· ai
[Paper] Empowering Reliable Visual-Centric Instruction Following in MLLMs
Evaluating the instruction-following (IF) capabilities of Multimodal Large Language Models (MLLMs) is essential for rigorously assessing how faithfully model ou...
-
- · devops
[Paper] Software-Defined Agentic Serving
As multi-agent LLM pipelines grow in complexity, existing serving paradigms fail to adapt to the dynamic serving conditions. We argue that agentic serving syste...
- · ai
[Paper] Sparse Knowledge Distillation: A Mathematical Framework for Probability-Domain Temperature Scaling and Multi-Stage Compression
We develop a unified theoretical framework for sparse knowledge distillation based on probability-domain softening operators. While the equivalence p^{1/T} prop...
- · ai
[Paper] X-MuTeST: A Multilingual Benchmark for Explainable Hate Speech Detection and A Novel LLM-consulted Explanation Framework
Hate speech detection on social media faces challenges in both accuracy and explainability, especially for underexplored Indic languages. We propose a novel exp...
- · ai
[Paper] UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision
While Unified Multimodal Models (UMMs) have achieved remarkable success in cross-modal comprehension, a significant gap persists in their ability to leverage su...
- · ai
[Paper] MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
The hallmark of human intelligence is the ability to master new skills through Constructive Episodic Simulation-retrieving past experiences to synthesize soluti...
- · ai
[Paper] AnatomiX, an Anatomy-Aware Grounded Multimodal Large Language Model for Chest X-Ray Interpretation
Multimodal medical large language models have shown impressive progress in chest X-ray interpretation but continue to face challenges in spatial reasoning and a...
- · ai
[Paper] Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning
Machine unlearning aims to forget sensitive knowledge from Large Language Models (LLMs) while maintaining general utility. However, existing approaches typicall...
- · ai
[Paper] Decentralized Autoregressive Generation
We present a theoretical analysis of decentralization of autoregressive generation. We define the Decentralized Discrete Flow Matching objective, by expressing ...
- · ai
[Paper] Multi-Modal Data-Enhanced Foundation Models for Prediction and Control in Wireless Networks: A Survey
Foundation models (FMs) are recognized as a transformative breakthrough that has started to reshape the future of artificial intelligence (AI) across both acade...
- · ai
[Paper] DiffBench Meets DiffAgent: End-to-End LLM-Driven Diffusion Acceleration Code Generation
Diffusion models have achieved remarkable success in image and video generation. However, their inherently multiple step inference process imposes substantial c...
- · ai
[Paper] LSP-DETR: Efficient and Scalable Nuclei Segmentation in Whole Slide Images
Precise and scalable instance segmentation of cell nuclei is essential for computational pathology, yet gigapixel Whole-Slide Images pose major computational ch...