GRPO Training Dynamics for Small Language Models
arXiv:2609.39321v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has emerged as a memory-efficient reinforcement fine-tuning (RFT) technique for reasoning-intensive tasks. H
Knowledge catalogue
arXiv:2609.39321v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has emerged as a memory-efficient reinforcement fine-tuning (RFT) technique for reasoning-intensive tasks. H
arXiv:2609.39871v1 Announce Type: new Abstract: Hyperspectral remote sensing has advanced across diverse deep learning paradigms, including spectral spatial CNNs, Vision Transformers, Mamba, graph neu
A few days ago I released Jeff-Qwen3.5-0.8B, a small 'System 1' model that picks between options you define and returns a calibrated probability for each, in one forward pass. Speed was great on my M4
arXiv:2609.40103v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as automated judges for AI-generated content, yet a single judge is unreliable and even a panel o
arXiv:2603.26741v2 Announce Type: replace-cross Abstract: Goal-conditioned visual navigation has been a long-standing testbed for embodied AI. We study a natural language-conditioned variant, language
arXiv:2609.38789v1 Announce Type: new Abstract: Reconstruction errors in multivariate time-series anomaly detection may not reliably distinguish abnormal behavior from benign deviations. Language-deri
arXiv:2609.39547v1 Announce Type: new Abstract: GUI agents built on large language and vision-language models still struggle on unseen applications and complex multi-step tasks, as completing real GUI
arXiv:2609.38799v1 Announce Type: new Abstract: Understanding multi-perspective alternative narratives requires identifying how their information agrees, conflicts, or differs across sources. Existing
arXiv:2609.38377v1 Announce Type: new Abstract: Evaluating the physical consistency of generated videos remains a fundamental challenge. Existing approaches rely on off-the-shelf vision-language model
arXiv:2609.39291v1 Announce Type: new Abstract: Physics-informed computational methods usually optimize parameters within a functional representation whose structure is fixed in advance. This work pro
arXiv:2609.39607v1 Announce Type: cross Abstract: Skills extend an agent's capabilities by injecting instructions and information into the context, and are widely used by agents such as OpenClaw and C
arXiv:2609.39833v1 Announce Type: new Abstract: Extreme rainfall events are increasing in intensity and frequency as climate change accelerates. While kilometer-scale precipitation forecasts are criti
arXiv:2609.38265v1 Announce Type: cross Abstract: Onboard AI is gaining interest for space applications such as vessel, wildfire, and cloud detection, where real-time processing can improve mission re
arXiv:2609.38473v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) is now the standard way to ground Large Language Models (LLMs) in external knowledge, yet the design space of ret
arXiv:2609.39518v1 Announce Type: new Abstract: Effective human-AI collaboration requires partners to establish references through interaction, which becomes fragile when descriptions are ambiguous, s
arXiv:2609.35470v1 Announce Type: cross Abstract: Applied researchers increasingly convert images into features with pretrained encoders, then use those features in a downstream prediction model. The
arXiv:2609.39563v1 Announce Type: new Abstract: Existing video language models encode sampled RGB frames independently, so a long video must either exhaust the token budget or drop the changes between
arXiv:2609.39644v1 Announce Type: new Abstract: Ribosome profiling (Ribo-seq) measures ribosome distributions along mRNAs, but observed occupancy profiles also contain experiment-specific distortions
arXiv:2609.38491v1 Announce Type: new Abstract: Clinical research in psychiatry increasingly relies on large scale collection of spoken language data to identify acoustic and linguistic biomarkers. Ye
arXiv:2609.39788v1 Announce Type: new Abstract: Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and
arXiv:2609.38757v1 Announce Type: new Abstract: Large language models are increasingly participating in complex real-world tasks in the form of algorithm-design agents, designing and refining algorith
arXiv:2609.40360v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has improved the reasoning capabilities of large language models (LLMs), yet their predictions r
arXiv:2609.39741v1 Announce Type: new Abstract: Large forecasting applications often combine statistical, machine-learning, and neural models. These families solve the same problem but differ in fitte
This is impressive! Face-to-face conversation is where AI interfaces are heading. @tavus gave me early access to Griffin, a video-to-video model that watches and listens as you talk. It can interrupt
arXiv:2609.32923v2 Announce Type: replace Abstract: Wireless digital twins (DTs) rely on 3D environment models to predict radio propagation and support wireless-network decisions, yet these models are
arXiv:2609.38347v1 Announce Type: new Abstract: Quantifying collective fish behavior requires accurate trajectories, yet multi-view 3D tracking remains challenging due to frequent occlusions, visually
arXiv:2609.39265v1 Announce Type: new Abstract: The Segment Anything Model (SAM) achieves remarkable performance in visual segmentation. The latest SAM3 extends promptable segmentation to concept-leve
arXiv:2609.39232v1 Announce Type: cross Abstract: EDF relies on continuous monitoring of its power plants to detect anomalies as soon as they occur. Given the absence of a universally optimal streamin
arXiv:2609.38275v1 Announce Type: cross Abstract: Persistent memory helps LLM agents carry information across long interactions, but correct memory can still be used incorrectly when queries change or
arXiv:2609.38621v1 Announce Type: new Abstract: Two scientific findings can disagree without contradicting each other. Determining whether they conflict requires knowing whether they describe comparab
arXiv:2609.40027v1 Announce Type: new Abstract: Causal action verifiers gate an agent's state-changing tool calls by checking whether each proposed intervention is identifiable against a committed act
arXiv:2609.37788v1 Announce Type: cross Abstract: Rubrics support the structured evaluation of language models. We propose a rubric for assessing expressed clinical reasoning in model responses, drawi
arXiv:2609.36488v1 Announce Type: new Abstract: Large language model (LLM) agents have demonstrated strong performance on complex web navigation tasks, yet they remain brittle in real-world settings w
arXiv:2509.20411v3 Announce Type: replace-cross Abstract: Machine learning-based cybersecurity systems are highly vulnerable to adversarial attacks, while Generative Adversarial Networks (GANs) act as
arXiv:2609.37941v1 Announce Type: new Abstract: This study provides a data-driven analysis of a novel dataset of single-cell Anion Exchange Membrane water electrolyzers (AEMWE), operated under constan
arXiv:2609.37236v1 Announce Type: new Abstract: An agent that uses tools typically responds to what the user explicitly asks, yet completing the task may require information the user never requested.
arXiv:2609.36628v1 Announce Type: new Abstract: Vision-Language Models (VLMs) can generate rich video captions, yet often misidentify which person performs an action or which limb is involved, particu
arXiv:2609.37905v1 Announce Type: cross Abstract: Click-Through Rate prediction, a core task in recommendation and advertising systems, relies on modeling interactions among sparse categorical feature
arXiv:2602.11678v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual understanding, yet they suffer from a critical limitation: structu
arXiv:2609.36505v1 Announce Type: new Abstract: Agentic reinforcement learning (ARL) with verifiable rewards improves the ability of large language models (LLMs) to tackle knowledge-intensive tasks by
arXiv:2609.36730v1 Announce Type: new Abstract: Agents increasingly build on code written by other agents, and they reimplement rather than reuse, growing the codebases later agents must work in. To m
arXiv:2609.36914v1 Announce Type: new Abstract: Post-training has been shown to significantly improve language models' performance on tasks with verifiable outcomes, including mathematical reasoning,
arXiv:2609.36218v1 Announce Type: cross Abstract: Large language models are increasingly evaluated in specialized domains such as law, medicine, software engineering, and cybersecurity, yet film remai
arXiv:2609.37216v1 Announce Type: cross Abstract: Large language models can generate plausible code-review comments, but such comments may contain technically incorrect claims that mislead developers.
arXiv:2609.36173v1 Announce Type: cross Abstract: Parallel speculative drafting generates multiple candidates in one backbone pass, but independent token selection can produce inconsistent continuatio
arXiv:2609.37923v1 Announce Type: new Abstract: Agents can learn from past executions, but enabling different agents to reuse and build on one another's experience remains challenging. We introduce Ep
arXiv:2609.36575v1 Announce Type: new Abstract: Visuomotor policies for humanoid loco-manipulation must generalize across object poses and lighting from only a handful of demonstrations. 3D Diffusion
arXiv:2609.37655v1 Announce Type: new Abstract: Advancing spatial intelligence in Multimodal Large Language Models (MLLMs) is bottlenecked by the scarcity of complex, scalable 3D question-answer (QA)
https://preview.redd.it/xs01ds930nsh1.png?width=4800&format=png&auto=webp&s=939762bcf3fbd93e137d4f97e927dda38aaf30fd Back in July I shared LokalBot here. It's a free, open-source Mac app that records
arXiv:2609.37488v1 Announce Type: cross Abstract: Frozen multimodal large language models (MLLMs) now solve standard referring expression comprehension with a single prompted call, yet on adversarial
arXiv:2609.36532v1 Announce Type: cross Abstract: In multiclass probabilistic prediction, Utility Calibration (UC), which focuses auditing on specified utilities, has recently received attention as a
arXiv:2609.37882v1 Announce Type: new Abstract: Every text classifier for an African language begins with a budgeting question: how many labelled examples are needed, and can labels from other African
I've been closely following the rise of the Strata inference engine and as someone with 28GB VRAM and 32GB RAM I'm itching to buy 32GB more RAM just to use Flash Next. But of course before I make such
arXiv:2609.37944v2 Announce Type: cross Abstract: A wide range of methods have been proposed, including physics-informed neural networks, which are powerful but do not guarantee identifiability of the
arXiv:2602.05385v2 Announce Type: replace Abstract: Text-to-SQL is a key natural language processing task that maps natural language questions to SQL queries, enabling intuitive interaction with web-b
arXiv:2609.38049v1 Announce Type: new Abstract: Generative models for function-valued data, such as time series and solutions of partial differential equations, must learn distributions over infinite-
arXiv:2601.11433v2 Announce Type: replace Abstract: Deep Differentiable Logic Gate Networks (LGNs) and Lookup Table Networks (LUTNs) are demonstrated to be suitable for the automatic classification of
arXiv:2606.21804v2 Announce Type: replace-cross Abstract: Maintainability is a core dimension of software engineering, shaping how code is written, reviewed, and developed over time. While coding agen
arXiv:2609.36115v1 Announce Type: new Abstract: Industry applications often demand low-latency classification, yet current large language model (LLM) approaches remain poorly suited for latency-critic
arXiv:2609.36518v1 Announce Type: cross Abstract: Robots must often continue a task after a target moves, the viewpoint shifts, or an obstacle appears, even though their earlier observations and commi