Suivi des pages liées
Entrer un nom de page pour voir les modifications faites récemment sur des pages liées vers ou depuis cette page (pour voir les membres d’une catégorie, entrez Catégorie:Nom de catégorie). Les modifications des pages de votre liste de suivi sont en gras.
Légende des abréviations :
- N
- Cette modification a créé une nouvelle page (voir aussi la liste des nouvelles pages)
- m
- Cette modification est mineure.
- b
- Cette modification a été effectuée par un robot.
- (±123)
- La taille de la page a changé de ce nombre d’octets.
2 juillet 2025
| N 15:41 | Ovis-U1 diffhist +399 Pitpitt discussion contributions (Page créée avec « ==en construction== == Définition == XXXXXXXXX == Français == ''' Ovis-U1''' == Anglais == '''Ovis-U1''' Ovis-U1, a 3-billion-parameter model, combines multimodal understanding, text-to-image generation, and image editing, achieving state-of-the-art performance in various benchmarks. == Source == [https://huggingface.co/papers/2506.23044 Source : huggingface] Catégorie:vocabulary ») | ||||
| N 15:40 | Matryoshka Multimodal Models diffhist +1 151 Pitpitt discussion contributions (Page créée avec « ==en construction== == Définition == XXXXXXXXX == Français == ''' XXXXXXXXX ''' == Anglais == '''Matryoshka Multimodal Models''' Matryoshka Multimodal Models learn to represent visual content as nested sets of visual tokens that capture information across multiple coarse-to-fine granularities. Our approach offers several unique benefits for LMMs: (1) One can explicitly control the visual granularity per test instance during inference, e.g. , adjusting the... ») | ||||
29 juin 2025
| 14:52 | Best-of-N Strategy diffhist +54 Arianne discussion contributions | ||||
27 juin 2025
| 16:56 | Conceptualization in Contexts diffhist +38 Arianne discussion contributions | ||||
| 16:56 | Conceptual Similarity Judgment diffhist +38 Arianne discussion contributions | ||||
| 16:55 | Conceptual Property Judgment diffhist +38 Arianne discussion contributions | ||||
26 juin 2025
|
|
N 12:48 | Best-of-N Strategy 2 modifications historique +2 330 [Arianne (2×)] | |||
|
|
12:48 (actu | diff) +1 035 Arianne discussion contributions | ||||
| N |
|
10:51 (actu | diff) +1 295 Arianne discussion contributions (Page créée avec « == en construction == == Définition == xxxxxxx == Français == ''' XXXXXX''' Voir aussi '''reward hacking problem''' == Compléments == '' à faire'' <!--The BoN strategy does not scale with the number of samples N due to the reward hacking problem. Particularly significant in scenarios where the AI model may not have a singularly deterministic output but can benefit from generating a spectrum of possibilities to increase the chance of achieving a higher qua... ») | |||
|
|
12:38 | Self-Consistency 2 modifications historique +797 [Arianne (2×)] | |||
|
|
12:38 (actu | diff) +494 Arianne discussion contributions | ||||
|
|
10:38 (actu | diff) +303 Arianne discussion contributions | ||||
| 12:27 | Multi-Token Projection diffhist +1 146 Arianne discussion contributions | ||||
| 12:10 | COPEN diffhist +135 Arianne discussion contributions | ||||
|
|
12:07 | Conceptualization in Contexts 2 modifications historique +1 035 [Arianne (2×)] | |||
|
|
12:07 (actu | diff) +1 Arianne discussion contributions | ||||
|
|
12:05 (actu | diff) +1 034 Arianne discussion contributions | ||||
| 12:00 | Conceptual Property Judgment diffhist +457 Arianne discussion contributions | ||||
| 11:36 | Conceptual Similarity Judgment diffhist +539 Arianne discussion contributions | ||||
| N 10:11 | AnimaX diffhist +396 Pitpitt discussion contributions (Page créée avec « ==en construction== == Définition == XXXXXXXXX == Français == ''' AnimaX''' == Anglais == '''AnimaX''' AnimaX creates multi-skeleton 3D animations by blending video diffusion model priors with skeleton-based control, using joint video-pose diffusion and shared positional encodings. == Source == [https://huggingface.co/papers/2506.19851 Source : huggingface] Catégorie:vocabulary ») | ||||
| N 10:09 | Drag-and-Drop LLMs diffhist +454 Pitpitt discussion contributions (Page créée avec « ==en construction== == Définition == XXXXXXXXX == Français == ''' XXXXXXXXX ''' == Anglais == '''Drag-and-Drop LLMs''' LoRA, a parameter-efficient finetuning method for large language models, underperforms full finetuning in target domains but provides better regularization and maintains diverse generation compared to other techniques. == Source == [https://huggingface.co/papers/2506.16406 Source : huggingface] Catégorie:vocabulary ») | ||||
25 juin 2025
| 18:26 | Top-Down Parsing diffhist +757 Arianne discussion contributions | ||||
| 15:00 | Multi-Token Projection diffhist +388 Arianne discussion contributions | ||||
| 14:55 | Conceptual Property Judgment diffhist +430 Arianne discussion contributions | ||||
22 juin 2025
| N 17:21 | World Model diffhist +231 Pitpitt discussion contributions (Page créée avec « ==en construction== == Définition == XXXXXXXXX == Français == ''' XXXXXXXXX ''' == Anglais == '''World Model''' == Source == [https://www.nvidia.com/en-us/glossary/world-models/ Source : nvidia ] Catégorie:vocabulary ») | ||||
| N 17:16 | Polars diffhist +677 Pitpitt discussion contributions (Page créée avec « ==en construction== == Définition == XXXXXXXXX == Français == ''' XXXXXXXXX ''' == Anglais == '''Polars''' == Source == [https://www.nvidia.com/en-us/glossary/polars/ Source : nvidia] Polars is an open-source DataFrame library for data manipulation and analysis. It is implemented in Rust and uses Apache Arrow’s columnar memory format for efficient data processing. The library provides a structured and typed API, enabling users to perform a wide range o... ») | ||||
| N 17:13 | Numba diffhist +225 Pitpitt discussion contributions (Page créée avec « ==en construction== == Définition == XXXXXXXXX == Français == ''' XXXXXXXXX ''' == Anglais == '''XXXXXXXXX''' == Source == [https://www.nvidia.com/en-us/glossary/numba/ Source : nvidia] Catégorie:vocabulary ») | ||||
| N 17:12 | Humanoid Robot diffhist +534 Pitpitt discussion contributions (Page créée avec « ==en construction== == Définition == XXXXXXXXX == Français == ''' XXXXXXXXX ''' == Anglais == '''Humanoid Robot''' Humanoids are general-purpose, bipedal robots modeled after the human form factor and designed to work alongside humans to augment productivity. They’re capable of learning and performing a variety of tasks, such as grasping an object, moving a container, loading or unloading boxes, and more. == Source == [https://www.nvidia.com/en-us/glos... ») | ||||
| N 17:11 | Data Flywheel diffhist +428 Pitpitt discussion contributions (Page créée avec « ==en construction== == Définition == XXXXXXXXX == Français == ''' XXXXXXXXX ''' == Anglais == '''Data Flywheel''' A data flywheel is a feedback loop where data collected from interactions or processes is used to continuously refine AI models, which in turn generates better outcomes and more valuable data. == Source == [https://www.nvidia.com/en-us/glossary/data-flywheel/ Source : nvidia] Catégorie:vocabulary ») | ||||
| N 17:10 | AI-RAN diffhist +655 Pitpitt discussion contributions (Page créée avec « ==en construction== == Définition == XXXXXXXXX == Français == ''' XXXXXXXXX ''' == Anglais == '''AI-RAN''' AI-RAN AI-RAN (artificial intelligence—radio access network) is a technology that enables the full integration of AI into the radio access network to realize transformative gains in operational performance, deliver new AI-based services, and unlock monetization opportunities. It enhances connectivity across mobile networks by leveraging AI to impro... ») | ||||
| N 17:09 | AI Factory diffhist +564 Pitpitt discussion contributions (Page créée avec « ==en construction== == Définition == XXXXXXXXX == Français == ''' XXXXXXXXX ''' == Anglais == '''AI Factory''' An AI factory is a specialized computing infrastructure designed to create value from data by managing the entire AI life cycle, from data ingestion to training, fine-tuning, and high-volume AI inference. The primary product is intelligence, measured by token throughput, which drives decisions, automation, and new AI solutions. == Source ==... ») | ||||
| 13:24 | Conceptual Similarity Judgment diffhist +358 Arianne discussion contributions | ||||
|
|
13:19 | Out Of Vocabulary Word 2 modifications historique +620 [Arianne (2×)] | |||
|
|
13:19 (actu | diff) +590 Arianne discussion contributions | ||||
|
|
11:56 (actu | diff) +30 Arianne discussion contributions | ||||
| 11:08 | Goal Regression diffhist +171 Arianne discussion contributions | ||||
20 juin 2025
| N 16:23 | Process Reward Model diffhist +279 Arianne discussion contributions (Page créée avec « == en construction == == Définition == xxxxxxx == Français == ''' XXXXXX''' == Anglais == ''' Process Reward Model''' ''' PRM''' == Sources == [https://arxiv.org/abs/2501.07301 Source : arxiv] [https://github.com/sdiehl/prm Source : GitHub] Catégorie:vocabulary ») | ||||
| N 16:20 | Self-Consistency diffhist +576 Arianne discussion contributions (Page créée avec « == en construction == == Définition == xxxxxxxx == Français == ''' XXXXXX''' == Anglais == ''' Self-Consistency''' ''' SC''' == Sources == [https://arxiv.org/html/2408.17017v1 Source : arxiv] [https://medium.com/@linz07m/self-consistency-a-better-approach-for-reasoning-in-llms-1a1b6798d443 Source : Medium] [https://www.promptingguide.ai/techniques/consistency Source : Prompt Engineering Guide] [https://towardsdatascience.com/achieving-greater-self... ») | ||||
| N 16:14 | Top-Down Parsing diffhist +689 Arianne discussion contributions (Page créée avec « == en construction == == Définition == xxxxxxx Voir aussi '''analyse syntaxique ascendante''' et '''analyse syntaxique''' == Français == ''' Analyse descendante''' == Anglais == ''' Top-Down Parsing''' ''' Top-Down Analysis''' ''' Topdown Analysis''' == Sources == [https://vitrinelinguistique.oqlf.gouv.qc.ca/fiche-gdt/fiche/8410056/analyse-descendante Source : Vitrine linguistique, OQLF] [https://www.btb.termiumplus.gc.ca/tp... ») | ||||
| N 16:08 | Multi-Token Projection diffhist +724 Arianne discussion contributions (Page créée avec « == en construction == == Définition == xxxxxxx Voir aussi '''apprentissage par renforcement avec rétroaction humaine''' et '''réseau autoattentif''' == Compléments == ''à faire'' == Français == ''' XXXXXX''' == Anglais == ''' Multi-Token Projection''' ''' Multiple-Token Projection''' ''' MTP''' == Sources == [https://arxiv.org/html/2505.07608v1 Source : arxiv] [https://datascientest.com/multi-token-prediction-tout-savoir Source : DataSc... ») | ||||
| N 15:58 | Conceptualization in Contexts diffhist +336 Arianne discussion contributions (Page créée avec « == en construction == == Définition == xxxxxxxx Voir aussi '''COPEN''' == Français == ''' XXXXXX''' == Anglais == ''' Conceptualization in Contexts''' ''' CiC''' == Sources == [https://arxiv.org/abs/2211.04079 Source : arxiv] [https://paperswithcode.com/dataset/copen Source : paperswithcode] Catégorie:vocabulary ») | ||||
| N 15:55 | Conceptual Property Judgment diffhist +334 Arianne discussion contributions (Page créée avec « == en construction == == Définition == xxxxxxxx Voir aussi '''COPEN''' == Français == ''' XXXXXX''' == Anglais == ''' Conceptual Property Judgment''' '''CPJ''' == Sources == [https://arxiv.org/abs/2211.04079 Source : arxiv] [https://paperswithcode.com/dataset/copen Source : paperswithcode] Catégorie:vocabulary ») | ||||
| N 15:26 | Conceptual Similarity Judgment diffhist +337 Arianne discussion contributions (Page créée avec « == en construction == == Définition == xxxxxxxx Voir aussi '''COPEN''' == Français == ''' XXXXXX''' == Anglais == ''' Conceptual Similarity Judgment''' ''' CSJ''' == Sources == [https://arxiv.org/abs/2211.04079 Source : arxiv] [https://paperswithcode.com/dataset/copen Source : paperswithcode] Catégorie:vocabulary ») | ||||
| N 15:23 | Out Of Vocabulary Word diffhist +375 Arianne discussion contributions (Page créée avec « == en construction == == Définition == xxxxx == Français == ''' XXXXXX''' == Anglais == ''' Out Of Vocabulary Word''' ''' Out-Of-Vocabulary Word''' ''' OOV word''' == Sources == [https://aclanthology.org/P19-1402/ Source : ACL Anthology] [https://spotintelligence.com/2024/10/08/out-of-vocabulary-oov-words/ Source : Spot Intelligence] Catégorie:vocabulary ») | ||||
| N 15:19 | Goal Regression diffhist +584 Arianne discussion contributions (Page créée avec « == en construction == == Définition == xxxxxx Voir aussi '''apprentissage basé sur l'explication''' == Français == ''' Régression de buts''' ''' Régression de but''' ''' Substitution régressive''' == Anglais == ''' Goal Regression''' == Sources == [https://www.btb.termiumplus.gc.ca/tpv2alpha/alpha-eng.html?lang=eng&i=1&srchtxt=r%C3%A9gression+de+buts&index=alt&codom2nd_wet=1#resultrecs Source : TERMIUM Plus] [https://vitrinelinguistique.oqlf.g... ») | ||||
| 13:52 | Query By Example diffhist +10 Arianne discussion contributions | ||||
19 juin 2025
|
|
N 13:36 | KV Cache 2 modifications historique +1 045 [Pitpitt (2×)] | |||
|
|
13:36 (actu | diff) +2 Pitpitt discussion contributions | ||||
| N |
|
13:35 (actu | diff) +1 043 Pitpitt discussion contributions (Page créée avec « ==en construction== == Définition == XXXXXXXXX == Français == ''' XXXXXXXXX ''' == Anglais == '''KV Cache''' a KV cache stores intermediate key (K) and value (V) computations for reuse during inference (after training), which results in a substantial speed-up when generating text. The downside of a KV cache is that it adds more complexity to the code, increases memory requirements (the main reason I initially didn't include it in the book), and can't be us... ») | |||
| N 13:34 | MiniMax-M1 diffhist +854 Pitpitt discussion contributions (Page créée avec « ==en construction== == Définition == == Français == ''' MiniMax-M1''' == Anglais == '''MiniMax-M1''' MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. MiniMax-M1 is powered by a hybrid Mixture-of-Experts (MoE) architecture combined with a lightning attention mechanism. The model is developed based on our previous MiniMax-Text-01 model, which contains a total of 456 billion parameters with 45.9 billion parameters ac... ») | ||||
17 juin 2025
| 15:41 | Journal des renommages Claude COULOMBE discussion contributions a déplacé la page Rule-Based Machine Translation vers Traduction automatique à base de règles | ||||
| 15:40 | Rule-Based Machine Translation diffhist −52 Claude COULOMBE discussion contributions | ||||
| 15:27 | Insertion de segment textuel diffhist −98 Patrickdrouin discussion contributions | ||||
15 juin 2025
| 15:56 | Silent Data Corruption diffhist +395 Arianne discussion contributions | ||||
| 15:19 | Query By Example diffhist +134 Arianne discussion contributions | ||||
