Skip to content

Research separate from news

What could become important next

A preprint is a signal, not a finished product or an independently confirmed result. We therefore track research papers separately and show the actual state of supporting evidence for each one.

1381 published research events

Latest work

A significant claim from a single source is published only after further confirmation.

Research only one source so far

Self-distillation with privileged information fails on difficult tasks

The arXiv research paper reproduces the claimed successes of self-distillation (SD) and explains its failures on QA, mathematics, coding and agentic tool use. The method works on simple tasks; on harder ones, training loss decreases but accuracy does not improve. The cause is ‘PI bias’: The teacher…

arXiv cs.AI (Artificial Intelligence) Original source ↗
Research only one source so far

A model of long-term AI system persistence without cumulative deterioration

The arXiv study presents Redundancy-Adjusted Artificial Age Score, a mathematical framework for analyzing whether AI systems can operate indefinitely without unbounded growth in structural age. The main result: When redundancy conditions are met, a system can pass through infinitely many cycles with bounded age-related…

arXiv cs.AI (Artificial Intelligence) Original source ↗
Research only one source so far

Protecting pretrained weights with deep low-rank residual networks

The research paper introduces DLR-Lock, a method protecting pretrained models against unauthorized adaptation. It replaces MLP layers with deep low-rank residual networks that increase memory during the backward pass and make fine-tuning harder. It preserves the model's original capabilities.

Apple Machine Learning Research Original source ↗
Research only one source so far

OncoTriad-QA: A benchmark for oncology diagnosis

The OncoTriad-QA benchmark combines radiological, pathological and genomic data with 86.1 thousand questions from 9 thousand patients. OncoVLM outperforms MedGemma-4B by 10.7 points in multimodal oncology analysis.

arXiv cs.CL (Computation and Language / NLP) Original source ↗
Research only one source so far

ANCHOR-RE: A neuro-symbolic framework for biomedical relation extraction

The ANCHOR-RE research framework integrates ontology-guided reasoning and verification rules into LLM inference for biomedical relation extraction. It improved performance on three benchmarks: SemRepGS 0.654→0.676, DDI 0.769→0.872, ChemProt 0.939→0.941; accuracy on post-cutoff data was 69%.

arXiv cs.CL (Computation and Language / NLP) Original source ↗
Research only one source so far

AS-FedBridge: federated learning with mixed artificial and spiking neurons

The research team publishes AS-FedBridge, a framework for federated learning on resource-constrained devices. It combines artificial neural networks and spiking neural networks, which offer greater energy efficiency. The framework introduces a bridge with a Pseudo-Spike interface for transforming continuous signals into…

arXiv cs.LG (Machine Learning) Original source ↗
Research only one source so far

New DDRSR method for symbolic regression

A research paper from arXiv introduces DDRSR (Deep Divide-and-Reduce), a method that improves the approach to symbolic regression. The new method addresses problems with the previous method, AI Feynman – it expands the options for decomposing expressions, avoids brute-force search and increases practical usability. It includes…

arXiv cs.LG (Machine Learning) Original source ↗
Research only one source so far

Interface damage during KDA linearization: Diagnosing and repairing Qwen3-0.6B-Base

The research team converted 21 of the 28 attention layers in Qwen3-0.6B-Base to KDA linear attention. After conversion, the model fixated on the answer position (choosing ‘A’ 81% of the time) rather than following the content, and accuracy fell to 25–29%. Format-targeted KL + SFT + DPO raised C-Eval by +12.48 points. Code and weights released.

arXiv cs.CL (Computation and Language / NLP) Original source ↗
Research only one source so far

MemArena: A benchmark for personal assistants with memory management on edge devices

The MemArena benchmark tests personal AI assistants with memory management on edge devices using open-weight models. The research involves 50 agents communicating over 15 days. Key findings: the memory backend is more important for accuracy than model size; all systems struggle with permission-aware access…

arXiv cs.CL (Computation and Language / NLP) Original source ↗
Research only one source so far

TabletCraft: bidirectional neural translation of Akkadian and cuneiform rendering

The article introduces TabletCraft, an open-source system for bidirectional translation between Akkadian and English. The ByT5 model trained on 116K samples achieves 49.1 BLEU for Akkadian→English and 48.5 BLEU for English→Akkadian (the first published result in the reverse direction). The system integrates…

arXiv cs.CL (Computation and Language / NLP) Original source ↗
Research only one source so far

Apple research on controlling outlier tokens in diffusion transformers

The Apple ML Research team identified a problem with outlier tokens in diffusion transformers (DiTs) for image generation — a few high-norm tokens reduce quality. They proposed Dual-Stage Registers (DSR), with training-time and test-time registers. Testing on ImageNet and in text-to-image…

Apple Machine Learning Research Original source ↗
Research only one source so far

AI adoption in organizations does not curb R&D waste

A third of companies spend 25–40% of their R&D budget on projects with no output, and nearly half of teams estimate a loss of >1 million dollars per project. According to IEEE Spectrum, companies apply AI more to analysis and modeling than to decision-making in early ideation and feasibility, where it would have the greatest effect.

IEEE Spectrum — Artificial Intelligence Original source ↗