Solar Intelligence
arXiv:2609.13648v1 Announce Type: new Abstract: Solar energy decision support is fragmented across dashboards that provide data without explanation, research papers are slow to parse, and general-purpose language models…
Daily edition · Information Retrieval
The daily ledger
TILens turns technical updates into a focused daily brief: official releases, trusted reporting, and practitioner analysis, deduplicated and organized by topic.
54 articles · 4 sources · 54 papers ·
Top topics: AI · Information Retrieval · AI Research
SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization
arXiv:2609.14320v1 Announce Type: new Abstract: Recently, linear attention layers have been increasingly adopted to replace softmax attention at scale for long-context modeling. However, existing context extension…
ShopEase: A Generative AI-Based Multi-Agent Framework for Intelligent Enterprise Customer Support Using Hybrid Retrieval-Augmented Generation
arXiv:2609.13856v1 Announce Type: new Abstract: Enterprise customer support systems must answer customer questions correctly, retrieve the right policy information, use customer context, and pass difficult cases to…
MMLA: Memory-Mediated Learning Architecture for Predictive Dual-State Adaptation
arXiv:2606.28876v4 Announce Type: replace Abstract: Memory-Mediated Learning Architecture (MMLA) separates slow base parameters theta, a bounded numerical policy carrier Phi, and a bounded authoritative memory M.…
SatIR: Scalable High-Recall Constraint-Satisfaction-Based Information Retrieval for Clinical Trials Matching
arXiv:2604.08849v4 Announce Type: replace Abstract: Many real-world retrieval and matching problems require more than topical relevance: a candidate must satisfy the specific constraints of one profile among many, not…
Prefix Sharing Is a Sorting Problem
arXiv:2609.13692v1 Announce Type: new Abstract: LLM serving reuses KV cache by exact prefix match, so when a prompt is assembled from a set of reusable pieces -- retrieved passages, tool definitions, few-shot exemplars…
Odds-Shift Slippage in One-vs-Rest Rankers: Diagnosing and Repairing Reweighting-Induced Top-K Errors
arXiv:2609.13810v1 Announce Type: new Abstract: One-vs-rest rankers that show each user the top-$K$ of many rare labels usually counter imbalance with a per-label positive-class weight, scale_pos_weight $= n_-/n_+$.…
Self-Evolving Memory for Generative Recommendation
arXiv:2609.15598v1 Announce Type: new Abstract: Generative recommendation has emerged as a promising end-to-end paradigm for personalized recommendation. However, user preferences continuously evolve over time, making…
P3Rec: Distilling Prior--Posterior Preference Reasoning for LLM-based Recommendation
arXiv:2609.13993v1 Announce Type: new Abstract: Large language models (LLMs) exhibit strong semantic understanding and preference reasoning capabilities, offering new opportunities for user modeling in recommender…
Cost Characterization of Vertically Partitioned Federated Knowledge Graphs
arXiv:2609.13664v1 Announce Type: cross Abstract: Knowledge graphs are increasingly distributed across autonomous organizations that share an entity space but own disjoint subsets of relations, forming a vertical…
EviQE: Evidence Selection for LLM-Based Query Expansion
arXiv:2609.14875v1 Announce Type: new Abstract: LLM-based query expansion increasingly conditions reformulation on documents retrieved from the target corpus, yet most work focuses on how to generate expansions rather…
Route Me If You Can: A Benchmark for Query Reformulation Selection
arXiv:2609.14885v1 Announce Type: new Abstract: LLM-based query reformulation can improve retrieval, but no single reformulation strategy is consistently optimal across queries, domains, retrievers, or model backbones.…
Clean Scores, Buried Evidence, and Confident Wrong: A Receipt-Based Audit of Frontier Agentic QA
arXiv:2609.15319v1 Announce Type: new Abstract: Frontier models score well on shallow document/chart reading tasks. In a controlled data-room audit, moving evidence into buried conditions reduced accuracy, increased…
CRAMER: Control via Request-Aware Masking for Editing Recommenders
arXiv:2608.25370v2 Announce Type: replace Abstract: Sequential recommendation models, while powerful, have limited flexibility in responding to immediate user requests, making it difficult to adapt their recommendations…
Speak to the City: Multimodal Resolution for Outside-the-Vehicle References
arXiv:2609.14691v1 Announce Type: cross Abstract: As autonomous vehicles and Extended Reality (XR) headsets enable novel in-car interactions, seamlessly querying physical landmarks, known as Outside-the-Vehicle…
Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation
arXiv:2609.11115v2 Announce Type: replace-cross Abstract: Benchmark researchers and developers of large language models (LLMs) and other AI systems need to find relevant evaluations, locate their benchmark datasets and…
The Magnitude Mirage: Rethinking Confidence for Reasoning-Intensive Retrieval
arXiv:2609.15578v1 Announce Type: new Abstract: Many production RAG systems implement retrieval abstention by thresholding raw similarity scores, implicitly treating score magnitude as a confidence signal. We…
ClinAgent: A ReAct-Based Agent for Conversational Access to Clinical Trial Information
arXiv:2609.13860v1 Announce Type: cross Abstract: Querying clinical trial registries remains a manual and error-prone process, requiring researchers to navigate large volumes of semi-structured data without support for…
Where to Look and What to Use: Retrieve-Localize-Generate for Long-Term Conversational Memory Question Answering
arXiv:2609.07093v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) enables large language models (LLMs) to answer questions by accessing external knowledge and has been widely adopted for…
VARG: Value-Aware and Ranking-Aligned Generative Retrieval for Dynamic E-commerce Search
arXiv:2609.14493v1 Announce Type: new Abstract: Integrating recall and pre-ranking in e-commerce search requires candidate generation to account for relevance, personalization, and business value before final ranking.…
Loading more...
Showing 1 day · 54 items available