Accepted Industry Track Papers
- Boosting Decision-Making Ability of LLMs with Speculative Reward Model Cost-Effectively
need - RAVEN: Robust Advertisement Video Violation Temporal Grounding via Reinforcement Reasoning
need - DistilQwen2.5: Industrial Practices of Training Distilled Open Lightweight Language Models
need - SimUSER: Simulating User Behavior with Large Language Models for Recommender System Evaluation
need - MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection
need - LLM-Enhanced Self-Evolving Reinforcement Learning for Multi-Step E-Commerce Payment Fraud Risk Detection
need - ORMind: A Cognitive-Inspired End-to-End Reasoning Framework for Operations Research
need - TN-Eval: Rubric and Evaluation Protocols for Measuring the Quality of Behavioral Therapy Notes
need - NeKo: Cross-Modality Post-Recognition Error Correction with Tasks-Guided Mixture-of-Experts Language Model
need - TablePilot: Recommending Human-Preferred Tabular Data Analysis with Large Language Models
need - Model Merging for Knowledge Editing
need - HierGR: Hierarchical Semantic Representation Enhancement for Generative Retrieval in Food Delivery Search
need - Generating Q&A Benchmarks for RAG Evaluation in Enterprise Settings
need - Conceptual Diagnostics for Knowledge Graphs and Large Language Models
need - To Chat or Task: a Multi-turn Dialogue Generation Framework for Task-Oriented Dialogue Systems
need - Optimization before Evaluation: Evaluation with Unoptimized Prompts Can be Misleading
need - Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models
need - Learning from Litigation: Graphs for Retrieval and Reasoning in eDiscovery
need - Speed Without Sacrifice: Fine-Tuning Language Models with Medusa and Knowledge Distillation in Travel Applications
need - Proactive Guidance of Multi-Turn Conversation in Industrial Search
need - SpeechWeave: Diverse Multilingual Synthetic Text & Audio Data Generation Pipeline for Training Text to Speech Models
need - Privacy Preserving Data Selection for Bias Mitigation in Speech Models
need - ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industry
need - PlanGPT: Enhancing Urban Planning with Tailored Language Model and Efficient Retrieval
need - Operational Advice for Dense and Sparse Retrievers: HNSW, Flat, or Inverted Indexes?
need - LEAP & LEAN: Look-ahead Planning and Agile Navigation for LLM Agents
need - User Feedback Alignment for LLM-powered Interest Exploration in Large-scale Recommendation Systems
need - AIDE: Attribute-Guided MultI-Hop Data Expansion for Data Scarcity in Task-Specific Fine-tuning
need - Sentiment Reasoning for Healthcare
need - Reinforcement Learning for Adversarial Query Generation to Enhance Relevance in Cold-Start Product Search
need - Auto Review: Second Stage Error Detection for Highly Accurate Information Extraction from Phone Conversations
need - From Recall to Creation: Generating Follow-Up Questions Using Bloom’s Taxonomy and Grice’s Maxims
need - REVISE: A Framework for Revising OCRed text in Practical Information Systems with Data Contamination Strategy
need - TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering
need - MIRA: Empowering One-Touch AI Services on Smartphones with MLLM-based Instruction Recommendation
need - Scaling Context, Not Parameters: Training a Compact 7B Language Model for Efficient Long-Context Processing
need - Towards Multi-System Log Anomaly Detection
need - Multi-Step Generation of Test Specifications using Large Language Models for System-Level Requirements
need - Straightforward Meta-Evaluation of LLMs-as-judges in Machine Translation and DR-100, the LLM-tailored Assessment Metric
need - SocialForge: simulating the social internet to provide realistic training against influence operations
need - Run LoRA Run: Faster and Lighter LoRA Implementations
need - Genetic Instruct: Scaling up Synthetic Generation of Coding Instructions for Large Language Models
need - Generating OpenAPI Specifications from Online API Documentation with Large Language Models
need - CoAlign: Uncertainty Calibration of LLM for Geospatial Repartition
need - Arctic-TILT. Business Document Understanding at Sub-Billion Scale
need - Graph-Linguistic Fusion: Using Language Models for Wikidata Vandalism Detection
need - LOTUS: A Leaderboard for Detailed Image Captioning from Quality to Societal Bias and User Preferences
need - CiteFix: Enhancing RAG Accuracy Through Post-Processing Citation Correction
need - Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond
need - Efficient Out-of-Scope Detection in Dialogue Systems via Uncertainty-Driven LLM Routing
need - Transforming Podcast Preview Generation: From Expert Models to LLM-Based Systems
need - A Perspective on LLM Data Generation with Few-shot Examples: from Intent to Kubernetes Manifest
need - LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questions
need - Overlapping Context with Variable-Length Stride Increases Diversity when Training Large Language Model for Code
need - Grammar-Constrained Decoding Makes Large Language Models Better Logical Parsers
need - AUTOSUMM: A Comprehensive Framework for LLM-Based Conversation Summarization
need - RedactX: An LLM-Powered Framework for Automatic Clinical Data De-Identification
need - QUPID: Quantified Understanding for Enhanced Performance, Insights, and Decisions in Korean Search Engines
need - Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correction
need - EdgeInfinite: A Memory-Efficient Infinite-Context Transformer for Edge Devices
need - Scaling Under-Resourced TTS: A Data-Optimized Framework with Advanced Acoustic Modeling for Thai
need - ArchiDocGen: Multi-Agent Framework for Expository Document Generation in the Architectural Industry
need - LexGenie: Automated Generation of Structured Reports for European Court of Human Rights Case Law
need - Accelerating Antibiotic Discovery with Large Language Models and Knowledge Graphs
need - FoodTaxo: Generating Food Taxonomies with Large Language Models
need - Enriching children’s stories with LLMs: Delivering multilingual data enrichment for children’s books at scale and across markets
need - Advanced Messaging Platform (AMP): Pipeline for Automated Enterprise Email Processing
need - Semantic Outlier Removal with Embedding Models and LLMs
need - SLENDER: Small Language Models for NER in Low-Resource Englishes
need - A Large-Scale Real-World Evaluation of an LLM-Based Virtual Teaching Assistant
need - Filter-And-Refine: A MLLM Based Cascade System for Industrial-Scale Video Content Moderation
need - ASK: Aspects and Retrieval based Hybrid Clarification in Task Oriented Dialogue Systems
need - MotiR: Motivation-aware Retrieval for Long-Tail Recommendation
need - A Framework for Flexible Extraction of Clinical Event Contextual Properties from Electronic Health Records
need - Enhancing LLM-as-a-Judge through Active-Sampling-based Prompt Optimization
need - Small Language Models in the Real World: Insights from Industrial Text Classification
need - AutoChunker: Structured Text Chunking and its Evaluation
need - SQLGenie: A Practical LLM based System for Reliable and Efficient SQL Generation
need - Hard Negative Mining for Domain-Specific Retrieval in Enterprise Systems
need - Interpretable Company Similarity with Sparse Autoencoders
need - Domain Adaptation of Foundation LLMs for e-Commerce
need - sudo rm -rf agentic_security
need - MedPlan: A Two-Stage RAG-Based System for Personalized Medical Plan Generation
need - Synthesizing and Adapting Error Correction Data for Mobile Large Language Model Applications
need - MultiMed: Multilingual Medical Speech Recognition via Attention Encoder Decoder
need - MICE: Mixture of Image Captioning Experts Augmented e-Commerce Product Attribute Value Extraction
need - Won: Establishing Best Practices for Korean Financial NLP
need - Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning?
need - OccuTriage: An AI Agent Orchestration Framework for Occupational Health Triage Prediction
need - The Long CoT Collection: A Fully Open Dataset for Initializing Large Reasoning Models
need - SingaKids: A Multilingual Multimodal Dialogic Tutor for Language Learning
need - Unifying Streaming and Non-streaming Zipformer-based ASR
need - A Semi-supervised Scalable Unified Framework for E-commerce Query Classification
need - CodeIF: Benchmarking the Instruction-Following Capabilities of Large Language Models for Code Generation
need - BI-Bench : A Comprehensive Benchmark Dataset and Unsupervised Evaluation for BI Systems
need - A Parallelized Framework for Simulating Large-Scale LLM Agents with Realistic Environments and Interactions
need - ENGinius: A Bilingual LLM Optimized for Plant Construction Engineering
need - Consistency-Aware Online Multi-Objective Alignment for Related Search Query Generation
need - Towards Generating Controllable and Solvable Geometry Problem by Leveraging Symbolic Deduction Engine
need - TableCoder: Table Extraction from Text via Reliable Code Generation
need - Are LLMs reliable? An exploration of the reliability of large language models in clinical note generation
need - Convert Language Model into a Value-based Strategic Planner
need - ConCodeEval: Evaluating Large Language Models for Code Constraints in Domain-Specific Languages
need - Unveiling Dual Quality in Product Reviews: An NLP-Based Approach
need - Enhancing Marker Scoring Accuracy through Ordinal Confidence modelling in Educational Assessments
need - Building Production-Grade Conversational Agents with Workflow Graphs
need - EXPLAIN: Enhancing Retrieval-Augmented Generation with Entity Summary
need - EcoDoc: A Cost-Efficient Multimodal Document Processing System for Enterprises Using LLMs
need