query-based discovery and reproducible tools for data-centric quantum battery analytics.

This study systematically characterizes a multiprobe grid algorithm for ANN search, revealing a d-scaling crossover on GloVe embeddings where grid maintains constant dimensional scaling while other methods degrade, with near-linear query scaling and lower indexing cost, suggesting competitiveness in high-dimensional settings and informing efficient transformer design.

This paper introduces a domain knowledge-based graph convolution network for ECG recognition, incorporating PRQST landmarks as domain knowledge. A double-stream directed graph models intra- and inter-cycle spatial and temporal dependencies. On the First Chinese ECG Intelligent Competition dataset, the method achieves an overall F1 score of 88.1% and 76.3% for rare categories, outperforming state-of-the-art models.

This paper studies adversarial robustness in programming-by-example systems, introducing a new attack mode where an adversary observes the synthesizer and chooses examples that most damage the returned program. The authors formalize worst-case corruption for finite version spaces, implement search algorithms, and propose Version-Space Partition Aggregation (VPA) as a defense. Experiments show that low-margin tasks have an adversarial robustness dimension missed by random-noise evaluations, and VPA only helps when clean semantics maintain a partition vote margin, which often fails in realistic tasks.