Machine Learning

Tier-3 ISE final year with ongoing ML research (TMLR/Q1/NeurIPS target), trying to understand real impact in India [D]

I went through a bunch of older posts here about research vs dev roles, but most of them were either very general or not really in a simi...

UMKC Announces New Master of Science in Artificial Intelligence

UMKC announces a new Master of Science in Artificial Intelligence program aimed at addressing workforce demand for AI expertise, set to l...

Improving AI models’ ability to explain their predictions

If frontier AI labs have unlimited shovels, what's stopping them from building everything?

I found myself explaining AI tokens to my mom over the weekend. At first I related them to building bricks: blocks of data the model uses...

[2603.16790] InCoder-32B: Code Foundation Model for Industrial Scenarios

Abstract page for arXiv paper 2603.16790: InCoder-32B: Code Foundation Model for Industrial Scenarios

[2603.16430] EngGPT2: Sovereign, Efficient and Open Intelligence

Abstract page for arXiv paper 2603.16430: EngGPT2: Sovereign, Efficient and Open Intelligence

[2603.13846] Is Seeing Believing? Evaluating Human Sensitivity to Synthetic Video

Abstract page for arXiv paper 2603.13846: Is Seeing Believing? Evaluating Human Sensitivity to Synthetic Video

[2603.13294] Real-World AI Evaluation: How FRAME Generates Systematic Evidence to Resolve the Decision-Maker's Dilemma

Abstract page for arXiv paper 2603.13294: Real-World AI Evaluation: How FRAME Generates Systematic Evidence to Resolve the Decision-Maker...

[2602.08482] CLEAR: A Knowledge-Centric Vessel Trajectory Analysis Platform

Abstract page for arXiv paper 2602.08482: CLEAR: A Knowledge-Centric Vessel Trajectory Analysis Platform

[2603.12057] Coarse-Guided Visual Generation via Weighted h-Transform Sampling

Abstract page for arXiv paper 2603.12057: Coarse-Guided Visual Generation via Weighted h-Transform Sampling

[2603.09964] Understanding the Use of a Large Language Model-Powered Guide to Make Virtual Reality Accessible for Blind and Low Vision People

Abstract page for arXiv paper 2603.09964: Understanding the Use of a Large Language Model-Powered Guide to Make Virtual Reality Accessibl...

[2603.07554] Nwāchā Munā: A Devanagari Speech Corpus and Proximal Transfer Benchmark for Nepal Bhasha ASR

Abstract page for arXiv paper 2603.07554: Nwāchā Munā: A Devanagari Speech Corpus and Proximal Transfer Benchmark for Nepal Bhasha ASR

[2603.07455] Image Generation Models: A Technical History

Abstract page for arXiv paper 2603.07455: Image Generation Models: A Technical History

[2602.00665] Can Small Language Models Handle Context-Summarized Multi-Turn Customer-Service QA? A Synthetic Data-Driven Comparative Evaluation

Abstract page for arXiv paper 2602.00665: Can Small Language Models Handle Context-Summarized Multi-Turn Customer-Service QA? A Synthetic...

[2601.04497] Vision-Language Agents for Interactive Forest Change Analysis

Abstract page for arXiv paper 2601.04497: Vision-Language Agents for Interactive Forest Change Analysis

[2601.01627] JMedEthicBench: A Multi-Turn Conversational Benchmark for Evaluating Medical Safety in Japanese Large Language Models

Abstract page for arXiv paper 2601.01627: JMedEthicBench: A Multi-Turn Conversational Benchmark for Evaluating Medical Safety in Japanese...

[2601.00809] A Modular Reference Architecture for MCP-Servers Enabling Agentic BIM Interaction

Abstract page for arXiv paper 2601.00809: A Modular Reference Architecture for MCP-Servers Enabling Agentic BIM Interaction

[2512.22065] StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars

Abstract page for arXiv paper 2512.22065: StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars

[2511.23342] Overcoming the Curvature Bottleneck in MeanFlow

Abstract page for arXiv paper 2511.23342: Overcoming the Curvature Bottleneck in MeanFlow

[2512.12812] Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, and LLaMA

Abstract page for arXiv paper 2512.12812: Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, ...

[2512.10932] BabyVLM-V2: Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation Models

Abstract page for arXiv paper 2512.10932: BabyVLM-V2: Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation M...

[2512.08503] Disrupting Hierarchical Reasoning: Adversarial Protection for Geographic Privacy in Multimodal Reasoning Models

Abstract page for arXiv paper 2512.08503: Disrupting Hierarchical Reasoning: Adversarial Protection for Geographic Privacy in Multimodal ...

[2512.05658] Multilingual Medical Reasoning for Question Answering with Large Language Models

Abstract page for arXiv paper 2512.05658: Multilingual Medical Reasoning for Question Answering with Large Language Models