arXiv:2609.16722v1 Announce Type: new Abstract: Scaling Multimodal Large Language Models (MLLMs) to long-form video understanding is bottlenecked by the…
Category: AI
ANIMASK: What the Model Contributes to Role Play in Simulated Story Worlds
arXiv:2609.16667v1 Announce Type: new Abstract: When a language model plays a character, the observed behavior reflects both the assigned persona and the…
AI for Games in the Foundation Model Era
arXiv:2609.16679v1 Announce Type: new Abstract: Foundation models, alongside advances in learned game-world models, are reshaping AI across the game…
EchoPath: Execution-Level Replayable Memory for GUI Agents
arXiv:2609.16635v1 Announce Type: new Abstract: Computer-use agents increasingly operate browsers, software, and desktop applications via CLI or API…
little m: An AI Agent for Industrial Process Optimization
arXiv:2609.16680v1 Announce Type: new Abstract: Manufacturing consumes one third of global energy and still has significant room for improvement in terms…
ReDraft, Don’t Just Distill: Reference-Driven Revision for Continual VLLM Post-Training
arXiv:2609.16639v1 Announce Type: new Abstract: Continual post-training of large multimodal models should add new capabilities while preserving those from…
QueryFormer: Winning Solution for KDD Cup 2026 Tencent UniRec Challenge
arXiv:2609.16548v1 Announce Type: new Abstract: Post-click conversion rate (pCVR) prediction requires jointly modeling feature interactions and sequential…
A Framework for Generating Valid Context-Specific Benchmarks through Expert Guidance
arXiv:2609.16592v1 Announce Type: new Abstract: This paper presents an end-to-end approach for generating context-specific large language model (LLM)…
Do LLMs Have Values? A Quantitative Analysis and Alignment Framework for Values in Large Language Models
arXiv:2609.16589v1 Announce Type: new Abstract: As Large Language Models (LLMs) increasingly handle complex subjective tasks, aligning their intentions…
Query-Aware Source-Risk Triage for Retrieval-Augmented Generation
arXiv:2609.16564v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) pipelines may omit a source’s material relationship to the query. We…