AI and infrastructure news
Filter by type: Paper273
- 19 days ago
arxiv.orgTest-time training layers for sequence modeling
A paper published on September 24, 2026 presents sequence-modeling layers with linear complexity and hidden states updated through self-supervised learning.
- 19 days ago arxiv.org
Sparse layers and looping for scaling language models
An article published on September 26, 2026 compares standard Transformers and Mixture-of-Experts, with and without looping, and reports a scaling advantage for Looped-MoE models.
- 19 days ago arxiv.org
CAMI evaluates RAG indexes under a limited budget
Published on June 30, 2026, the CAMI paper proposes selecting semantic enrichment indexes for ingestion pipelines based on retrieval goals and computational cost.
- 19 days ago arxiv.org
CMDR evaluates multimodal retrieval across document pages
Published on July 8, 2026, the article presents CMDR and CMDR-Bench for retrieving relevant pages from multimodal documents, including queries that depend on context across pages.
- 19 days ago arxiv.org
CodeMidas proposes generating RL tasks from code
On September 21, 2026, CodeMidas presented a pipeline that converts features from open-source projects into executable reinforcement-learning environments for programming.
- 19 days ago openreview.net
How agents can learn from interaction traces
A survey published on June 27, 2026, discusses how agents in production turn interaction traces into durable capabilities, from self-evolution to meta-evolution.
- 19 days ago arxiv.org
Extending frozen LLMs to understand audio
A paper dated September 28, 2026, proposes injecting audio-conditioned vectors into a frozen LLM's KV cache to add audio understanding without tuning model weights.
How to evaluate AI agent memory
An article published on June 26, 2026 examines agent memory systems and notes that existing evaluations often treat memory as a black box.
- 19 days ago arxiv.org
Evaluating efficient attention in hybrid models
Published on June 16, 2026, the paper examines sliding-window attention and recurrent sequence mixers in hybrid language models, focusing on scalability, mechanisms, and architecture decisions.
- 19 days ago arxiv.org
How to assess autoregressive inference bottlenecks
An ICLR 2026 paper addresses a decoding bottleneck in probabilistic Transformer models. Companies can measure inference performance and identify opportunities for optimization.
- 19 days ago arxiv.org
How to evaluate asynchronous RL for agent post-training
A post published on July 9, 2026 discusses asynchronous RL for language-model post-training, updates as rollouts arrive, and stability techniques.
- 19 days ago arxiv.org
Comparing RAG approaches for semi-structured data
A paper published on June 25, 2026 presents a framework for comparing four RAG approaches across nine standardized scenarios.
- 19 days ago arxiv.org
How to allocate capacity in hierarchical search agents
An article published on July 9, 2026 examines delegation and execution roles in hierarchical search agents and identifies task decomposition as the main performance bottleneck.
- 19 days ago arxiv.org
How reinforcement learning is distributed across LLM layers
A preprint published on July 15, 2026, examines how reinforcement learning adaptation is distributed across transformer layers during LLM post-training.
- 19 days ago arxiv.org
How LLMs represent sums and arithmetic errors
An article published on June 28, 2026, analyzes internal representations during sums with multiple operands and proposes a geometric model to explain arithmetic errors.
- 19 days ago net.in.tum.de
How to observe packet paths through the Linux kernel
Published on June 27, 2026, the publication covers the path a packet takes through the Linux kernel and how this knowledge can help engineers analyze Linux network behavior.
- 19 days ago arxiv.org
Reducing Cost and Latency in LLM Applications
A July 10, 2026 article explores alternatives to long reasoning chains to balance accuracy, context size, compute cost, and latency.
- 19 days ago arxiv.org
Reducing training–inference gaps in RL for LLMs
An article published on June 30, 2026 discusses inconsistent probabilities between training and inference engines and describes TIS and checkpoint rejection when rewards diverge.
- 19 days ago arxiv.org
How to test n-gram lookups in language models
A technical publication dated August 25, 2026 describes Engram, a module that retrieves n-gram embeddings and can move its lookup table to the CPU with little inference slowdown.
How to verify rewards for coding agents
A paper published on July 11, 2026 examines four reward-verification designs and finds no single solution to the challenge of reliably evaluating coding agents.
- 19 days ago arxiv.org
Sharing QKV projections in Transformers
A paper published on July 2, 2026 evaluates attention variants that share projections and reports that equating key and value was excessive for the author's small ternary LLMs.
- 19 days ago arxiv.org
Lightweight compression reduces vectors in ColBERT systems
Published on July 8, 2026, the paper describes pooling-aware fine-tuning with k-means to reduce token vectors per document in ColBERT models, with no loss of accuracy according to the publication.
- 19 days ago arxiv.org
CTM-AI explores an AI architecture inspired by consciousness
Published on August 25, 2026, the article presents the early CTM-AI project, which applies the Conscious Turing Machine to AI architecture without reporting benchmark results.
- 19 days ago arxiv.org
Depth-wise batching in recurrent models: how to assess it
A post published on September 2, 2026 describes how overlapping requests at different recurrent depths may improve utilization in models with adaptive compute.
- 19 days ago arxiv.org
DepthBench proposes evaluating computational depth in Transformers
Presented on September 29, 2026, DepthBench compares information-flow approaches and examines whether they help deeper Transformers use their layers effectively.
- 19 days ago arxiv.org
Black-box LLM distillation with GAD
An article dated September 13, 2026 presents an on-policy method for distilling models using only the text outputs of a proprietary teacher.
- 19 days ago arxiv.org
Distilling Transformers into Mamba models
A paper published September 29, 2026 studies transferring knowledge from pretrained Transformers to state space models such as Mamba.
- 19 days ago arxiv.org
Diffusion-GR2 speeds up reasoning-based reranking
A post dated July 2, 2026 reports that Diffusion-GR2 achieves ranking accuracy close to an autoregressive model, with decoding 2.4–3.5 times faster.
DiscoBench tests search agents on ambiguous requests
Published on June 29, 2026, DiscoBench evaluates whether language-model search agents can handle vague, underspecified, or factually incorrect requests in multi-step retrieval and reasoning tasks.
- 19 days ago arxiv.org
Two-phase distillation for multitask models
A paper published on June 30, 2026 studies consolidating reinforcement-learning specialists into a multitask model through off-policy and on-policy distillation.
Dockerless proposes verifying patches without execution
Published on June 30, 2026, the paper describes a verifier that assesses coding-agent patches without running them. The proposal targets selecting SFT trajectories and providing rewards for RL, as an alternative to setting up repository-specific environments.
- 19 days ago arxiv.org
DreamSmooth smooths sparse rewards in RL
Presented in an ICLR paper published on June 28, 2026, DreamSmooth applies temporal reward smoothing in model-based RL and was evaluated on RoboDesk and Shadow Hand.
- 19 days ago arxiv.org
Dual-Cache: sharing context across LLMs
A paper published on September 26, 2026 presents a latent protocol for transferring information across heterogeneous models by translating KV caches and adding joint mixing between layers.
- 19 days ago arxiv.org
EfficientRollout speeds up RL rollouts for LLMs
A paper dated July 5, 2026 describes system-adaptive self-speculative decoding and reports up to 19.6% faster rollout generation.
- 19 days ago arxiv.org
Relevance embeddings for candidate retrieval
A Yandex paper published on July 7, 2026 describes query and item embeddings to retrieve candidates efficiently when relevance scoring is costly.
- 19 days ago arxiv.org
EnvACE rehearses the world to train agents
Published on August 9, 2026, the article describes a reinforcement learning method that replaces interactions with external environments with internal rehearsals during agent training.
- 19 days ago arxiv.org
Learning-rate scaling in LLMs may be nonlinear
An article published on June 30, 2026, evaluates learning rates in GPT-2-style models ranging from 22 million to 707 million parameters, trained on 5 billion to 100 billion tokens.
- 19 days ago usenix.org
Study reports code overlap in network filtering systems
A USENIX Security paper reports code overlap between leaked Geedge Networks code and China's Great Firewall, including DNS and RST packet injection.
EvoRec proposes agents to optimize recommendations
Published on June 30, 2026, the paper presents a multi-agent framework intended to reduce manual optimization of recommendation systems by retaining methods across iterations and exploring ideas beyond a predefined search space.
ExploitGym evaluates AI agents on vulnerability exploitation
The ExploitGym research proposes evaluating whether AI agents can turn vulnerabilities into impacts such as unauthorized file access or code execution.
Let's assess your project
I reply with scope and a proposal.