Browse all research

Every Research Watch entry, newest first. Search, or narrow by topic, format, peer review, publisher and date.

1211 entries

Sort

The summaries are open to everyone. Sign in, free, to read the full entry.

Preprint
Not peer reviewed
From Tencent
Artificial Intelligence

Researchers report on-device small models learning when to call on cloud LLMs

Original title: Local-First Intelligence via Proactive SLM Collaborating with Feedback-Providing LLM

A preprint describes a trained small on-device model that decides when to ask a cloud LLM for help, balancing accuracy, speed and privacy.

Added 5 Nov 2026

Preprint
Not peer reviewed
Quantum Computing

Preprint reports trainable quantum kernels matching classical ones across eight datasets

Original title: A Versatile Variational Quantum Kernel Framework for Non-Trivial Classification

A preprint describes a variational quantum kernel framework that the authors say rivals classical kernels on tabular, image, time series and graph data.

Jiang Yuhan et al. · Added 5 Nov 2026

Preprint
Not peer reviewed
From Amazon
Artificial Intelligence

Preprint proposes lightweight module to cut visual tokens in multi-image AI models

Original title: Visual Tokens on Demand: Visual Budgeting for Scalable and Efficient Multi-Image Reasoning in Multimodal LLMs

A preprint describes mmVB, a small add-on that trims visual tokens for multi-image reasoning while keeping most accuracy.

Added 5 Nov 2026

Preprint
Not peer reviewed
From NVIDIA, QMatter, Evotec UK, IQM
Quantum Computing

Preprint reports quantum-classical simulation of a receptor’s self-cleavage in a membrane

Original title: Multiscale Quantum-Classical Simulation of Protein Autoproteolysis in a Million-Atom Membrane Environment

A preprint describes a hybrid quantum-classical workflow modelling how a receptor protein cleaves itself within a realistic, million-atom membrane environment.

Added 5 Nov 2026

Preprint
Not peer reviewed
From Sber
Artificial Intelligence

Researchers report conditions where zero-shot LLMs match small labelled datasets

Original title: Do You Even Need More Data? Rethinking LLM Deployment for Label-Scarce Tabular Classification with TabLens

A preprint introduces TabLens, a benchmark testing when LLMs can substitute for labelled data, prompt detail, or expert rules in tabular classification.

Added 5 Nov 2026

Preprint
Not peer reviewed
Artificial Intelligence

A preprint reports energy gains from quantizing LLMs depend heavily on prompt and output length

Original title: Towards Green AI: Evaluating Energy Efficiency for Quantized LLM Inference

A preprint finds quantized LLM inference saves most energy with long inputs and short outputs, with latency tracking energy use closely.

Petar Basta · Added 5 Nov 2026

Preprint
Not peer reviewed
Artificial Intelligence

Preprint reports distilling production LLM decisions into a cheaper small model

Original title: Iterate on an LLM, Serve on an SLM

A preprint describes refining an agent's behaviour on a large model, then distilling recorded decisions into a smaller one for cheaper, faster serving.

Keegan Wang · Added 5 Nov 2026

Preprint
Not peer reviewed
Artificial Intelligence

Preprint finds LLMs split on who gets access: needy regions or Global North

Original title: Need or Reputation? Region, National Income, and Academic Status in LLM Gatekeeping Decisions

A preprint reports large and small LLMs diverge sharply in simulated gatekeeping of academic resources by region, income and seniority.

Nouar AlDahoul et al. · Added 5 Nov 2026

Preprint
Not peer reviewed
From Martian
Artificial Intelligence

Researchers report a code-grounded test arena exposes hidden AI agent safety risks under pressure

Original title: AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation

A preprint describes an automated testing framework where AI agent risk rates rose sharply once scenarios added pressure or temptation.

Added 5 Nov 2026

Preprint
Not peer reviewed
Quantum Computing

A preprint proposes a new time-bin encoding for swapping photon qubit information

Original title: Parity-Based Time-Bin Encoding Enabling SWAP Between Polarization and Time-Bin Qubits

Researchers describe a parity-based time-bin encoding that lets polarisation and time-bin qubits on a single photon be swapped using standard optics.

Adam Sultan et al. · Added 5 Nov 2026

Preprint
Not peer reviewed
Quantum Computing

Researchers report faster quantum algorithms for estimating Rényi entropy

Original title: Improved Quantum Algorithms for Rényi Entropies Estimation

A preprint presents quantum algorithms that cut the number of queries needed to estimate Rényi entropy of a distribution.

Zongxing Xiong et al. · Added 5 Nov 2026

Preprint
Not peer reviewed
From Meta, Apple
Artificial Intelligence

Preprint proposes instruction-switchable LLM alignment method called CITA

Original title: ECLIPTICA — A Framework for Switchable LLM Alignment via CITA – Contrastive Instruction-Tuned Alignment

A preprint introduces CITA, a method letting one model checkpoint switch alignment behaviour via natural-language instructions rather than retraining.

Added 4 Nov 2026

Preprint
Not peer reviewed
From Infinigence-AI
Artificial Intelligence

Researchers propose history-free speculative decoding to speed up agentic LLM inference

Original title: DLite: History-free Speculative Decoding for Agentic AI

A preprint introduces DLite, a draft model that skips historical context to improve speculative decoding for agentic AI tasks.

Added 4 Nov 2026

Preprint
Not peer reviewed
Quantum Computing

Researchers report digital quantum simulation of Schwinger model under strong electric field

Original title: Digital Quantum Simulation of Nonequilibrium Dynamics in the Schwinger Model under a Strong External Electric Field

A preprint tests whether VQE plus Trotter evolution can reproduce strong-field Schwinger model dynamics seen in exact diagonalisation.

Haobin Chen et al. · Added 4 Nov 2026

Preprint
Not peer reviewed
From iFLYTEK
Artificial Intelligence

Researchers report a two-stage method for better multi-constraint instruction following

Original title: STAIF: A Stage-wise Optimization for Complex Instruction Following

A preprint describes STAIF, which separates soft and hard instruction constraints into two training stages to improve compliance.

Added 4 Nov 2026

Preprint
Not peer reviewed
Quantum Computing

Hybrid quantum-classical method tackles Fermi-Hubbard ground states without feedback loop

Original title: Explicitly correlated ground states with a feedback-free variational hybrid algorithm

A preprint reports a feedback-free hybrid algorithm that prepares momentum-space states on a quantum processor and optimises correlations classically afterwards.

Benjamin Corbett et al. · Added 4 Nov 2026

Preprint
Not peer reviewed
Artificial Intelligence

Researchers report LLM-written malware varies widely but keeps detectable seams

Original title: The Infinite Mutation Engine? Measuring Polymorphism in LLM-Generated Offensive Code

A preprint finds that Claude Opus 4.6 can generate structurally diverse malicious code cheaply, yet a single static signature still catches every sample.

Gabriel Hortea et al. · Added 4 Nov 2026

Preprint
Not peer reviewed
Quantum Computing

Researchers quantify when data re-uploading helps amplitude-embedded quantum models

Original title: A Tutorial on Quantum Amplitude Embedding with Data Re-Uploading

A preprint explains how repeating data uploads boosts amplitude-embedded quantum models, but only for higher-order targets.

Hyojun Ahn et al. · Added 4 Nov 2026

Preprint
Not peer reviewed
From Microsoft
Artificial Intelligence

Preprint proposes graph-based credit assignment for long-horizon LLM agent training

Original title: Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning

A preprint describes G2PO, a reinforcement learning method that models agent trajectories as a state-transition graph to sharpen credit assignment.

Added 4 Nov 2026

Preprint
Not peer reviewed
Artificial Intelligence

Agentic framework evolves jailbreak attack skills against frontier LLMs

Original title: RedDarwin: Evolving Jailbreak Skills against Frontier LLMs

A preprint reports an agent-driven system that evolves jailbreak attack skills, substantially raising success rates against frontier language models.

Zhouyuan Ma et al. · Added 4 Nov 2026