All Papers

Auto-generated index of papers extracted from wiki entries. 104 papers with 2+ mentions.

Group Relative Policy Optimization

Mentioned in 13 entries

• adagrpo-a-capability-aware-adaptive-enhancement-for-flow-bas
• bppo-binary-prefix-policy-optimization-for-efficient-grpo-st
• bv-blend-uncertainty-weighted-historical-baselines-for-stabl
• codistill-grpo-a-co-distillation-recipe-for-efficient-group-
• epig-tree-compute-optimal-branching-for-gradient-efficient-r
• grrm-group-relative-reward-modeling-for-machine-translation
• gupo-gradient-uncertainty-aware-policy-optimization-for-post
• hidden-states-know-where-reasoning-diverges-credit-assignmen
• i-sdpo-instance-level-adaptive-self-distillation-policy-opti
• lambdapo-a-lambda-style-policy-optimization-for-reasoning-la
• pair-prefix-aware-internal-reward-model-for-multi-turn-agent
• sd-grpo-verifiable-segment-decomposition-for-long-form-visio
• skip-connected-policy-optimization-for-implicit-advantage

Direct Preference Optimization

Mentioned in 13 entries

• adaptive-preference-optimization-with-uncertainty-aware-util
• ba-dpo-bias-adjusted-direct-preference-optimization-for-lang
• efficient-preference-poisoning-attack-on-offline-rlhf
• hipo-hierarchical-preference-optimization-for-adaptive-reaso
• improve-your-agents-tool-calling-accuracy-with-sft-and-dpo-o
• intrinsic-mutual-information-as-a-modulator-for-preference-o
• length-controlled-margin-based-preference-optimization-witho
• linear-dpo-linear-direct-preference-optimization-for-diffusi
• margin-adaptive-dpo-leveraging-reward-model-for-granular-con
• plc-dpo-posterior-label-correction-in-noisy-and-ambiguous-pr
• s-sppo-semantic-calibrated-self-play-preference-optimization
• tab-po-preference-optimization-with-a-token-level-adaptive-b
• tokenratio-principled-token-level-preference-optimization-vi

ARC-AGI-3

Mentioned in 11 entries

• answer-from-openai
• anyone-who-cared-about-the-science-of-ai-would-find-this-int
• arc-agi-3-a-new-challenge-for-frontier-agentic-intelligence
• goblin-level-blog-post
• gpt-56-sol-sets-a-new-sota-on-arc-agi-3-78-sol-is-the-first-
• gpt-6-astra-an-automated-ai-engineer-you-can-hire-for-6-an-h
• gpt-6-astra-scores-627-on-arc-agi-3-with-the-standard-harnes
• nvidia-built-its-own-coding-harness-to-optimize-cuda-gpu-ker
• nvidia-says-its-general-purpose-coding-agent-system-avo-scor
• our-general-purpose-coding-agent-just-scored-100-on-the-arc-
• training-to-benchmarks-getting-to-agi

Reinforcement Learning with Verifiable Rewards

Mentioned in 9 entries

• boosting-llm-reasoning-via-human-inspired-reward-shaping
• expo-exploration-prioritized-policy-optimization-via-adaptiv
• fg-expo-frontier-guided-exploration-prioritized-policy-optim
• lfpo-likelihood-free-policy-optimization-for-masked-diffusio
• multi-turn-rl-with-structural-and-performance-aware-rewards-
• perception-aware-policy-optimization-for-multimodal-reasonin
• policy-improvement-reinforcement-learning
• reinforcement-learning-with-robust-rubric-rewards
• selective-expert-guidance-for-effective-and-diverse-explorat

ParseBench

Mentioned in 7 entries

• anthropic-says-opus-47-hits-806-on-document-reasoning-up-fro
• astra-is-one-of-the-best-models-weve-tested-at-parsing-compl
• big-shoutout-to-perplexityai-for-properly-benchmarking-docum
• if-it-cant-parse-it-cant-perform-reliable-document-understan
• source-tweet-is-here-httpsxcomjerryjliu0status20449026207463
• thanks-for-the-shoutout-re-parsebench-opus-47-is-definitely-
• were-presenting-parsebench-at-cvpr-2026-today-come-learn-why

Low-Rank Adaptation

Mentioned in 4 entries

• controlnet-vs-lora
• lora-training-question
• the-mysterious-science-of-lora-training-sdxl
• when-training-a-wan-or-ltx-lora

SWE-Bench Pro

Mentioned in 4 entries

• 202618glm-51linux-202618linuxaiglm-51swe
• glm-51-from-zaiorg-is-now-live-on-orcarouter-1-open-source-m
• openai-says-it-found-widespread-task-issues-in-swe-bench-pro
• to-audit-swe-bench-pro-we-used-model-based-investigator-agen

TurboQuant

Mentioned in 4 entries

• a-note-on-turboquant-and-the-earlier-driveeden-line-of-work
• d-will-googles-turboquant-algorithm-hurt-ai-demand-for-memor
• sequential-kv-cache-compression-via-probabilistic-language-t
• turboquant-has-drawn-a-lot-of-attention-recently-but-the-acc

Platonic Representation Hypothesis

Mentioned in 4 entries

• displacement-geometry-captures-platonic-shared-reality-acros
• representation-alignment-rests-on-linear-structure
• rethinking-the-good-enough-embedding-for-easy-few-shot-learn
• the-capability-convergence-hypothesis-capability-from-access

ARC-AGI

Mentioned in 4 entries

• gemini
• remember-openai-tripled-its-score-on-arc-agi-with-a-harness-
• this-is-the-sort-of-early-prediction-you-can-make-when-you-p
• vcbench-benchmarking-llms-in-venture-capital

Navier-Stokes Millennium Prize Problem

Mentioned in 4 entries

• ainews-openai-reports-navier-stokes-singularity-find-in-88-h
• holy-shit
• one-of-the-most-amazing-moments-for-me-in-openai-history-was
• were-sharing-a-solution-to-the-navier-stokes-millennium-priz

FlashAttention

Mentioned in 3 entries

• flashattention-fa1fa4-in-pytorch---educational-implementatio
• qflash-bridging-quantization-and-memory-efficiency-in-vision
• we-power-1m-developers-globally-our-researchers-developed-fl

Language Models Need Sleep

Mentioned in 3 entries

• language-models-need-sleep
• language-models-need-sleep-let-your-agents-sleep-folks-on-a-
• the-top-ai-papers-of-the-week-may-24---may-31---skillopt---a

Lighthouse Attention

Mentioned in 3 entries

• cool-idea-from-nous-research-what-if-you-could-speed-up-long
• paper-httpsarxivorgabs260506554-code-httpsgithubcomighoshsub
• the-top-ai-papers-of-the-week-may-11---may-17---aevo----mem-

Temporal Straightening for Latent Planning

Mentioned in 3 entries

• come-and-chat-with-us-in-icml-excited-to-present-temporal-st
• temporal-straightening-for-latent-planning
• yann-lecuns-lab-borrowed-a-trick-from-the-human-brain-and-mo

Code as Agent Harness

Mentioned in 3 entries

• code-as-agent-harness
• great-new-paper-to-read-code-as-agent-harness-bookmark-it
• the-top-ai-papers-of-the-week-may-18---24---aira---metacogag

Reinforcement Learning from Verifiable Rewards

Mentioned in 3 entries

• marlaas-multi-tenant-asynchronous-reinforcement-learning-as-
• selector-guided-autonomous-curriculum-for-one-shot-reinforce
• what-are-key-factors-for-updates-in-rl-for-llm-reasoning

Group Relative Policy Optimization (GRPO)

Mentioned in 3 entries

• max-out-grpo-signal-adaptive-trace-prefix-control-for-hard-r
• reasoning-from-scratch-round-number-6-an-introduction-and-im
• reco-reweighting-grpo-against-distributional-concentration

JEPA

Mentioned in 3 entries

• be-yann-lecun-spend-years-building-jepa-at-meta-company-focu
• eladgil-bs-attention-was-born-in-montral-pytorch-in-nyc-alph
• lecun90-ai15m-yann-lecunjepa

TRINITY: An Evolved LLM Coordinator

Mentioned in 3 entries

• trinity-an-evolved-llm-coordinator
• trinity-an-evolved-llm-coordinator-httpsarxivorgabs251204695
• what-if-instead-of-building-one-giant-ai-we-evolved-a-coordi

Sakana Fugu Technical Report

Mentioned in 3 entries

• sakana-fugu-technical-report
• sakana-fugu-technical-report-httpsarxivorgabs260621228
• sakana-fugu-technical-report-httpsgithubcomsakanaaifugublobm

The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems

Mentioned in 3 entries

• babyagi-has-200-citations-but-0-papers-i-just-published-my-f
• recommended-reading
• the-paper

SimpleQA

Mentioned in 2 entries

• didnt-expect-this-we-replaced-embeddings-with-jev-in-gpt-res
• googles-ai-overviews-spew-out-millions-of-false-answers-per-

Neural Computers

Mentioned in 2 entries

• neural-computers
• neural-computers-rmaruy-httpsrmaruyhatenablogcomentry2026041

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Mentioned in 2 entries

• clawbench-can-ai-agents-complete-everyday-online-tasks
• clawbench-can-ai-agents-complete-everyday-online-tasks-153-t

Scaling Latent Reasoning via Looped Language Models

Mentioned in 2 entries

• i-strongly-suspect-that-claude-mythos-is-a-looped-language-m
• scaling-latent-reasoning-via-looped-language-models

Memory Intelligence Agent

Mentioned in 2 entries

• memory-intelligence-agent
• the-top-ai-papers-of-the-week-april-6---12---memento---neura

Stateless Decision Memory for Enterprise AI Agents

Mentioned in 2 entries

• stateless-decision-memory-for-enterprise-ai-agents
• worth-a-read-if-you-are-building-production-grade-ai-agents

GPQA

Mentioned in 2 entries

• all-benchmarks-are-flawed-but-gpqa-has-been-fairly-consisten
• paper-gpqa-mmlu-pro-and-mmmu-pro-were-audited-for-broken-que

CubePart: An Open-Vocabulary Part-Controllable 3D Generator

Mentioned in 2 entries

• cubepart-an-open-vocabulary-part-controllable-3d-generator
• cubepart-an-open-vocabulary-part-controllable-3d-generator-l

MirrorCode

Mentioned in 2 entries

• mirrorcode-ai-can-rebuild-entire-programs-from-behavior-alon
• paper-httpsepochaifilesmirrorcode3d9aabpdf

AlphaEvolve

Mentioned in 2 entries

• arepsilon-memevo-adaptive-cross-task-memory-transfer-for-llm
• improvevolve-basin-hopping-meets-llm-guided-evolutionary-sea

PostTrainBench

Mentioned in 2 entries

• glm-52-is-5x-cheaper-than-opus-48-and-11x-than-fable-5-yet-i
• this-is-a-wild-result-locus-the-automated-research-system-fr

ReAct

Mentioned in 2 entries

• benchmarking-local-agent-architecture-react-loop-vs-graph
• production-grade-ai-agents-for-financial-compliance-lessons-

Integrated Gradients

Mentioned in 2 entries

• diffusion-integrated-gradients-controllable-path-generation-
• spectral-integrated-gradients-for-coarse-to-fine-feature-att

AutoScientists

Mentioned in 2 entries

• banger-paper-from-harvard-autoscientists-drops-the-central-p
• the-top-ai-papers-of-the-week-may-24---may-31---skillopt---a

Attention Is All You Need

Mentioned in 2 entries

• as-america-turns-250-we-put-together-250-open-ai-milestones-
• built-trained-a-transformer-from-scratch-in-pure-pytorch-for

Sparser, Faster, Lighter Transformer Language Models

Mentioned in 2 entries

• sakanaailabs-nvidiaai-sparser-faster-lighter-transformer-lan
• sparser-faster-lighter-transformer-language-models

Measuring the Symmetry--Data Exchange Rate

Mentioned in 2 entries

• measuring-the-symmetry--data-exchange-rate
• r-measuring-the-symmetry--data-exchange-rate

Distribution Matching Distillation

Mentioned in 2 entries

• pdmd-projected-distribution-matching-distillation-for-video-
• sgmd-score-gradient-matching-distillation-for-few-step-video

Stealing Reasoning Traces from Proprietary LLM APIs

Mentioned in 2 entries

• hidden-reasoning-from-claude-and-gpt-are-decoded-and-it-is-i
• stealing-reasoning-traces-from-proprietary-llm-apis

D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models

Mentioned in 2 entries

• d-opsd-on-policy-self-distillation-for-continuously-tuning-s
• tongyi-mai-papers-d-opsd-on-policy-self-distillation-for-con

Proximal Policy Optimization

Mentioned in 2 entries

• ano-a-principled-approach-to-robust-policy-optimization
• reflective-policy-optimization

Contrastive SDF

Mentioned in 2 entries

• contrastive-sdf-gives-copies-of-the-same-model-opposing-beli
• were-sharing-new-research-with-apolloaievals-on-reward-seeki

Chain-of-Thought

Mentioned in 2 entries

• hybrid-latent-reasoning-with-decoupled-policy-optimization
• thinking-economically-a-hierarchical-framework-for-adaptive-

RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably

Mentioned in 2 entries

• excited-to-share-our-new-paper-rope-distinguishes-neither-po
• rope-distinguishes-neither-positions-nor-tokens-in-long-cont

The Next Decade in AI

Mentioned in 2 entries

• if-we-had-done-everything-i-suggested-in-my-2020-arxiv-artic
• six-years-ago-world-cognitive-models-were-the-centerpiece-of

Constrained Adaptive Rejection Sampling

Mentioned in 2 entries

• constrained-adaptive-rejection-sampling
• on-the-pod-constrained-adaptive-rejection-sampling-with-ucsd

Unified Neural Scaling Laws

Mentioned in 2 entries

• unified-neural-scaling-laws
• unified-neural-scaling-laws-paper-release-r

Joint Embedding Variational Bayes

Mentioned in 2 entries

• joint-embedding-variational-bayes
• r-joint-embedding-variational-bayes-tmlr-26

Learning to Orchestrate Agents in Natural Language with the Conductor

Mentioned in 2 entries

• introducing-our-new-work-learning-to-orchestrate-agents-in-n
• learning-to-orchestrate-agents-in-natural-language-with-the-

SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges

Mentioned in 2 entries

• 2026-sag-sql-retrieval-augmented-generation
• sag-sql-retrieval-augmented-generation-with-query-time-dynam

GAMUT

Mentioned in 2 entries

• new-research-from-meta-bookmark-it-most-factuality-work-chec
• the-top-ai-papers-of-the-week-july-20---july-26---gamut---pr

Transformers with Selective Access to Early Representations

Mentioned in 2 entries

• transformers-with-selective-access-to-early-representations
• transformers-with-selective-access-to-early-representations-

From Sensors to Insight: Rapid, Edge-to-Core Application Development for Sensor-Driven Applications

Mentioned in 2 entries

• from-sensors-to-insight-rapid-edge-to-core-application-devel
• poster-from-sensors-to-insight-rapid-edge-to-core-applicatio

Bridging Spherical Black-Box Optimizers

Mentioned in 2 entries

• bridging-spherical-black-box-optimizers
• we-are-pleased-to-present-our-latest-research-at-icml2026-br

Scaling Laws for Mixture Pretraining Under Data Constraints

Mentioned in 2 entries

• 2026-scaling-laws-mixture-pretraining-data-constraints
• scaling-laws-for-mixture-pretraining-under-data-constraints

Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes

Mentioned in 2 entries

• 2025-evidence-grounded-multimodal-urban-benchmark
• evidence-grounded-trustworthy-multimodal-reasoning-and-evalu

Elastic Attention Cores for Scalable Vision Transformers

Mentioned in 2 entries

• elastic-attention-cores-for-scalable-vision-transformers
• elastic-attention-cores-for-scalable-vision-transformers-r

Transformer

Mentioned in 2 entries

• originally-the-transformer-paper-was-proposed-to-improve-goo
• testing-gpt-6-astra-on-visualizing-popular-ai-papers-started

Delta Attention Residuals

Mentioned in 2 entries

• delta-attention-residuals
• r

3D Gaussian Splatting

Mentioned in 2 entries

• fourier-splatting-generalized-fourier-encoded-primitives-for
• tsgl-teacher-student-graph-learning-for-3dgs-compression

Is Grep All You Need?

Mentioned in 2 entries

• great-paper-discussing-agentic-search-vs-vector-search
• the-top-ai-papers-of-the-week-may-11---may-17---aevo----mem-

LLMs Corrupt Your Documents When You Delegate

Mentioned in 2 entries

• further-notes-on-our-recent-research-on-ai-delegation-and-lo
• llms-corrupt-your-documents-when-you-delegate

Learning, Fast and Slow: Towards LLMs That Adapt Continually

Mentioned in 2 entries

• learning-fast-and-slow-towards-llms-that-adapt-continually
• learning-fast-and-slow-towards-llms-that-adapt-continually-r

Follow the Mean: Reference-Guided Flow Matching

Mentioned in 2 entries

• follow-the-mean-reference-guided-flow-matching
• follow-the-mean-reference-guided-flow-matching-r

Environment-free Synthetic Data Generation for API-Calling Agents

Mentioned in 2 entries

• environment-free-synthetic-data-api-calling-agents
• environment-free-synthetic-data-generation-for-api-calling-a

MetaCogAgent

Mentioned in 2 entries

• new-paper-worth-reading-metacogagent-metacogagent-equips-a-m
• the-top-ai-papers-of-the-week-may-18---24---aira---metacogag

Memory as a Model

Mentioned in 2 entries

• memory-as-a-model-the-paper-augments-any-llm-with-a-separate
• the-top-ai-papers-of-the-week-may-18---24---aira---metacogag

Dinitz-Garg-Goemans conjecture

Mentioned in 2 entries

• llamaparse-cant-solve-a-conjecture-but-it-can-parse-this-as-
• who-would-you-give-authorship-to-the-person-who-wrote-58-wor

Scaling Behavior of Single LLM-Driven Multi-Agent Systems

Mentioned in 2 entries

• scaling-behavior-of-single-llm-driven-multi-agent-systems
• scaling-behavior-of-single-llm-driven-multi-agent-systems-do

Evidence Compilation Before Semantic Memory: ActiveGraph on LongMemEval-S

Mentioned in 2 entries

• activegraph-longmemeval-experiment-1-httpsxcomactivegraphais
• activegraphs-website-newsletter-and-marketing-are-all-run-on

Harnessing Agentic Evolution

Mentioned in 2 entries

• harnessing-agentic-evolution
• harnessing-agentic-evolution-pay-attention-to-this-one-if-yo

SkillOpt

Mentioned in 2 entries

• the-top-ai-papers-of-the-week-may-24---may-31---skillopt---a
• this-skillopt-paper-from-microsoft-is-a-must-read-bookmark-i

LongMemEval

Mentioned in 2 entries

• 1-on-memory-benchmark-longmemeval-with-gemini-flash-not-pro-
• the-quarq-agent-is-built-on-langgraph-langgraph-makes-it-eas

ExtractBench

Mentioned in 2 entries

• if-youre-interested-in-checking-out-llamaparse-for-document-
• we-wrote-a-36-page-arxiv-whitepaper-on-extractbench-our-effo

RLM paper

Mentioned in 2 entries

• the-term-rlm-recursive-language-model-got-a-lot-of-buzz-this
• very-notable-trajectory-comparison-writeup-here-buried-in-th

LEAP

Mentioned in 2 entries

• new-research-from-google-just-shows-the-impressive-results-y
• the-top-ai-papers-of-the-week-may-31---june-7---leap---autol

AutoMem

Mentioned in 2 entries

• automem-i-quite-like-this-idea-of-metamemory-bookmark-it-thi
• the-top-ai-papers-of-the-week-june-28---july-5---rlmf---auto

The Efficiency Frontier

Mentioned in 2 entries

• the-efficiency-frontier-cool-paper-on-context-management-as-
• the-top-ai-papers-of-the-week-may-24---may-31---skillopt---a

Attention to Mamba

Mentioned in 2 entries

• new-paper-from-apple-interesting-idea-attention-to-mamba-the
• the-top-ai-papers-of-the-week-april-19---26---skill-rag---de

Autogenesis

Mentioned in 2 entries

• cool-new-paper-on-self-improving-agents
• the-top-ai-papers-of-the-week-april-19---26---skill-rag---de

Agentic World Modeling

Mentioned in 2 entries

• agentic-world-modeling-massive-40-author-survey-just-dropped
• the-top-ai-papers-of-the-week-april-26---may-3---latent-agen

Recursive Multi-Agent Systems

Mentioned in 2 entries

• new-paper-recursive-multi-agent-systems
• recursive-multi-agent-systems

Skill Retrieval Augmentation for Agentic AI

Mentioned in 2 entries

• skill-retrieval-augmentation-for-agentic-ai
• skill-retrieval-augmentation-for-agentic-ai-great-read-for-a

When RL Meets Adaptive Speculative Training: A Unified Training-Serving System

Mentioned in 2 entries

• 6-when-rl-meets-adaptive-speculative-training-a-unified-trai
• when-rl-meets-adaptive-speculative-training-a-unified-traini

ChartQA

Mentioned in 2 entries

• document-ocr-benchmarks-are-still-an-open-problem-existing-d
• parsebench-is-the-first-benchmark-to-include-vlm-chart-under

A global workspace in language models

Mentioned in 2 entries

• interesting-stuff-and-the-visualization-at-the-end-is-worth-
• the-anthropomorphization-of-this-one-is-off-the-charts-why-d

SWE-bench Verified

Mentioned in 2 entries

• lm-performancewith-only-27b-parameters-qwen36-27b-outperform
• qwen-36-35b-a3b-is-insane-at-coding-unslothai-recently-dropp

Evaluating and Improving LLM Self-Modeling

Mentioned in 2 entries

• evaluating-and-improving-llm-self-modeling
• evaluating-and-improving-llm-self-modeling-really-interestin

Statistically-Lossless Quantization of Large Language Models

Mentioned in 2 entries

• paper-statistically-lossless-quantization-of-large-language-
• statistically-lossless-quantization-of-large-language-models

SWE-bench

Mentioned in 2 entries

• swe-explore-benchmarking-how-coding-agents-explore-repositor
• vcbench-benchmarking-llms-in-venture-capital

DeepSWE

Mentioned in 2 entries

• fugu-ultra-v2-by-the-numbers-full-results-httpssakanaaifugu-
• glm-53-flash-can-now-be-run-locally-run-3-bit-on-128gb-ram-v

MedAgentBench

Mentioned in 2 entries

• grok-46-is-1-on-healthcare-questions
• grok-46-takes-top-spot-on-this-benchmark

Deep learning is hitting a wall

Mentioned in 2 entries

• people-who-say-this-kind-of-thing-are-completely-lost-about-
• so-many-people-misremember-or-never-read-what-i-said-in-in-2

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD

Mentioned in 2 entries

• paper-slai-t-rex-full-parameter-post-training-of-the-deepsee
• slai-t-rex-full-parameter-post-training-of-the-deepseek-v4-f

Learning Multi-Agent Coordination via Sheaf-ADMM

Mentioned in 2 entries

• excited-to-share-our-paper-learning-multi-agent-coordination
• learning-multi-agent-coordination-via-sheaf-admm

CoSA: Correlation-Guided Change Attention with Learnable Residual Gating for Remote Sensing Change Detection

Mentioned in 2 entries

• cosa-correlation-guided-change-a-ttention-with-learnable-res
• cosa-correlation-guided-change-attention-with-learnable-resi

Modality-Autoregressive World-Action Models

Mentioned in 2 entries

• modality-autoregressive-world-action-models
• must-read-papers-of-the-week-jepa-anything-modality-autoregr

In-Context Robot Learning with VLM Agents

Mentioned in 2 entries

• in-context-robot-learning-with-vlm-agents
• must-read-papers-of-the-week-jepa-anything-modality-autoregr

Shared Selective Persistent Memory for Agentic LLM Systems

Mentioned in 2 entries

• 2026-shared-selective-persistent-memory
• shared-selective-persistent-memory-for-agentic-llm-systems

Reinforcement Learning for Calibrated Decisions

Mentioned in 2 entries

• jevs-calibration-was-measured-the-llms-won-d
• typesafe-ai-debuts-jev-a-model-using-reinforcement-learning-

Self-Play Pretraining with Zero Data

Mentioned in 2 entries

• can-an-lm-starting-from-random-init-learn-to-generate-all-of
• self-play-pretraining-with-zero-data

Complex KDA: Understanding and Enhancing the Expressivity of Kimi Delta Attention

Mentioned in 2 entries

• complex-kda-understanding-and-enhancing-the-expressivity-of-
• r-complex-kda-understanding-and-enhancing-the-expressivity-o