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

Codec-Gauge: Optimizing KV-cache compression in Transformers

A scientific paper introduces Codec-Gauge, a technique using learned orthogonal channel transformations for more efficient KV-cache compression in Transformers. Across six models with 3–6 bits/value, it achieved a 44% reduction in KL divergence compared with raw coordinates and outperformed DCT, PCA and Hadamard controls.

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

Intelligent caching in systems with multiple AI agents

A research paper on arXiv describes a new cache eviction strategy in multi-agent systems. The strategy combines recomputation costs, the number of graph dependencies and agent invocation frequency. On three benchmarks, it reduces latency by up to 64.7 % compared with no caching and by 31.1 %…

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

DC-Leap: Accelerating diffusion language models without training

A preprint introduces DC-Leap, a method for accelerating diffusion LLM inference without retraining. It uses a dynamic verification strategy to address Joint Probability Dependence Error and draft-guided decoding. Tests show speedups of up to 53× on MBPP, or 105× with KV-Cache, with…

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

InferenceBench: A benchmark for optimizing LLM inference using AI agents

A new benchmark evaluates AI agents optimizing LLM inference on an H100 GPU within a 2-hour limit. Agents achieve speedups of up to 8× over PyTorch and approach vLLM, but fall short of hyperparameter optimization (11.53×). The identified problem is not domain knowledge but the ability to propose and…

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

Semi-supervised distillation of text-attributed graphs

A research paper on arXiv introduces an algorithm for more efficient processing of text-attributed graphs with LLMs. The method combines data distillation with Wasserstein Distance and generates textual summaries. It achieves a better performance-compression trade-off in downstream tasks.

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

Regex filters in LLM security: A study of zero effectiveness against adversarial attacks

A study examines whether regex filters improve the security of LLM applications using Gemini-2.5-flash. Across 45 adversarial attempts, the filter never blocked dangerous content (0 %), although an LLM judge detected refusals in 56–100 % of cases. Conclusion: the effectiveness of model alignment depends on the measurement metric.

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

Conflict resolution in air corridors under degraded surveillance using multi-agent reinforcement learning

A research study develops a Deep Q-Network framework for autonomous conflict resolution between heterogeneous unmanned aircraft and EVTOL in 3D corridors. Tests across 90 traffic density combinations showed that conflicts are usually resolved within 1 second and agents maintain their heading 79 % of the time.

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

SalesLoop: Improving sales lead ranking with reinforcement learning

A research paper introduces SalesLoop, a method for ranking potential customers in CRM systems using reinforcement learning based on actual sales outcomes. Tests show a +7.9 % increase in NDCG@K and +15.8 % in P@K, with a production A/B test at a Chinese electric vehicle manufacturer with 16.5 million leads…

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

Uncertainty estimation in medical AI improves clinical decisions

Research showed that Monte Carlo dropout applied to an X-ray classifier improves detection of incorrect diagnoses (AUROC +0.023). When the uncertainty signal was presented as a binary warning rather than numerical scores, doctors reduced confidently wrong diagnoses from 8.5 % to 2.7 %. Uncertainty carries decision value…

arXiv cs.LG (Machine Learning) Original source ↗