Knowledge catalogue
arXiv:2610.18057v1 Announce Type: new Abstract: Transformers can implement reinforcement-learning algorithms in context, yet how off-policy control emerges within Transformers remains poorly understoo
arXiv:2610.18478v1 Announce Type: new Abstract: Large vision-language models (LVLMs) have shown strong potential for embodied vision-language navigation (VLN), yet their performance degrades on long-h
I built a desktop app harness that keeps local meeting notes and can use them to autocomplete my typing as well as complement my dictation with additional context via reading my screen or using the pr
Learn to build custom harnesses, folks! Here is an impressive paper showing the impact of a good custom harness on long-context work. GLM-5.3-Flash goes from 4.4% to 61.1% exact match on OfficeQA Pro
(1/7) I'd like to provide some additional context for the remarks that can be found in this interview. (2/7) My discomfort with the attention being paid to existential risk---and with the ongoing domi
arXiv:2610.12571v1 Announce Type: new Abstract: Most systems trained by equilibrium propagation or coupled learning are in the same class as multi-layer perceptrons: while they may be universal functi
arXiv:2610.13755v1 Announce Type: cross Abstract: Training long-horizon language model agents requires assigning credit to intermediate decisions from sparse terminal feedback. Within a finite group o
DISCLAIMER: the post and the model card was made with the assist of AI. Hiya, I’m releasing Recursive BitNet N-Gram 102M, a small experiment combining ternary weights, shared transformer layers, and h
arXiv:2610.10590v1 Announce Type: new Abstract: Tool-using agents repeatedly carry observations whose useful content can be much smaller than their original payload. We study agent-controlled forgetti
HauhauCS ships their uncensored Qwen3.8-27B as GGUF only. NInfer, a C++/CUDA wanted its own format. Now the same model that ran at 91.6 tok/s / 131K under llama.cpp does: 262K context (the model's ful
arXiv:2610.12104v1 Announce Type: cross Abstract: Building a capable video editor remains significantly harder than a video generator: editing requires (source, instruction, edited) triplets that are
arXiv:2610.10335v1 Announce Type: new Abstract: Visual in-context learning (ICL), well suited to label-scarce medical imaging, uses support image-label pairs to demonstrate input-output mappings, whil
arXiv:2610.08115v1 Announce Type: cross Abstract: Hamilton-Jacobi reachability constructs safety certificates for specified dynamics and safety constraints, tying each certificate to the deployment co
Context, OpenAI cracked or made important progress in hundreds of big problems today: https://openai.com/index/sharing-ai-progress-in-mathematics/ (And I am seeing rapid increases in the ability of AI
arXiv:2610.08300v1 Announce Type: new Abstract: Long-term conversational memory is becoming an integral component of modern LLM systems. Proposed architectures group records by topics and events, cons
Off-the-shelf AI assistants forget you between conversations. This post shows how to build a personal assistant that accumulates context using OpenClaw on Amazon Bedrock AgentCore runtime, with AgentC
arXiv:2607.09082v2 Announce Type: replace Abstract: Training-free in-context segmentation enables new object categories to be introduced at inference time from a single annotated reference image, elim
arXiv:2610.02368v1 Announce Type: new Abstract: Long-horizon compositional manipulation has become increasingly important for real-world robot deployment, where a single task involves multiple coordin
arXiv:2610.01076v1 Announce Type: new Abstract: Structured electronic health records (EHRs) contain a patient's clinical trajectory as a sequence of clinical codes. Answering clinical questions from s
arXiv:2610.01569v1 Announce Type: cross Abstract: Unmanned aerial vehicle (UAV) swarms increasingly rely on language-model agents to provide adaptive mission-level reasoning in uncertain environments.
.@AnthropicAI’s Thariq on what Claude Mods unlock: conversation context, subagents, structured output, and control over the UI. “It has a bunch of things in the scope … like how many turns is in this
arXiv:2601.09717v2 Announce Type: replace-cross Abstract: Online medical consultations contain sensitive health information whose privacy implications depend not only on the entities mentioned but als
arXiv:2609.39437v1 Announce Type: new Abstract: Large language models (LLMs) encode substantial latent geographic knowledge, yet they reason poorly over space and are unreliable when queried from coor
pplx-decider-v1-27b is fine-tuned from Qwen3.8-27B with a 250k context window. View the weights on Hugging Face: https://huggingface.co/perplexity-ai/pplx-decider-v1-27b Get started with the Perplexit
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:2609.38099v1 Announce Type: cross Abstract: Turning decoder-only large language models (LLMs) into strong dense retrievers typically requires some form of retriever training. In this paper, we a
arXiv:2609.38173v1 Announce Type: new Abstract: We study robotic in-context learning (ICL), an emerging paradigm that enables robots to infer and execute tasks from visual demonstrations. Despite its
arXiv:2609.37057v1 Announce Type: new Abstract: Achieving strong performance with graph neural networks (GNNs) typically requires training and hyperparameter tuning for each dataset, incurring repeate
arXiv:2609.37311v1 Announce Type: new Abstract: Recent Recommendation Agents (RecAgents) offer a promising alternative by shifting recommendation to an active, user-side paradigm, where generative age
arXiv:2609.36062v1 Announce Type: new Abstract: Long-context sequence models face a fundamental tradeoff: softmax attention uses flexible token-level interactions at quadratic cost, whereas linear att
arXiv:2609.34847v1 Announce Type: new Abstract: Time series prediction is a common application of reservoir computing. When the training and testing time series data contains multiple dynamical regime
arXiv:2609.34893v1 Announce Type: new Abstract: Learning-based manipulation policies relying on RGB cameras often suffer from degraded observations under extreme exposure. Event cameras mitigate this
arXiv:2609.34555v1 Announce Type: new Abstract: Long-context LLM serving is increasingly bottlenecked by decode, where large KV caches limit batch size and underutilize GPUs. Sparse KV cache offloadin
arXiv:2609.34261v1 Announce Type: cross Abstract: General-purpose vision-language models offer a promising way to zero-shot robot control: gptastra{} excels at open-ended and language- or image-condit
arXiv:2609.34044v1 Announce Type: new Abstract: Reasoning vision-language models (VLMs) process images and videos as long sequences of visual tokens, making inference expensive. Training-free token pr
arXiv:2609.32546v1 Announce Type: new Abstract: Large language models can generate several records within one autoregressive completion, making earlier answers available as context for later records.
arXiv:2609.34707v1 Announce Type: new Abstract: Object navigation requires an embodied agent to find an object in an unseen environment under partial observability and a limited motion budget. Existin
arXiv:2609.35055v1 Announce Type: new Abstract: Long contexts are central to modern transformer systems, but most expressivity results choose a different network for each fixed sequence length. We stu
arXiv:2609.31354v1 Announce Type: new Abstract: Contemporary large language model (LLM) chat systems treat conversation history as an immutable sequence of turns that defines the model's working conte
arXiv:2609.29447v1 Announce Type: cross Abstract: Smart maritime infrastructures provide continuous access to heterogeneous sensing streams, enabling repeated experimentation, digital-twin development
arXiv:2609.29118v1 Announce Type: new Abstract: LiDAR place recognition is a key front end for loop closure and global relocalization, yet indoor retrieval remains difficult when attitude or sensor mo
arXiv:2609.29875v1 Announce Type: new Abstract: Long horizon language model agents continually accumulate reasoning history, increasing context length and inference cost even after earlier decisions h
arXiv:2601.05353v3 Announce Type: replace Abstract: Accurate blood glucose forecasting using continuous glucose monitoring (CGM) data can support the early prediction of dysglycemic risk. However, cur
arXiv:2609.27173v1 Announce Type: new Abstract: Solving complex tasks in domains such as science, medicine, law, and finance often requires assembling interdependent information scattered across vast,
This is a fantastic blog post from our research team on the importance of calibrated confidence scores. Here it's in the context of document extraction, it's also extremely important for more general
arXiv:2609.26300v1 Announce Type: new Abstract: Despite their strong performance, large language models (LLMs) are bottlenecked by KV cache memory traffic during long-context inference. Sparse attenti
arXiv:2609.25836v1 Announce Type: new Abstract: Multi-task optimization (MTO) addresses a set of optimization tasks simultaneously, often suffering from inaccurate inter-task relationship estimation u
arXiv:2609.25845v1 Announce Type: cross Abstract: Many vision applications ask several independent, forced-choice questions about the same image. Visual Jev encodes the image and public context once,
arXiv:2609.22939v1 Announce Type: cross Abstract: Long-context models read a novel the way a person reads a printout: one token after another, in narrative order, with the whole history competing for
In our evaluations, we see that GPT-6 Sol reads about 17% less context than GPT-5.6 Sol to reach the same score, and rarely leaves a repo with failing tests after its last edit. GPT-6 Luna’s biggest g
arXiv:2603.28431v4 Announce Type: replace Abstract: Although 3D Gaussian Splatting (3DGS) enables high-fidelity real-time rendering, its prohibitive storage overhead severely hinders practical deploym
arXiv:2609.24238v1 Announce Type: new Abstract: We reproduce and stress-test the work of Yu et al. (2023), who characterize how language models (LMs) arbitrate between memorized knowledge and contradi
arXiv:2603.08269v2 Announce Type: replace Abstract: In-context imitation learning allows robots to acquire skills from demonstrations, yet one-shot trajectory generation remains fragile under environm
arXiv:2609.22943v1 Announce Type: new Abstract: Efficient large language model (LLM) instruction tuning requires selecting response supervision with supporting prompt context. Existing methods typical
arXiv:2609.22259v1 Announce Type: new Abstract: Context layers, curated documentation that an analytics agent fetches at query time, produce large accuracy gains on text-to-SQL benchmarks. A with/with
arXiv:2609.21172v1 Announce Type: new Abstract: Large language models (LLMs) are moving onto mobile devices for increasingly diverse workloads over text, images, video, and audio. These applications o
Astra for Law: Frontier intelligence built for your practice. A new offering powered by GPT-6 Astra with tools, settings, and context to support the expertise and judgment of lawyers and legal technol
Romeo Lupascu has criticized the prevailing AI agency framework, which relies on repeatedly looping an LLM core with identical context. He calls this strategy “deeply flawed” and argues that it should
arXiv:2609.18856v1 Announce Type: cross Abstract: Compact acoustic models face a challenging quality-capacity trade-off. We investigate two factors in this regime: encoder context and Mel-spectrogram
arXiv:2609.17888v1 Announce Type: cross Abstract: We study the problem of demonstration selection, which involves selecting a subset of examples for prepending to a query to a language model. This pro