Online Experiential Learning for Language Models
arXiv:2603.16856v2 Announce Type: replace Abstract: The prevailing paradigm for improving large language models relies on offline training with human annotations or simulated environments, leaving the
Knowledge catalogue
arXiv:2603.16856v2 Announce Type: replace Abstract: The prevailing paradigm for improving large language models relies on offline training with human annotations or simulated environments, leaving the
arXiv:2606.28667v1 Announce Type: new Abstract: Sign languages are compositional systems where meaning arises by combining sublexical phonological parameters, such as handshape, location, and movement
arXiv:2606.28805v1 Announce Type: new Abstract: At competitive speeds and spins, a table tennis ball follows complex, counterintuitive trajectories that a robot must track and precisely counter within
arXiv:2606.29346v1 Announce Type: new Abstract: Post-hoc explanation methods are routinely used to interpret scientific machine learning models, with the deliverable understood to be insight into the
arXiv:2606.29520v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used as assistants across the software development lifecycle, yet their ability to reason about software
arXiv:2606.29579v1 Announce Type: cross Abstract: Spatial reasoning remains a persistent challenge for many vision language models (VLMs), and improving it typically requires fine-tuning with substant
Sonnet 5 is here! This is going to support better long-running agents. Previous Sonnet models were unreliable, so it's great to see the improved version that can complete agentic tasks more reliably.
Super excited about open-source router systems and routing models like @vllm_project semantic router: https://huggingface.co/llm-semantic-router The future is multi-models and you'll want to customize
arXiv:2606.29700v1 Announce Type: new Abstract: Planning often requires symbolic specifications that are both executable and verifiable. For large language models deployed in autonomous or decision-su
arXiv:2606.29241v1 Announce Type: new Abstract: Data-generating priors are a central component of tabular foundation models because they define the task distribution used during pretraining. However,
arXiv:2510.16732v3 Announce Type: replace Abstract: Embodied AI requires agents that perceive, act, and anticipate how actions reshape future world states. World models serve as internal simulators th
arXiv:2606.28049v1 Announce Type: new Abstract: In recent years, multimodal large language models (MLLMs) have shown strong potential for embodied intelligence, yet their ability to maintain geometric
arXiv:2606.27383v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as research assistants, yet it remains unclear whether they can calibrate research takeaways to the
arXiv:2606.27634v1 Announce Type: new Abstract: Small Language Models (SLMs) are increasingly being considered for deployment on edge devices such as laptops, enabling private, low-latency, and locall
Ben Jiang / South China Morning Post: DeepSeek details DSpark, a speculative decoding framework for its V4 models, saying it speeds up AI inference by up to 85% and was tested on Gemma and Qwen — Chin
arXiv:2510.00809v3 Announce Type: replace Abstract: While Time Series Foundation Models (TSFMs) excel in zero-shot tasks, their behavior under continual fine tuning is poorly understood. We present th
arXiv:2606.27679v1 Announce Type: cross Abstract: Probe-based uncertainty estimation (UE) has emerged as a prominent approach to detect hallucinations in Large Language Models (LLMs) by learning uncer
arXiv:2606.27660v1 Announce Type: new Abstract: Vision-Language Models (VLMs) improve generalization and interpretability in autonomous driving but suffer from efficiency issues due to long visual tok
arXiv:2606.27444v1 Announce Type: new Abstract: Aerial 6DoF localization typically relies on precise GNSS signals or radiometrically rich 3D reconstructions, limiting scalability and on-board deployme
This is smart from Cline. They just launched ClinePass, which makes it easy to access the latest open-weight models like GLM 5.2, Kimi k2.7-code, Mimo 2.5, Deepseek v4 pro, Minimax M3, and more. Alway
arXiv:2606.26541v1 Announce Type: new Abstract: Data from affected populations are crucial for informing humanitarian response, but their value depends on timely and consistent interpretation of nuanc
arXiv:2606.27371v1 Announce Type: new Abstract: State-of-the-art flow models generate stunning images from text or image prompts. However, they suffer from diversity collapse when generating multiple
arXiv:2606.26196v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have recently made remarkable progress in unifying vision-language understanding and reasoning, especially fo
arXiv:2606.26880v1 Announce Type: new Abstract: Language-model representations provide structured, high-dimensional annotations of naturalistic language stimuli and can serve as informative neural pre
arXiv:2606.27047v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong performance across a wide range of tasks, but ensuring their reliability in highly technical dom
arXiv:2606.26161v1 Announce Type: new Abstract: Linear directions in activation space have been identified for both refusal and persona traits in instruction-tuned chat models, but the two have been s
arXiv:2606.26108v1 Announce Type: new Abstract: Larger language models consistently outperform smaller ones on reasoning benchmarks, yet the reasoning differences underlying this gap remain underexplo
arXiv:2603.02156v2 Announce Type: replace-cross Abstract: Emerging 6G visions, reflected in ongoing standardization efforts within 3GPP, IETF, ETSI, ITU-T, and the O-RAN Alliance, increasingly charact
arXiv:2606.25442v1 Announce Type: new Abstract: Safety alignment of large language models (LLMs) typically depends on high-quality supervision data, such as safe demonstrations or preference pairs. Ho
The underrated part of this announcement is that Fireworks has been quietly great behind the scenes helping us eval and serve these models Big kudos to the Fireworks team! Kimi K2.7 Code and GLM 5.2 a
arXiv:2606.25160v1 Announce Type: cross Abstract: The rapid rise of Vision-Language Models (VLMs) in egocentric visual understanding has made low-latency inference in human-robot collaborative (HRC) t
arXiv:2606.24945v1 Announce Type: new Abstract: We ask a representation-learning question about physical world models: when does a conservation law remain certifiable after a model learns a latent rep
arXiv:2606.24829v1 Announce Type: new Abstract: Camera-prompted text-to-video (T2V) models are increasingly used to synthesize virtual camera captures, such as orbiting objects or moving through stati
arXiv:2606.23744v1 Announce Type: cross Abstract: Deep learning has become an important tool in computational pathology, enabling automated analysis of histopathological images. While convolutional ne
arXiv:2606.24102v1 Announce Type: new Abstract: Most electronic health record (EHR) foundation models encode clinical events as discrete event tokens from a fixed vocabulary and therefore cannot direc
arXiv:2606.24488v1 Announce Type: cross Abstract: Learning causal models from fragmented biomedical data is challenging because clinical, molecular, and imaging variables are often incomplete or not j
arXiv:2606.24187v1 Announce Type: new Abstract: Long video understanding remains a daunting challenge for Multimodal Large Language Models (MLLMs) due to the excessive computation and memory footprint
arXiv:2606.22999v1 Announce Type: new Abstract: The rapid deployment of Vision-Language Models (VLMs) in dynamic environments necessitates the ability to learn continuously without forgetting. However
arXiv:2606.21496v1 Announce Type: cross Abstract: Deploying generalist robotic agents in the real world requires transferable skills. Specifically, a policy trained to clone a behavior from object-spe
arXiv:2510.10854v3 Announce Type: replace Abstract: Diffusion models have demonstrated remarkable performance in generating high-dimensional samples across domains such as vision, language, and the sc
arXiv:2603.08206v5 Announce Type: replace Abstract: Modern tabular foundation models such as TabPFN and TabICL naturally produce full predictive distributions, while the benchmarks used to evaluate th
arXiv:2606.22473v1 Announce Type: cross Abstract: Speech language models (SLMs) have been extensively studied, with the common paradigm incorporating text data and pre-trained text LMs. A leading appr
arXiv:2606.23296v1 Announce Type: new Abstract: Developing generalist embodied agents requires interactive environments providing visually realistic feedback and accurate action-conditioned dynamics.
arXiv:2603.14343v2 Announce Type: replace Abstract: Large Audio-Language Models (LALMs) have shown strong performance in speech understanding, making speech a natural interface for accessing factual i
arXiv:2606.21194v1 Announce Type: new Abstract: Medical Vision-Language Models (Med-VLMs) achieve strong expert-level performance, yet their ability to generate patient-accessible descriptions remains
arXiv:2606.21372v1 Announce Type: cross Abstract: Vision-language-action (VLA) models rely on discrete action tokenizers to bridge continuous robot control and autoregressive sequence modeling, yet ex
arXiv:2606.22249v1 Announce Type: new Abstract: In recent years, weight quantization that encodes the learnable parameters of large language models in an n-bit format has garnered significant attentio
arXiv:2606.20754v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown strong performance in robotic manipulation, but reliable uncertainty quantification remains challenging,
rumors of new models being delayed 🚨 SCOOP(s): - GPT-5.6 has been delayed and will no longer release this week. New target is ~mid-July. - DeepMind are not satisfied with the current state of 3.5 Pro
arXiv:2606.23444v1 Announce Type: cross Abstract: Accurate dynamics models are critical for informed decision-making in robotic systems, particularly for agile aerial vehicles operating under uncertai
arXiv:2602.10217v2 Announce Type: replace Abstract: We study machine unlearning in large generative models by framing the task as density ratio estimation to a target distribution rather than supervis
Sarah Basford Canales / The Guardian: In a rare joint statement, Five Eyes leaders warn AI models capable of taking down governments and businesses are mere months away, urging leaders to “act now” —
arXiv:2606.11568v1 Announce Type: new Abstract: Despite recent advances, Vision Language Models (VLMs) still struggle to grasp the dynamics of the world. We note that the ability to reason about a 4D
arXiv:2606.11204v1 Announce Type: new Abstract: Accurate extraction of structured information from Safety Data Sheets (SDS) remains challenging in industrial safety due to heterogeneous document forma
arXiv:2601.14031v2 Announce Type: replace-cross Abstract: Forecasting intermittent time series, which contain zeros, is a crucial challenge in supply chains as inventory policies require probabilistic
arXiv:2606.11220v1 Announce Type: new Abstract: Forecasting human life outcomes is important to gain insights into how individuals attain long and healthy lives. Conventional statistical approaches yi
arXiv:2606.11260v1 Announce Type: cross Abstract: Humans process rich auditory environments through tightly integrated cognitive capabilities such as audio perception, audio reasoning, and memory. Des
Maxwell Zeff / Wired: Anthropic backtracks on a policy limiting Claude Fable 5's ability to develop other AI models, after significant backlash from the AI research community — The company changed cou
arXiv:2606.09954v1 Announce Type: cross Abstract: Large models for time-series forecasting have been emerged as a promising paradigm for training models on heterogeneous collections of signals. These
arXiv:2606.10819v1 Announce Type: cross Abstract: RS-MLLMs enable natural-language understanding and spatial reasoning over earth observation imagery. However, existing models support only a narrow ra