Research Intelligence
Papers and results from labs and universities: training, evaluation, robotics and new methods. 296 articles in the last 30 days.
The Download: mice with part-human brains and climate tech innovators
Thomas Macaulay · MIT Technology Review AI · 17 Sept 2026
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Meet a mouse
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the wor
Meet the innovators under 35 shaping climate tech
Casey Crownhart · MIT Technology Review AI · 17 Sept 2026
Each year, the editorial team at MIT Technology Review puts together a list of 35 innovators under 35—a group of researchers, inventors, and other you
Each year, the editorial team at MIT Technology Review puts together a list of 35 innovators under 35—a group of researc
Making AI-Assisted Claims Independently Challengeable: Publication Authority and a Protocol for Falsifiable Publication Records
Torsten Olivi Tiltack, Yifei Dong, Kun Yu, Xu Wang, Wei Liu, Jianlong Zhou, Ren Ping Liu, Fang Chen · arXiv · 17 Sept 2026
arXiv:2609.17631v1 Announce Type: new Abstract: AI-assisted claims can appear authoritative when evidence, analysis, human authorization, presentation
arXiv:2609.17631v1 Announce Type: new Abstract: AI-assisted claims can appear authoritative when evidence, analysis, hum
EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents
Sehee Kim, Yumin Choi, Minki Kang, Sung Ju Hwang · arXiv · 17 Sept 2026
arXiv:2609.17632v1 Announce Type: new Abstract: Large language model (LLM) trading agents can combine market data, news, and executable analysis, but
arXiv:2609.17632v1 Announce Type: new Abstract: Large language model (LLM) trading agents can combine market data, news,
One Color Preprocessing Improves DSATUR
Adam Nouira, Lucas Isenmann · arXiv · 17 Sept 2026
arXiv:2609.17633v1 Announce Type: new Abstract: The Graph Coloring Problem (GCP) is NP-hard and DSATUR stands as one of the fastest heuristics for it
arXiv:2609.17633v1 Announce Type: new Abstract: The Graph Coloring Problem (GCP) is NP-hard and DSATUR stands as one of
Physics-Constrained Digital Twins for Sensor Integrity in Urban Pedestrian Flow: Detecting Stealthy False Data Injection with Conformal Guarantees
Oscar Mogollon Gutierrez, Fatemeh Ghasemi, Mohammadhossein Homaei, Andres Caro, Mar Avila · arXiv · 17 Sept 2026
arXiv:2609.17635v1 Announce Type: new Abstract: City pedestrian counting systems now feed economic indicators, planning decisions and safety operation
arXiv:2609.17635v1 Announce Type: new Abstract: City pedestrian counting systems now feed economic indicators, planning
What You Can't See Is Still What You Learn: A Preregistered Sixty-Society Confirmation That Evidence Masking Drives Compositional Generalization
Narcis Marincat · arXiv · 17 Sept 2026
arXiv:2609.17637v1 Announce Type: new Abstract: Restricting what a module can read may improve what a system learns to compute. We test this in a prer
arXiv:2609.17637v1 Announce Type: new Abstract: Restricting what a module can read may improve what a system learns to c
CapMem: A Benchmark for Caption-Based Episodic Memory in Egocentric Video
Dingli Liang, Yiqiao Xie, Yukai Huang, Zhaokai Wang, Weitong Cai, Guangwen Feng, Jifei Song, Zhensong Zhang, Hang Zhang · arXiv · 17 Sept 2026
arXiv:2609.17688v1 Announce Type: new Abstract: Wearable assistants require episodic memory over egocentric video, yet current vision-language models
arXiv:2609.17688v1 Announce Type: new Abstract: Wearable assistants require episodic memory over egocentric video, yet c
GraphEcho: Structural Redundancy and Evidence Provenance in LLM Graph Agents
Sikun Wang, Yixi Zhou, Lei Fan, Fan Zhang · arXiv · 17 Sept 2026
arXiv:2609.17695v1 Announce Type: new Abstract: A large language model (LLM) agent can follow more graph paths without acquiring more independent evid
arXiv:2609.17695v1 Announce Type: new Abstract: A large language model (LLM) agent can follow more graph paths without a
GVD: Governed Versioning and Deduplication for Document Repositories
Mohammadreza Sediqin, Shivali Dalmia, Sumukha Thoppanahalli, Abhishek Mukherji · arXiv · 17 Sept 2026
arXiv:2609.17696v1 Announce Type: new Abstract: Document repositories evolve continuously. Guidelines and policies are revised, superseded, and re-upl
arXiv:2609.17696v1 Announce Type: new Abstract: Document repositories evolve continuously.
NeMo Data Designer: An Extensible Framework for Multimodal Synthetic Data Generation
Johnny Greco, Nabin Mulepati, Andre Manoel, Eric Tramel, Kirit Thadaka, Mike Knepper, Dhruv Nathawani, Dane Corneil, Yev Meyer, Alex Watson, Maarten Van Segbroeck · arXiv · 17 Sept 2026
arXiv:2609.17699v1 Announce Type: new Abstract: We present NeMo Data Designer (NDD), an open-source, general-purpose framework for multi-modal synthet
arXiv:2609.17699v1 Announce Type: new Abstract: We present NeMo Data Designer (NDD), an open-source, general-purpose fra
A Systematic Evaluation of the COTQ Provincial Land Cover Product: Structural Consistency, Spectral Separability, and Relative Positioning Against ESA, ESRI, and Google Products
\'Etienne Clabaut, Samuel Foucher, Yacine Bouroubi · arXiv · 17 Sept 2026
arXiv:2609.17731v1 Announce Type: new Abstract: High-resolution land use and land cover (LULC) products derived from Sentinel-2 imagery are widely use
arXiv:2609.17731v1 Announce Type: new Abstract: High-resolution land use and land cover (LULC) products derived from Sen
Imitation Learning for Autonomous Driving in CARLA
Jordy Kieto · arXiv · 17 Sept 2026
arXiv:2609.17757v1 Announce Type: new Abstract: Behavioral cloning trains a policy offline on expert demonstrations, but deployment is closed loop: ea
arXiv:2609.17757v1 Announce Type: new Abstract: Behavioral cloning trains a policy offline on expert demonstrations, but
SAGE: Governed Artifact Generation from Enterprise Guidelines
Mohammadreza Sediqin, Shivali Dalmia, Sumukha Thoppanahalli, Srinivasa Karthikeya Reddy Kovvuri, Abhishek Mukherji · arXiv · 17 Sept 2026
arXiv:2609.17775v1 Announce Type: new Abstract: Enterprise guideline documents mix narrative text, complex tables, and embedded images, and converting
arXiv:2609.17775v1 Announce Type: new Abstract: Enterprise guideline documents mix narrative text, complex tables, and e
FairCompressAgent: An Agentic Framework for Fairness-Aware Model Compression for FPGA Deployment
Yuanbo Guo, Yiyu Shi · arXiv · 17 Sept 2026
arXiv:2609.17786v1 Announce Type: new Abstract: Fairness-aware model compression requires selecting methods and configurations that balance accuracy,
arXiv:2609.17786v1 Announce Type: new Abstract: Fairness-aware model compression requires selecting methods and configur
A Four-Stage Decomposition of Word-Problem Solving and Mechanistic Fragility in LLM Math Reasoning
Zhongdi Qu, Carla P. Gomes · arXiv · 17 Sept 2026
arXiv:2609.17804v1 Announce Type: new Abstract: Large language models solve grade-school math word problems with high accuracy, yet a single irrelevan
arXiv:2609.17804v1 Announce Type: new Abstract: Large language models solve grade-school math word problems with high ac
Learning Heterogeneous Preferences
Shiwali Mohan, Matt Hong, Dule Shu, Aniek Fransen, Shabnam Hakimi, Matt Klenk · arXiv · 17 Sept 2026
arXiv:2609.17847v1 Announce Type: new Abstract: Learning from human feedback has become a central paradigm for training modern AI systems, where model
arXiv:2609.17847v1 Announce Type: new Abstract: Learning from human feedback has become a central paradigm for training
SNOMED CT Concept Recommendation from Masked Clinical Context
Ali Noori · arXiv · 17 Sept 2026
arXiv:2609.17855v1 Announce Type: new Abstract: Standardizing clinical language to SNOMED CT supports interoperability, analytics, and reusable phenot
arXiv:2609.17855v1 Announce Type: new Abstract: Standardizing clinical language to SNOMED CT supports interoperability,
The Inference Engineering Pareto Atlas: Which Optimizations Dominate the Cost, Quality, and Latency Frontier?
Srikanta Datta Tumkur, Jay Iyer, Mehar Simhadri, Sai Pavan Kumar, Sai Kapil Kumar, Ramesh Nampelly · arXiv · 17 Sept 2026
arXiv:2609.17863v1 Announce Type: new Abstract: LLM inference optimizations report speedups on different models, GPUs, prompts, and quality metrics, m
arXiv:2609.17863v1 Announce Type: new Abstract: LLM inference optimizations report speedups on different models, GPUs, p
Do Frontier Models Seek Safety Evidence Before Acting?
Omer Tafveez · arXiv · 17 Sept 2026
arXiv:2609.17865v1 Announce Type: new Abstract: Frontier models are often evaluated on how they respond to safety information once it is already in co
arXiv:2609.17865v1 Announce Type: new Abstract: Frontier models are often evaluated on how they respond to safety inform