AI News Archive: April 29, 2026 — Part 25

Sourced from 500+ daily AI sources, scored by relevance.

• Dreambase Data Agent Skills

  Analytical skills for data agents running on Supabase

  🧰 ToolsApr 29, 2026https://www.producthunt.com/products/dreambase-ai?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+the500feed+%28ID%3A+283491%29
• SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts

  As Large Language Models (LLMs) are increasingly integrated into academic peer review, their vulnerability to adversarial prompts -- adversarial instructions embedded in submissions to manipulate outcomes -- emerges as a critical threat to scholarly integrity. To counter this, we propose a novel adv...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26506v1
• StarDrinks: An English and Korean Test Set for SLU Evaluation in a Drink Ordering Scenario

  LLMs and speech assistants are increasingly used for task-oriented interactions, yet their evaluation often relies on controlled scenarios that fail to capture the variability and complexity of real user requests. Drink ordering, for example, involves diverse named entities, drink types, sizes, cust...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26500v1
• Theory-Grounded Evaluation Exposes the Authorship Gap in LLM Personalization

  Stylistic personalization - making LLMs write in a specific individual's style, rather than merely adapting to task preferences - lacks evaluation grounded in authorship science. We show that grounding evaluation in authorship verification theory transforms what benchmarks can measure. Drawing on th...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26460v1
• When Hidden States Drift: Can KV Caches Rescue Long-Range Speculative Decoding?

  Speculative decoding accelerates LLM inference, but SOTA hidden-state-based drafters suffer from long-range decay: draft accuracy degrades as the speculative step increases. Existing work attributes this decay to train-inference mismatch and proposes test-time training (TTT) as a remedy, yet we obse...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26412v1
• Benchmarking Complex Multimodal Document Processing Pipelines: A Unified Evaluation Framework for Enterprise AI

  Most enterprise document AI today is a pipeline. Parse, index, retrieve, generate. Each of those stages has been studied to death on its own -- what's still hard is evaluating the system as a whole. We built EnterpriseDocBench to take a swing at it: parsing fidelity, indexing efficiency, retrieval...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26382v1
• SG-UniBuc-NLP at SemEval-2026 Task 6: Multi-Head RoBERTa with Chunking for Long-Context Evasion Detection

  We describe our system for SemEval-2026 Task 6 (CLARITY: Unmasking Political Question Evasions), which classifies English political interview responses by coarse-grained clarity (3-way) and fine-grained evasion strategy (9-way). Since responses frequently exceed the 512-token limit of standard Trans...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26375v1
• Shorthand for Thought: Compressing LLM Reasoning via Entropy-Guided Supertokens

  Reasoning in Large Language Models incurs significant inference-time compute, yet the token-level information structure of reasoning traces remains underexplored. We observe that reasoning tokens split into two functional types: low-entropy \textit{structural} tokens (recurring phrases that scaffold...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26355v1
• DSIPA: Detecting LLM-Generated Texts via Sentiment-Invariant Patterns Divergence Analysis

  The rapid advancement of large language models (LLMs) presents new security challenges, particularly in detecting machine-generated text used for misinformation, impersonation, and content forgery. Most existing detection approaches struggle with robustness against adversarial perturbation, paraphra...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26328v1
• Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control

  Reinforcement learning (RL) has unlocked complex reasoning abilities in large language models (LLMs). However, most RL algorithms suffer from performance saturation, preventing further gains as RL training scales. This problem can be characterized by the collapse of entropy, a key diagnostic for exp...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26326v1
• A Systematic Comparison of Prompting and Multi-Agent Methods for LLM-based Stance Detection

  Stance detection identifies the attitude of a text author toward a given target. Recent studies have explored various LLM-based strategies for this task, from zero-shot prompting to multi-agent debate. However, existing works differ in data splits, base models, and evaluation protocols, making fair ...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26319v1
• Benchmarking PyCaret AutoML Against BiLSTM for Fine-Grained Emotion Classification: A Comparative Study on 20-Class Emotion Detection

  Fine-grained emotion classification, which identifies specific emotional states such as happiness, anger, sadness, and fear, remains a challenging task in natural language processing. This study benchmarks classical machine learning and deep learning approaches for 20-class emotion classification us...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26310v1
• FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients

  LLM workflows, which coordinate structured calls to individual LLMs (each augmented with varying instructions and tools) to achieve a particular goal, offer a promising path towards extending the capabilities of LLMs and building powerful systems that can tackle diverse tasks. However, existing appr...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26258v1
• A New Semisupervised Technique for Polarity Analysis using Masked Language Models

  I developed a new version of Latent Semantic Scaling (LSS) employing word2vec as a masked language model. Unlike original spatial models, it assigns polarity scores to words and documents as predicted probabilities of seed words to occur in given contexts. These probabilistic polarity scores are mor...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26230v1
• Comparative Analysis of AutoML and BiLSTM Models for Cyberbullying Detection on Indonesian Instagram Comments

  This study compares machine learning and deep learning approaches for cyberbullying detection in Indonesian-language Instagram comments. Using a balanced dataset of 650 comments labeled as Bullying and Non-Bullying, the study evaluates Naive Bayes, Logistic Regression, and Support Vector Machine wit...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26229v1
• Breaking the Autoregressive Chain: Hyper-Parallel Decoding for Efficient LLM-Based Attribute Value Extraction

  Some text generation tasks, such as Attribute Value Extraction (AVE), require decoding multiple independent sequences from the same document context. While standard autoregressive decoding is slow due to its sequential nature, the independence between output sequences offers an opportunity for paral...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26209v1
• Picsart CLI

  Picsart's power right from your AI chat box

  🧰 ToolsApr 29, 2026https://www.producthunt.com/products/picsart?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+the500feed+%28ID%3A+283491%29
• Option-Order Randomisation Reveals a Distributional Position Attractor in Prompted Sandbagging

  A predecessor pilot (Cacioli, 2026) found that Llama-3-8B implements prompted sandbagging as positional collapse rather than answer avoidance. However, fixed option ordering in MMLU-Pro left open whether this reflected a model-level position-dominant policy or dataset-level distractor structure. Thi...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26206v1
• What Kind of Language is Easy to Language-Model Under Curriculum Learning?

  Many of the thousands of attested languages share common configurations of features, creating a spectrum from typologically very rare (e.g., object-verb-subject word order) or impossible languages to very common combinations of features (e.g., subject-object-verb word order). One central question is...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26844v1
• Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding

  RL post-training of frontier language models is increasingly bottlenecked by autoregressive rollout generation, making rollout acceleration a central systems challenge. Many existing efficiency methods improve throughput by changing the rollout or optimization regime, for example, through off-policy...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26779v1
• SAGE: A Strategy-Aware Graph-Enhanced Generation Framework For Online Counseling

  Effective mental health counseling is a complex, theory-driven process requiring the simultaneous integration of psychological frameworks, real-time distress signals, and strategic intervention planning. This level of clinical reasoning is critical for safety and therapeutic effectiveness but is oft...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26630v1
• Zero-Shot to Full-Resource: Cross-lingual Transfer Strategies for Aspect-Based Sentiment Analysis

  Aspect-based Sentiment Analysis (ABSA) extracts fine-grained opinions toward specific aspects within text but remains largely English-focused despite major advances in transformer-based and instruction-tuned models. This work presents a multilingual evaluation of state-of-the-art ABSA approaches acr...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26619v1
• EmoTransCap: Dataset and Pipeline for Emotion Transition-Aware Speech Captioning in Discourses

  Emotion perception and adaptive expression are fundamental capabilities in human-agent interaction. While recent advances in speech emotion captioning (SEC) have improved fine-grained emotional modeling, existing systems remain limited to static, single-emotion characterization within isolated sente...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26417v1
• Text Style Transfer with Machine Translation for Graphic Designs

  Globalization of graphic designs such as those used in marketing materials and magazines is increasingly important for communication to broad audiences. To accomplish this, the textual content in the graphic designs needs to be accurately translated and have the text styling preserved in order to fi...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26361v1
• A Dual-Task Paradigm to Investigate Sentence Comprehension Strategies in Language Models

  Language models (LMs) behave more like humans when their cognitive resources are restricted, particularly in predicting sentence processing costs such as reading times. However, it remains unclear whether such constraints similarly affect sentence comprehension strategies. Besides, existing methods ...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26351v1
• The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation

  Objective metrics for emotional expressiveness are vital for speech generation, particularly in expressive synthesis and voice conversion requiring emotional prosody transfer. To quantify this, the field widely relies on emotion similarity between reference and generated samples. This approach compu...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26347v1
• Classification of Public Opinion on the Free Nutritional Meal Program on YouTube Media Using the LSTM Method

  Public opinion towards the Free Nutritious Meal Program (MBG) on YouTube social media reflects diverse community responses. This study applies the Long Short-Term Memory (LSTM) method to classify sentiments from 7,733 YouTube comments. The results show that the LSTM model achieves 89% accuracy, with...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26312v1
• Folding Tensor and Sequence Parallelism for Memory-Efficient Transformer Training & Inference

  We present tensor and sequence parallelism (TSP), a parallel execution strategy that folds tensor parallelism and sequence parallelism onto a single device axis. In conventional multi-dimensional parallelism layouts, tensor parallelism (TP) shards model weights while sequence parallelism (SP) shards...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26294v1
• StratMem-Bench: Evaluating Strategic Memory Use in Virtual Character Conversation Beyond Factual Recall

  Achieving realistic human-like conversation for virtual characters requires not only a simple memorization and recall of past events, but also the strategic utilization of memory to meet factual needs and social engagement. Current memory utilization relevant (e.g., memory-augmented generation, long...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26243v1
• LATTICE: Evaluating Decision Support Utility of Crypto Agents

  We introduce LATTICE, a benchmark for evaluating the decision support utility of crypto agents in realistic user-facing scenarios. Prior crypto agent benchmarks mainly focus on reasoning-based or outcome-based evaluation, but do not assess agents' ability to assist user decision-making. LATTICE addr...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26235v1
• Three-Step Nav: A Hierarchical Global-Local Planner for Zero-Shot Vision-and-Language Navigation

  Breakthrough progress in vision-based navigation through unknown environments has been achieved by using multimodal large language models (MLLMs). These models can plan a sequence of motions by evaluating the current view at each time step against the task and goal given to the agent. However, curre...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26946v1
• AnimateAnyMesh++: A Flexible 4D Foundation Model for High-Fidelity Text-Driven Mesh Animation

  Recent advances in 4D content generation have attracted increasing attention, yet creating high-quality animated 3D models remains challenging due to the complexity of modeling spatio-temporal distributions and the scarcity of 4D training data. We present AnimateAnyMesh++, a feed-forward framework f...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26917v1
• Redesign by Nodewave

  Free and open‑source, stop designing. Describe.

  🧰 ToolsApr 29, 2026https://www.producthunt.com/products/redesign-by-nodewave?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+the500feed+%28ID%3A+283491%29
• SEAL: Semantic-aware Single-image Sticker Personalization with a Large-scale Sticker-tag Dataset

  Synthesizing a target concept from a single reference image is challenging in diffusion-based personalized text-to-image generation, particularly for sticker personalization where prompts often require explicit attribute edits. With only one reference, test-time fine-tuning (TTF) methods tend to ove...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26883v1
• Uncertainty-Aware Pedestrian Attribute Recognition via Evidential Deep Learning

  We propose UAPAR, an Uncertainty-Aware Pedestrian Attribute Recognition framework. To the best of our knowledge, this is the first EDL-based uncertainty-aware framework for pedestrian attribute recognition (PAR). Unlike conventional deterministic methods, which fail to assess prediction reliability ...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26873v1
• Edge AI for Automotive Vulnerable Road User Safety: Deployable Detection via Knowledge Distillation

  Deploying accurate object detection for Vulnerable Road User (VRU) safety on edge hardware requires balancing model capacity against computational constraints. Large models achieve high accuracy but fail under INT8 quantization required for edge deployment, while small models sacrifice detection per...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26857v1
• TAP into the Patch Tokens: Leveraging Vision Foundation Model Features for AI-Generated Image Detection

  Recent methods demonstrate that large-scale pretrained models, such as CLIP vision transformers, effectively detect AI-generated images (AIGIs) from unseen generative models when used as feature extractors. Many state-of-the-art methods for AI-generated image detection build upon the original CLIP-V...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26772v1
• GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

  We present GLM-5V-Turbo, a step toward native foundation models for multimodal agents. As foundation models are increasingly deployed in real environments, agentic capability depends not only on language reasoning, but also on the ability to perceive, interpret, and act over heterogeneous contexts s...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26752v1
• Circular Phase Representation and Geometry-Aware Optimization for Ptychographic Image Reconstruction

  Traditional iterative reconstruction methods are accurate but computationally expensive, limiting their use in high-throughput and real-time ptychography. Recent deep learning approaches improve speed, but often predict phase as a Euclidean scalar despite its $2π$ periodicity, which can introduce wr...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26664v1
• State Beyond Appearance: Diagnosing and Improving State Consistency in Dial-Based Measurement Reading

  Multimodal large language models (MLLMs) have achieved impressive progress on general multimodal tasks, yet they remain brittle on dial-based measurement reading. In this paper, we study this problem through controlled benchmarks and feature-space probing, and show that current MLLMs not only achiev...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26614v1
• MTCurv: Deep learning for direct microtubule curvature mapping in noisy fluorescence microscopy images

  Accurate quantification of the geometry of curvilinear biological structures is essential for understanding cellular mechanics and disease-related morphological alterations. Microtubule curvature is a key descriptor of filament rigidity and mechanical perturbations. However, reliable curvature extra...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26517v1
• Robust Alignment: Harmonizing Clean Accuracy and Adversarial Robustness in Adversarial Training

  Adversarial Training (AT) is one of the most effective methods for developing robust deep neural networks (DNNs). However, AT faces a trade-off problem between clean accuracy and adversarial robustness. In this work, we reveal a surprising phenomenon for the first time: Varying input perturbation in...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26496v1
• Attribution-Guided Multimodal Deepfake Detection via Cross-Modal Forensic Fingerprints

  Audio-visual deepfakes have reached a level of realism that makes perceptual detection unreliable, threatening media integrity and biometric security. While multimodal detection has shown promise, most approaches are binary classification tasks that often latch onto dataset-specific artifacts rather...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26453v1
• Are Data Augmentation and Segmentation Always Necessary? Insights from COVID-19 X-Rays and a Methodology Thereof

  Purpose: Rapid and reliable diagnostic tools are crucial for managing respiratory diseases like COVID-19, where chest X-ray analysis coupled with artificial intelligence techniques has proven invaluable. However, most existing works on X-ray images have not considered lung segmentation, raising conc...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26437v1
• Sparsity as a Key: Unlocking New Insights from Latent Structures for Out-of-Distribution Detection

  Sparse Autoencoders (SAEs) have demonstrated significant success in interpreting Large Language Models (LLMs) by decomposing dense representations into sparse, semantic components. However, their potential for analyzing Vision Transformers (ViTs) remains largely under-explored. In this work, we pres...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26409v1
• Decoupled Prototype Matching with Vision Foundation Models for Few-Shot Industrial Object Detection

  Industrial object detection systems typically rely on large annotated datasets, which are expensive to collect and challenging to maintain in industrial scenarios where the inventory of objects changes frequently. This work addresses the challenge of few-shot object detection in such industrial scen...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26404v1
• ProcFunc: Function-Oriented Abstractions for Procedural 3D Generation in Python

  We introduce ProcFunc, a library for Blender-based procedural 3D generation in Python. ProcFunc provides a library of easy-to-use Python functions, which streamline creating, combining, analyzing, and executing procedural generation code. ProcFunc makes it easy to create large-scale diverse training...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26943v1
• World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning

  Vision-language models (VLMs) have shown strong performance on static visual understanding, yet they still struggle with dynamic spatial reasoning that requires imagining how scenes evolve under egocentric motion. Recent efforts address this limitation either by scaling spatial supervision with synt...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26934v1
• jyni

  Fresh, verified B2B leads — discovered by jyni AI 24/7

  🧰 ToolsApr 29, 2026https://www.producthunt.com/products/jyni?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+the500feed+%28ID%3A+283491%29
• Graph-based Semantic Calibration Network for Unaligned UAV RGBT Image Semantic Segmentation and A Large-scale Benchmark

  Fine-grained RGBT image semantic segmentation is crucial for all-weather unmanned aerial vehicle (UAV) scene understanding. However, UAV RGBT semantic segmentation faces two coupled challenges: cross-modal spatial misalignment caused by sensor parallax and platform vibration, and severe semantic con...

  📄 ResearchApr 29, 2026http://arxiv.org/abs/2604.26893v1