b11339
llama : clamp kpool re-pool bound to existing pools (#29805) tests : simplify function signature llama : clamp kpool re-pool bound to existing pools The n_tokens/kpool + n_seqs_unq bound on n_new_g ov
Knowledge catalogue
llama : clamp kpool re-pool bound to existing pools (#29805) tests : simplify function signature llama : clamp kpool re-pool bound to existing pools The n_tokens/kpool + n_seqs_unq bound on n_new_g ov
ggml : add alloc_buffer_n to buffer type interface (#23671) ggml : add alloc_buffer_n to buffer type interface Add alloc_buffer_n method to ggml_backend_buffer_type_i interface, with a public API ggml
arXiv:2607.16731v2 Announce Type: replace Abstract: Marine biogeochemical forecasting is increasingly important for managing marine ecosystems and the carbon cycle, yet global, seasonal forecast produ
arXiv:2610.02070v1 Announce Type: new Abstract: Memory-augmented large language models must decide which memories to retain, and recent systems do so by estimating each memory's effect on task perform
arXiv:2610.00047v1 Announce Type: new Abstract: Diversity collapse in parallel chain-of-thought has motivated inference-time interventions built on a natural design: when a process reward model (PRM)
arXiv:2606.15396v2 Announce Type: replace-cross Abstract: Malicious content generated from large language models (LLMs) could pose severe safety risks and ethical concerns. While existing LLM safety g
arXiv:2410.22046v4 Announce Type: replace-cross Abstract: Chord progressions encapsulate important information about music, pertaining to its structure and conveyed emotions. They serve as the backbon
arXiv:2610.01710v1 Announce Type: new Abstract: Visual grounding localizes an object described by language with a bounding box. Most multimodal grounding models compress target identification, spatial
arXiv:2610.00234v1 Announce Type: new Abstract: 'Train a model on the same problems written under two incompatible conventions, both correct, and ask what the ordering of that data writes into the par
arXiv:2610.00232v1 Announce Type: new Abstract: Fixed-size recurrent memory limits storage growth during inference, but successful recall depends on the task and training. We study a small DeltaNet va
arXiv:2610.01921v1 Announce Type: cross Abstract: Cross-lingual contrastive learning has been a core component of multilingual encoder training, but the ability to explicitly align representations is
arXiv:2610.01513v1 Announce Type: new Abstract: Long-term dependencies remain a major challenge for sequential decision-making in the field of AI: RNNs suffer from vanishing gradients and the limited
arXiv:2610.01256v1 Announce Type: new Abstract: Errors in LLM agent executions and their visible consequences can be separated by many steps, making decisive-error localization a matter of understandi
arXiv:2610.01168v1 Announce Type: cross Abstract: Time Series Anomaly Detection has received increasing attention, driven by the growing availability of complex time series data. This surge has led to
arXiv:2610.01847v1 Announce Type: cross Abstract: Model specifications define how large language models (LLMs) should behave, guiding alignment training, inference-time behavior, and evaluation. Yet t
arXiv:2610.00982v1 Announce Type: cross Abstract: Vision-language-action (VLA) models struggle on history-dependent manipulation tasks, where the current observation alone does not determine the actio
arXiv:2610.01746v1 Announce Type: cross Abstract: Autonomous driving systems have become a central focus of intelligent transportation research, with End-to-End Learning and Modular Architectures offe
arXiv:2610.00661v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) generate text by denoising a sequence or successive blocks, allowing several tokens to be revealed in parallel
arXiv:2610.00922v1 Announce Type: new Abstract: Gaze estimation under natural head-eye motion underpins applications from driver monitoring to human-computer interaction. Single-frame methods predict
arXiv:2603.08961v2 Announce Type: replace Abstract: Maintaining balance under external hand forces is critical for humanoid bimanual manipulation, where interaction forces propagate through the kinema
arXiv:2610.01967v1 Announce Type: new Abstract: As large language models (LLMs) keep growing in size and complexity, their training frameworks evolve at a rapid pace as well. Therefore, continuous int
arXiv:2610.01637v1 Announce Type: new Abstract: In recent decades, artificial intelligence has made significant progress in understanding and interacting with images. One of the important applications
arXiv:2607.16956v2 Announce Type: replace Abstract: Social navigation requires the robot to reason and respond in complex real-world environments. While recent works attempt to incorporate human-level
arXiv:2604.01997v2 Announce Type: replace Abstract: Gait analysis provides an objective characterization of locomotor function and is widely used to support diagnosis and rehabilitation monitoring acr
arXiv:2610.02036v1 Announce Type: new Abstract: AI agents can each make locally valid decisions yet jointly produce an invalid result. We call this the global coherence problem: a failure of shared st
arXiv:2610.00010v1 Announce Type: new Abstract: Long-horizon language agents increasingly rely on external memory as a frozen world model, yet current memory systems are usually judged only by task su
arXiv:2610.02193v1 Announce Type: cross Abstract: Discrete diffusion language models offer a compelling alternative to autoregressive generation for tasks demanding bidirectional reasoning and global
arXiv:2610.02186v1 Announce Type: cross Abstract: Molecular learning models are strongly shaped by their underlying representations. Yet standard sequential and graph formalisms struggle to explicitly
arXiv:2610.00004v1 Announce Type: new Abstract: Adam is the standard optimizer in deep learning, yet its geometric relationship to natural gradient descent (NGD) contains unresolved questions. We stud
arXiv:2610.00753v1 Announce Type: cross Abstract: End-to-end backpropagation has been the dominant mode of training in deep learning, allowing for the coordination of parameter updates across layers o
arXiv:2610.00355v1 Announce Type: new Abstract: Efficient indoor LiDAR perception is challenging because mobile robots must understand cluttered three-dimensional environments under strict latency and
arXiv:2610.02196v1 Announce Type: cross Abstract: We study test-time evolution for humanoid loco-manipulation: solving tasks that a controller was never trained for by repurposing its existing skills,
It is here now ! Enjoy our 4B model 🐸 https://huggingface.co/microsoft/FrogNano-4B-2609 4B parameters. ZERO distillation. 61.5% on SWE-bench Verified 🤯 Meet FrogNano 🐸: Qwen3.5-4B post-trained purely
arXiv:2610.00437v1 Announce Type: new Abstract: LLM agents generate intermediate reasoning and actions token by token, making extended interactions slow and computationally expensive. Jev-style models
arXiv:2610.01064v1 Announce Type: cross Abstract: Retrieving the right tables is a prerequisite for Text-to-SQL over realistic databases. Dense table retrievers rank schema elements independently, but
arXiv:2610.01172v1 Announce Type: new Abstract: We study learning rate (LR) scaling for hybrid architectures combining Transformer and State-Space Model (SSM) blocks, a class adopted by several recent
arXiv:2610.01236v1 Announce Type: new Abstract: Collaboration between a small language model (SLM) and a large language model (LLM) offers an opportunity to combine the efficiency of smaller models wi
arXiv:2610.00771v1 Announce Type: new Abstract: A central puzzle in transfer learning is why pre-training on one task can accelerate training or improve performance on another task, and what mechanism
arXiv:2610.01199v1 Announce Type: new Abstract: We consider low-budget active learning, which consists of selecting a limited number of points, the coreset, such that a model can be trained to high ac
arXiv:2610.01905v1 Announce Type: new Abstract: Online vectorized HD map construction is essential for scaling safe autonomous driving and requires accurate, real-time inference. Prior methods typical
arXiv:2610.01641v1 Announce Type: cross Abstract: Modern machine-learning models often contain strongly dependent or redundant features, making feature attribution difficult because shared predictive
arXiv:2610.00025v1 Announce Type: new Abstract: Agent harnesses increasingly want to run small language models (SLMs) on the microtasks around a frontier large language model (LLM) planner: auto-appro
arXiv:2610.00872v1 Announce Type: new Abstract: Long-term memory systems for large language models (LLMs) have gained popularity for extending reasoning capabilities across applications. Current memor
arXiv:2610.00604v1 Announce Type: cross Abstract: Vision-language-action policies often see only one or a few recent frames, which makes it difficult to evaluate how they use information that disappea
arXiv:2610.02038v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly combine reasoning, tool use, and action, but most evidence comes from episodic tasks with relatively imme
arXiv:2610.02001v1 Announce Type: new Abstract: Small open-weight models (2-9B) run on ordinary laptops, but under cloud-scale agent harnesses they rarely complete real tasks: tool prefill overflows t
arXiv:2610.00268v1 Announce Type: new Abstract: Multimodal graph learning faces a fundamental challenge: new classes may emerge after deployment, while models are trained with a fixed label space. Exi
arXiv:2610.00445v1 Announce Type: new Abstract: Pairwise guide--transcript scores do not enforce conservation of a finite guide-loaded RISC pool when they are interpreted independently as occupancies.
arXiv:2610.01762v1 Announce Type: new Abstract: Streaming video LLMs must retain evidence before its relevance to future tasks is known and respond when sufficient evidence becomes available. The chal
arXiv:2610.01067v1 Announce Type: new Abstract: Unmanned aerial vehicles (UAVs) searching for ground targets from a high altitude face a unique challenge, particularly when the target is already withi
arXiv:2607.15579v3 Announce Type: replace Abstract: Equipping humanoid robots with coherent and adaptable personas is crucial for fostering natural, engaging, and trustworthy human-robot interaction (
arXiv:2610.01601v1 Announce Type: cross Abstract: Decision models often score a variable-sized set of candidate actions encoded in a single sequence. This setting is increasingly relevant for System 1
arXiv:2610.00737v1 Announce Type: cross Abstract: Personalized image generation has remained narrowly focused on conditional synthesis from curated visual exemplars, rather than capturing who a user i
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:2610.01383v1 Announce Type: new Abstract: Analogical reasoning involves identifying and preserving relational structures across domains. However, existing approaches to AI-driven multimodal anal
Recursive Language Models: Claude Code, Agent Swarms, Big Research Bets, & the $40M AI Problem Solver https://www.latent.space/p/rlm MIT’s @a1zhang explains why Claude Code, Codex, and Pi are basicall
arXiv:2610.00348v1 Announce Type: cross Abstract: Backdoor attacks can be implanted in Large Language Models (LLMs) during training, causing unwanted behaviour when a trigger appears in the input. Exi
arXiv:2610.01249v1 Announce Type: new Abstract: Conventional reasoning protocols present a fixed, preselected task, so they cannot test whether an agent propagates relevant updates, preserves unaffect
arXiv:2610.00979v1 Announce Type: new Abstract: Training a single LLM agent jointly across diverse interactive environments has attracted increasing attention as a route to generalist agents. Existing
arXiv:2610.01496v1 Announce Type: new Abstract: Recent work on language-model adaptation has shown that single models can obtain informative training signals by evaluating their behavior in demonstrat