Knowledge catalogue
arXiv:2610.00538v1 Announce Type: cross Abstract: A real-time auditory scene analyzer (ASA) aims to carry out the tasks of locating, separating and classifying the sound sources present in a given aco
https://www.percepta.ai/blog/can-llms-grow-their-own-capabilities https://www.percepta.ai/blog/spotlight-memory 'Our new architecture, Spotlight, replaces attention with a memory that escapes this tra
arXiv:2610.00820v1 Announce Type: cross Abstract: General-purpose models can adapt to many tasks from context, while specialised models can execute individual functions with less capacity. Yet obtaini
arXiv:2610.01497v1 Announce Type: new Abstract: Molecular tumor boards integrate genomic findings, clinical context, and therapeutic evidence to support precision oncology. As AI enters this workflow,
arXiv:2610.00451v1 Announce Type: cross Abstract: Human motion, environmental contacts, and interaction forces are governed by common physical laws, yet existing approaches typically separate visual p
arXiv:2610.01589v1 Announce Type: new Abstract: Pretrained 3D encoders are typically developed on globally reconstructed scenes expressed in a consistent world coordinate frame, whereas embodied syste
I've been using my free time during weeknights and weekends for the last 11 months working on and refining a small domain-specific language model. It specializes on information about World War II. The
arXiv:2610.00767v1 Announce Type: cross Abstract: Pre-training interventions are critical to alignment research, since beliefs formed during pre-training shape how a model generalizes from later train
arXiv:2610.00314v1 Announce Type: new Abstract: Research agents explain planned experiments. We measure predictive credit with paired forecasts sharing an intervention, forecaster, and outcome while v
arXiv:2610.00710v1 Announce Type: new Abstract: As large language model (LLM) agents become widely adopted, they are increasingly deployed for tasks that require persistent monitoring or recurring act
arXiv:2610.01908v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves vision-language benchmark scores even without visual information during training. With im
arXiv:2610.00084v1 Announce Type: new Abstract: Detailed profession-specific system prompts raise token use and estimated cost per response without a consistent accuracy gain. We evaluate Scientific A
arXiv:2610.01278v1 Announce Type: new Abstract: Alzheimer's disease (AD) diagnosis requires sequential evidence acquisition under heterogeneous test costs and patient burden. Fixed-modality predictors
arXiv:2610.00493v1 Announce Type: new Abstract: Mixture-of-LoRA-experts methods raise the capacity of low-rank adaptation by routing each token to a few low-rank experts. Nearly all of them tie one in
Sharing some notes from OpenAI DevDay in parts. The first part matters, since it's on everyone's mind. How do you optimize for cost and performance? If you are building agentic applications today, the
arXiv:2610.00838v1 Announce Type: cross Abstract: Agentic reinforcement learning (RL) trains a large language model (LLM) to act over long, multi-step interactions. However, a single localized error c
arXiv:2610.01283v1 Announce Type: new Abstract: Reliable shelf monitoring is an important capability for retail automation, yet existing out-of-stock detection methods mainly operate in image space an
arXiv:2610.01799v1 Announce Type: new Abstract: Skill evolution offers a promising way to improve large language model agents without updating their parameters, but its use in formal theorem proving r
arXiv:2610.01177v1 Announce Type: cross Abstract: This work presents Diffusion Layer Integrated Gradients (DLIG), a token attribution method for diffusion language models (DLMs) that extends Integrate
arXiv:2610.00054v1 Announce Type: cross Abstract: Reading an LLM judge's verdict from the logits of its first generated token is cheap, requires no generation, and is exactly what constrained decoding
The same model, with the same weights, scores 62% in one agent harness and 33% in another. @adithya_s_k and the @huggingface team just released the ultimate guide to multi-harness RL, and it's one of
This is beautiful work @huggingface! 🤗 The same model, with the same weights, scores 62% in one agent harness and 33% in another. @adithya_s_k and the @huggingface team just released the ultimate guid
arXiv:2610.01887v1 Announce Type: cross Abstract: Dynamic resource assignment, the real-time allocation of task streams to heterogeneous processing nodes, is the backbone of modern computing infrastru
arXiv:2610.01323v1 Announce Type: new Abstract: Safety-aligned large language models (LLMs) often refuse a harmful request but comply once the same goal is spread over several turns. Preference object
arXiv:2610.00814v1 Announce Type: cross Abstract: Synthetic data are increasingly used to scale LLM training, yet more synthetic data do not necessarily produce better models. Useful synthetic data mu
arXiv:2610.00341v1 Announce Type: cross Abstract: As Large Multimodal Models (LMMs) transition toward natively unified architectures, evaluating their safety in synergistic harmful image-text generati
arXiv:2610.00827v1 Announce Type: cross Abstract: Large language models carry an internal notion of uncertainty in their sampling distribution, i.e., the probabilities they place on generating one ans
arXiv:2610.00083v1 Announce Type: new Abstract: Humans express uncertainty verbally via markers (e.g., 'possible,' 'likely'), yet most LLM uncertainty quantification (UQ) relies on costing likelihood-
arXiv:2610.00960v1 Announce Type: new Abstract: A video benchmark should reward the capability it claims to measure, yet models can exploit answer options, question text, or partial visual evidence. W
arXiv:2610.00666v1 Announce Type: cross Abstract: Qualitative comparison figures are central evidence in computer vision papers, and vision-language models (VLMs) are increasingly used to judge them.
arXiv:2610.01627v1 Announce Type: cross Abstract: Difficulty is one of the most fundamental properties of a question: it determines whether the question can meaningfully discriminate between models of
arXiv:2610.00654v1 Announce Type: new Abstract: Personalization has long relied on customer data to infer what an individual is likely to value. We call this customer evidence: the customer's historic
arXiv:2610.00163v1 Announce Type: cross Abstract: Complex problem solving depends on acting effectively and understanding how a system works. AI advice may support these outcomes unequally. Two prereg
arXiv:2602.14929v2 Announce Type: replace Abstract: Aligning ground-level imagery with geo-registered satellite maps is crucial for mapping, navigation, and situational awareness, yet remains challeng
arXiv:2609.39702v1 Announce Type: new Abstract: Adapting a language model to a specialized corpus means choosing which instruction-tuning tasks to train on under a fixed budget, and testing one choice
Matthew Green / A Few Thoughts on Cryptographic Engineering: A look at two opposing perspectives on AI agent sandboxing: infosec says labs need better containment while AI alignment says sandboxes can
arXiv:2511.00763v3 Announce Type: replace Abstract: We investigate the performance of large language models (LLMs) on repetitive deterministic prediction tasks and study how the sequence accuracy rate
arXiv:2609.39402v1 Announce Type: new Abstract: Value-model-free RLVR methods such as GRPO assign uniform advantages to all tokens in a rollout, ignoring that tokens contribute unequally. Recent metho
arXiv:2609.38607v1 Announce Type: cross Abstract: Shadow removal looks nearly solved on established benchmarks, yet remains brittle in the real world. Models have advanced; the paired training data th
arXiv:2609.40111v1 Announce Type: new Abstract: An unsuccessful LLM agent rollout contains more information than its final reward: the observations available to the agent, the actions it chose, and th
arXiv:2609.38296v1 Announce Type: new Abstract: Large language models (LLMs) can influence people's beliefs, yet little is known about whether and how they can manipulate each other. To investigate th
arXiv:2609.39964v1 Announce Type: new Abstract: Multi-modal integrated sensing and communication (ISAC) enables environmental perception and reliable connectivity for intelligent wireless networks. Da
arXiv:2609.39714v1 Announce Type: new Abstract: Top researchers have good intuition, but do language models have as good intuition about model training as top AI researchers? To measure model intuitio
arXiv:2609.36073v1 Announce Type: cross Abstract: The rapid proliferation of large language models (LLMs) in the context of education has introduced significant challenges in enforcement of academic i
arXiv:2609.39207v1 Announce Type: new Abstract: We present ASENA, an embodied agent system that connects general-purpose coding agents to robot sensing, computation, supervised execution, and persiste
arXiv:2609.40097v1 Announce Type: new Abstract: Existing auto-research benchmarks often entangle multiple sources of improvement, including training frameworks, hyperparameters, compute budgets, and d
arXiv:2609.38806v1 Announce Type: cross Abstract: Next-token prediction has driven remarkable progress in large language models, yet a growing body of evidence suggests that they can struggle on probl
arXiv:2609.39394v1 Announce Type: new Abstract: Large language models often solve independent problems in the same conversation. Can computation from earlier problems help them solve new ones? To answ
arXiv:2609.39665v1 Announce Type: new Abstract: Embodied agents must determine where to act, anticipate the resulting scene changes, and interpret observed outcomes to guide subsequent actions. This r
arXiv:2511.22254v5 Announce Type: replace Abstract: Self-evolving agents improve their performance on long-horizon tasks by learning from their own interactions with an environment. A common approach
Code review has to change for coding agents. Why? For me, it’s about scaling coding reviews while ensuring quality. If you give a coding agent one task, it can return several pull requests across diff
arXiv:2609.39081v1 Announce Type: cross Abstract: We spent five weeks using an LLM coding agent on open problems in coding theory: finding large sets of four-letter words, such as DNA barcodes, that s
arXiv:2609.40048v1 Announce Type: new Abstract: Ultra-long video temporal grounding requires balancing long-range evidence search with fine-grained event understanding under a limited visual budget, y
arXiv:2609.40253v1 Announce Type: cross Abstract: Online training enables computer-use agents (CUAs) to improve through interaction with executable environments. However, existing methods primarily re
arXiv:2609.38222v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) can ground large language models in external evidence, but retrieved context does not guarantee that generated clai
arXiv:2609.39955v1 Announce Type: new Abstract: Single-step retrosynthesis models are commonly evaluated by their ability to recover recorded reactions. In practice, chemists may need to choose among
arXiv:2609.39924v1 Announce Type: cross Abstract: Vision-language models face a fundamental scaling bottleneck: the number of visual tokens grows with both temporal duration and spatial resolution, ma
Hello everyone. I've recently ran some experiments comparing DDR4/PCIe4 and DDR5/PCIe5 for AI workstations on a pre-training run, and would like to hear yours thoughts. First of all, and as a summary
arXiv:2609.38777v1 Announce Type: new Abstract: A central goal of vision-language model (VLM) distillation is to transfer both the teacher's language capabilities and its visual understanding. However
arXiv:2609.39710v1 Announce Type: new Abstract: Scientific abstracts mix contributions with background, motivation, and meta-language, so tools that read them as-is cannot separate what a field produc