arXiv Machine Learning
Jul 3
The risk of KV cache compression
arXiv:2607. 01520v1 Announce Type: new Abstract: Transformer inference on long sequences is expensive because softmax attention repeatedly reads from a large KV cache.
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv AI
Jul 3
Adaptive Companionship for Group-Following Robots: Handling Dynamically Changing Group Formations
arXiv:2607. 01287v1 Announce Type: cross Abstract: Accompanying a group of humans is an essential aspect of developing human-like social cognition in robots.
arXiv AI
Jul 3
Evidence-State Rewards for Long-Context Reasoning
arXiv:2607. 02073v1 Announce Type: new Abstract: Long-context reasoning requires models to locate, revise, and synthesize evidence distributed across lengthy inputs.
arXiv AI
Jul 3
Prompt Coverage Adequacy
arXiv:2607. 02057v1 Announce Type: cross Abstract: In recent years, it has become increasingly evident that large language models (LLMs) and autonomous agents raise the level of abstraction in software development by shifting the focus from writing precise procedures to expressing intents and goals.
arXiv AI
Jul 3
DRIFTLENS: Measuring Memory-Induced Reasoning Drift in Personalized Language Models
arXiv:2607. 02374v1 Announce Type: new Abstract: Personalization changes what a model says to a user; we show that it can also change the reasoning trajectory used to justify the response.
arXiv AI
Jul 3
OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
arXiv:2607. 02461v1 Announce Type: cross Abstract: Diffusion transformers (DiTs) achieve state-of-the-art image and video generation, but their multi-step sampling and growing parameter count make inference expensive.
arXiv AI
Jul 3
Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas
arXiv:2607. 02504v1 Announce Type: cross Abstract: Long-form TV dramas present a formidable challenge for comprehensive video understanding, where deciphering complex storyline often relies on \textbf{speaker recognition}, the task of accurately attributing each spoken utterance to its respective character.
arXiv Machine Learning
Jul 3
From Lab to Reality: A Practical Evaluation of Deep Learning Models and LLMs for Vulnerability Detection
arXiv:2512. 10485v2 Announce Type: replace-cross Abstract: Vulnerability detection methods based on deep learning (DL) have shown strong performance on benchmark datasets, yet their real-world effectiveness remains underexplored.
arXiv Machine Learning
Jul 3
Transformer Geometry Observatory TGO-II: Representational Similarity Observatory
arXiv:2607. 02386v1 Announce Type: cross Abstract: While Vision Transformers have achieved remarkable success across computer vision and language applications, the geometric evolution of their internal representations throughout training remains insufficiently understood.
arXiv AI
Jul 3
The Wiola Architecture for Efficient Small Language Models
arXiv:2607. 01394v1 Announce Type: new Abstract: We present Wiola, a fully original Small Language Model (SLM) architecture built from first principles, sharing no structural lineage with any existing model family including GPT, LLaMA, Mistral, or Falcon.
arXiv Machine Learning
Jul 3
Recursive Models for Long-Horizon Reasoning
arXiv:2603. 02112v2 Announce Type: replace Abstract: Modern language models reason within bounded context, an inherent constraint that poses a fundamental barrier to long-horizon reasoning.
arXiv AI
Jul 3
Grounded autonomous scrutiny at scale: emergent critique from reproduction of published computational physics papers
arXiv:2604. 12198v2 Announce Type: replace-cross Abstract: Autonomous LLM agents now produce complete research artifacts in machine-learning sandboxes, but real computational physics is harder: experiments are first-principles calculations against re-runnable physical ground truth, and meaningful new work almost always builds on a key existing paper.
arXiv AI
Jul 3
OmniGAIA: Towards Native Omni-Modal AI Agents
arXiv:2602. 22897v3 Announce Type: replace Abstract: Human intelligence naturally intertwines omni-modal perception -- spanning vision, audio, and language -- with complex reasoning and tool usage to interact with the world.
Hugging Face Trending Papers
Jul 2
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
Understanding and reasoning over long contexts has become a key requirement for deploying large language models (LLMs) in realistic applications. Although recent LLMs support increasingly long context windows, they often fail to use relevant evidence that is already present in the input, revealing a gap between context access and effective context utilization.
Hugging Face Trending Papers
Jul 2
From SRA to Self-Flow: Data Augmentation or Self-Supervision?
Representation alignment has become an effective way to accelerate diffusion transformer training and improve generation quality. Recent self-alignment methods, such as SRA and Self-Flow, further remove the dependency on external pretrained encoders by constructing alignment within the diffusion model itself.
Hugging Face Trending Papers
Jul 2
Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation
Post-training large language models (LLMs) without real-world interaction feedback or human-labeled supervision remains challenging, particularly in specialized domains where expert annotations are costly to obtain. Recent annotation-free self-evolution methods address this by using the model's own outputs as supervision signals, constructing a teacher via additional context and aggregating predictions across multiple rollouts through majority voting to produce pseudo-labels.
Hugging Face Trending Papers
Jul 2
WattGPU: Predicting Inference Power and Latency on Unseen GPUs and LLMs
Large Language Model (LLM) inference workloads are a rapidly growing contributor to data center energy consumption. Optimizing these deployments requires matching specific LLMs to the most efficient GPUs, but operators currently lack the tools to do so without exhaustively profiling each combination.
Hugging Face Trending Papers
Jul 2
A Hippocampus for Linear Attention: An Exact Memory for What the Recurrent State Forgets
Linear-attention and state-space language models compress the prefix into a fixed-size recurrent state, yielding O(1) memory at the cost of a lossy exact memory: when many key--value associations compete, earlier facts are overwritten and needle recall degrades. Inspired by Complementary Learning Systems, we give linear attention a hippocampal complement.
Hugging Face Trending Papers
Jul 2
AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein Recognition
Vein recognition is a secure biometric technology often constrained by limited annotated data and imaging variations. While data augmentation mitigates this, strategies designed for natural images may disrupt the fine-grained topology and textures essential for identity discrimination.
Hugging Face Trending Papers
Jul 2
CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning
Reasoning Language Models (RLMs) have significantly improved performance on complex tasks by extending the reasoning chain. However, these chains are prone to containing factual errors, particularly in knowledge-intensive tasks.