arXiv AI
Aug 12
LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning
arXiv:2601. 10129v2 Announce Type: replace-cross Abstract: Current multimodal latent reasoning often relies on external supervision (e.
Retrieval-augmented generation
Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv AI
Aug 12
Similarity Gates Approve Reversals: A Validity Audit of Embedding-Cosine Thresholds in Agent Systems
arXiv:2608. 10216v1 Announce Type: cross Abstract: Agent frameworks ship quality gates that compare text blocks by embedding-cosine similarity and decide at a fixed cutoff.
arXiv AI
Aug 12
MD-ProTector: Positioning Multiple Data-Driven Prototypes for LLM-Generated Text Detection
arXiv:2608. 10459v1 Announce Type: cross Abstract: As LLM-generated content becomes more sophisticated, detection systems for distinguishing those texts from human-written text must operate at scale while handling diverse writing styles, domains, languages, and generator models.
arXiv AI
Aug 12
Mitigating Bus Bunching with Reinforcement Learning Enhanced by Semantic Stop Embedding
arXiv:2608. 10207v1 Announce Type: new Abstract: Bus bunching degrades service regularity and increases passenger waiting in high-frequency transit.
arXiv Machine Learning
Aug 12
CADET: Context-Conditioned Ads CTR Prediction With a Decoder-Only Transformer
arXiv:2602. 11410v2 Announce Type: replace Abstract: Click-through rate (CTR) prediction is fundamental to online advertising systems.
arXiv AI
Aug 12
SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation
arXiv:2608. 10775v1 Announce Type: new Abstract: Computer-using agents can perceive rich software interfaces, yet their decisions often lack visual procedural memory: they may recognize individual controls without identifying which familiar workflow is active, which control matters next, or what evidence would confirm progress.
arXiv Machine Learning
Aug 12
URS: A Unified Neural Routing Solver for Cross-Problem Zero-Shot Generalization
arXiv:2509. 23413v3 Announce Type: replace Abstract: Multi-task neural routing solvers have emerged as a promising paradigm for their ability to solve multiple vehicle routing problems (VRPs) using a single model.
arXiv Machine Learning
Aug 12
Post-Calibration Reliability Reranking of Relevance Decisions via Label-wise Monotone Projection
arXiv:2608. 10406v1 Announce Type: cross Abstract: Web search, product search, and question-answering retrieval systems often assign a relevance label and confidence score to each query-candidate pair.
arXiv AI
Aug 12
FedCGR: Federated Cross-Domain Generative Recommendation
arXiv:2608. 10929v1 Announce Type: new Abstract: Cross-domain recommendation (CDR) transfers preference knowledge across related domains, but federated deployment makes cross-domain alignment difficult because the behavioral anchors that align item spaces, such as overlapping users and shared interaction signals, are often sparse, unavailable, or privacy-sensitive across clients.
arXiv AI
Aug 12
TRACE: Trustworthy Retrieval-Augmented Conversational Engine
arXiv:2608. 10176v1 Announce Type: new Abstract: Public service chatbots are expected to deliver recommendations from an underlying public service directory, while also making sure that the recommendations respect explicit user constraints.
arXiv AI
Aug 12
Sheaf-Based Federated Representation Learning
arXiv:2608. 10016v1 Announce Type: cross Abstract: Heterogeneous federated systems require agents to learn and exchange informative representations despite differences in data distributions, sensing modalities, model architectures, latent dimensionalities, and local learning objectives.
arXiv AI
Aug 12
Reasoning Shortcuts and Value Symmetries: What Symmetry Permits, Architecture Realizes, and Optimization Selects
arXiv:2608. 10420v1 Announce Type: new Abstract: Reasoning shortcuts are solutions of a neurosymbolic system's rules that produce correct predictions through unintended concepts.
arXiv Machine Learning
Aug 12
P3CA: Encoder-Agnostic Interpretation of Vision Foundation Model Embeddings via Spatial Probing
arXiv:2608. 10131v1 Announce Type: cross Abstract: Vision foundation models are increasingly used as reusable encoders in medical image computing, yet their high-dimensional spatial embeddings are difficult to inspect beyond downstream task performance or global dimensionality reduction.
arXiv AI
Aug 12
Self-evolving Agentic Customer Support System at LinkedIn
arXiv:2608. 10224v1 Announce Type: new Abstract: Enterprise support agents operate in rapidly changing environments where policies, product capabilities, and knowledge bases evolve continuously, making static assistants brittle and costly to maintain.
arXiv AI
Aug 12
ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling
arXiv:2608. 10928v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) improve performance by allocating additional inference-time compute to generate extended chain-of-thought reasoning.
arXiv Machine Learning
Aug 12
When Do Anchor-Based Pointwise LLM Rerankers Help? Retriever Quality, Statistical Scope, and Anchor Design
arXiv:2608. 10528v1 Announce Type: cross Abstract: Anchor-based pointwise LLM reranking scores each candidate against a shared reference passage to recover cross-document context at pointwise cost.
arXiv AI
Aug 12
From Reasoning Depth to Reasoning Breadth: Evaluating Multi-Point Associative Reasoning in Large Language Models
arXiv:2608. 10444v1 Announce Type: cross Abstract: Large language models (LLMs) have made substantial progress on reasoning tasks that require increasingly long and complex inferential chains.
arXiv Machine Learning
Aug 12
Mapping and Measuring the Behavioral Evolution of Large Language Models
arXiv:2608. 11027v1 Announce Type: new Abstract: Benchmark leaderboards summarize how well a language model performs, but not how its behavior relates to that of other models or changes across generations.
arXiv Machine Learning
Aug 12
Beyond a Bag of Features: Set-Level Instability in Sparse Autoencoders
arXiv:2608. 11197v1 Announce Type: new Abstract: Shani et al.
arXiv AI
Aug 12
FITTER: Vocabulary-Agnostic Cross-Domain Inference on Temporal Knowledge Graphs
arXiv:2608. 10668v1 Announce Type: new Abstract: Temporal knowledge graphs are central to many uses of the Semantic Web, but existing completion methods assume the entities, relation names, and timestamps to be reasoned about are already known at training time, restricting each model to a single graph and vocabulary.