Research Feed Page 29

Search source-linked summaries of recent AI and machine-learning papers by topic, by date, or by whether they include code or a diagram.

Filter papers All papers

Browse by date

Resource filters

Sort options

Research results

Multimodal / Computer Vision By Haoyu Yang 2026-08-10
MedPixel: A Unified Pixel-Language Model for Medical Reasoning and Segmentation

MedPixel combines visual reasoning and image segmentation into a single architecture to bridge the gap between clinical text and pixel-level data.

Agents / Efficiency & Inference By Kaican Li 2026-08-11
InSight-doc: Agentic Visual Perception for Long-Document Understanding

InSight-doc uses an agentic system that zooms into document regions to reduce computational overhead and hallucination in multimodal models.

Agents By Giuseppe Destefanis 2026-08-11
GitSkills: A Dataset of Agent Skills on GitHub

Researchers built GitSkills, a dataset containing over 3.7 million agent instructions scraped from public GitHub repositories.

Multimodal / Training & Fine-Tuning By Changhao Xiang 2026-08-11
MultiModal Code-Switching: Interleaving Visual Objects into Language for Explicit Object-Level Alignment

MultiModal Code-Switching improves multimodal model alignment by replacing text tokens with visual object embeddings during pretraining.

Multimodal / Efficiency & Inference By Haoyu Zhang 2026-08-11 7
Ex-Omni-2D: Expressive Omni-Modal Dialogue Models with Native Visual Presence

Ex-Omni-2D generates multimodal dialogue responses that natively combine text, personalized speech, and reference-conditioned video to overcome the limitations of visually disembodied models.

Benchmarks & Evals / Reasoning By Akrin Zheng 2026-08-11
ENTLORE: A Graph-Grounded Benchmark for Latent Organizational Reasoning in Enterprise Question Answering

The authors introduce EntLORE, a graph-grounded benchmark designed to evaluate how well systems perform complex organizational reasoning beyond simple fact retrieval.

Efficiency & Inference / Benchmarks & Evals By Minsoo Kim 2026-08-11
Attention-Path Fragility as an Uncertainty Signal in Large Language Models

The paper introduces a technique called ASMI that measures model uncertainty by observing how responses change when random paths in the transformer's attention mechanism are disrupted.

Agents / Benchmarks & Evals By Shiyu Xuan 2026-08-11
Test-Time Self-Evolving GUI Visual Grounding via Reflection-Guided On-Policy Self-Distillation

The paper introduces a framework that allows GUI visual grounding models to continuously improve after deployment by learning from their own exploration failures through reflection-guided self-distillation.

Robotics / Multimodal By Yihan Lin 2026-08-10
JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling

The paper introduces JEPA-WAM, a framework that integrates spatially structured world modeling with vision-language-action policies to improve performance and robustness against distribution shifts.

Training & Fine-Tuning / Reinforcement Learning By Chris Han 2026-08-11 3
Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation

The researchers developed a reference-free post-training method to optimize machine translation models using only source-side text, bypassing the need for high-quality parallel data.

Efficiency & Inference / Multimodal By Zhuchenyang Liu 2026-08-11 2
DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation

DistilVDR creates compact single-vector document retrieval systems by distilling knowledge from large vision-language models into significantly smaller student encoders.

Agents / Benchmarks & Evals By Kushal Chakrabarti 2026-08-11
Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding

The paper identifies that agentic README files grow indefinitely due to catastrophic remembering, where the rationale for instructions is lost, and proposes a comment syntax to safely manage this metadata.

Agents / Reinforcement Learning By Qing Zong 2026-08-10 21
Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design

The paper presents a three-stage taxonomy to classify and structure how multiple agents and their environments can iteratively adapt to one another beyond static, single-entity learning models.

Agents / Safety & Alignment By Qianggang Ding 2026-08-11 37
ComBodied Agents: a New Paradigm of Human-Centric Agentic AI

The paper introduces a new framework called ComBodied Agents that focuses on supporting human wellbeing and long term goals rather than just executing isolated tasks.

Reasoning / Benchmarks & Evals By Bethel Hall 2026-08-10
VeriFin: A Neurosymbolic Framework for Verifying LLM-Generated Financial Claims

VeriFin uses a neurosymbolic framework to ground LLM financial claims in source document data and verify them using formal constraint solving.

Agents / Reasoning By Yuhang Cao 2026-08-11
Continuous Interaction Diffusion: A Diffusion-Native Runtime for Asynchronous Tool-Augmented Reasoning

The paper introduces a runtime architecture that enables diffusion language models to interact with tools asynchronously during the reasoning process.

Agents / Efficiency & Inference By Xiaofan Bai 2026-08-11 2
SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure

SkillZip optimizes agent instructions by identifying and removing redundant rules and workflows without requiring external task-based testing.

Agents / Benchmarks & Evals By Mizanur Rahman 2026-08-11 1
DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments?

The paper introduces DSAgentBench, a new benchmark designed to evaluate how effectively AI agents automate end-to-end data science workflows in realistic computer environments.

Agents / Benchmarks & Evals By Sourabrata Mukherjee 2026-08-11
Actions Speak Louder than Words: Measuring Cross-Lingual Policy Retention in Tool-Using Agents

The paper introduces a new measurement protocol to evaluate if AI agents execute the same tool-use action sequences across different languages.

Agents / Benchmarks & Evals By Junjie Ye 2026-08-11 1
SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information

SPIEval is a new human-curated benchmark designed to evaluate how effectively large language models handle complex tasks using personal information scattered across mobile applications.