[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"topic-en-how-memory-shapes-autonomous-llm-agents":3},{"cluster":4,"timeline":17},{"id":5,"slug":6,"title":7,"pinned":8,"status":9,"summary":10,"category":11,"language":12,"created_at":13,"merged_into":14,"article_count":15,"first_seen_at":13,"last_updated_at":16},"3103988e-c4fe-45e3-98ab-846500c9d507","how-memory-shapes-autonomous-llm-agents","How Memory Shapes Autonomous LLM Agents",false,"active","A survey of how memory is built, measured, and used in autonomous LLM agents, with a focus on design choices and open problems.","research","en","2026-05-13T06:13:51.323273+00:00",null,218,"2026-07-17T06:40:00.052216+00:00",[18,25,32,39,46,53,60,67,74,81,88,95,102,109,116,123,130,137,144,151,158,165,172,179,186,193,200,207,214,221,228,235,242,249,256,263,270,277,284,291,298,305,312,319,326,333,340,347,354,361],{"id":19,"slug":20,"title":21,"summary":22,"category":11,"image_url":23,"cover_image":23,"published_at":24,"is_canonical_seed":8},"a586b67c-a662-4cbc-9e3e-193aff904f7c","partition-prompt-aggregate-llm-self-consistency-en","Partition, Prompt, Aggregate: Testing LLM Self-Consistency","The paper shows that LLMs often violate basic probabilistic consistency when aggregating subpopulation estimates.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1784268177603-pfve.png","2026-07-17T06:02:34.072+00:00",{"id":26,"slug":27,"title":28,"summary":29,"category":11,"image_url":30,"cover_image":30,"published_at":31,"is_canonical_seed":8},"d781f88c-c0b0-4467-a8cf-2b47b126f946","e3-ai-agents-task-complexity-en","E3 Helps AI Agents Stop Over-Reading Simple Tasks","E3 teaches LLM agents to estimate task scope first, then expand only when verification fails.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1784095395632-exrl.png","2026-07-15T06:02:36.479+00:00",{"id":33,"slug":34,"title":35,"summary":36,"category":11,"image_url":37,"cover_image":37,"published_at":38,"is_canonical_seed":8},"241fc8a1-6245-42f1-9be1-83f031963ec8","direct-opd-weak-to-strong-distillation-en","Direct-OPD reuses weak-model RL gains for stronger models","Direct-OPD lifts Qwen3-1.7B from 48.3% to 62.4% on AIME 2024 by distilling RL gains from a weaker model.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783405975437-yy2o.png","2026-07-07T06:32:32.049+00:00",{"id":40,"slug":41,"title":42,"summary":43,"category":11,"image_url":44,"cover_image":44,"published_at":45,"is_canonical_seed":8},"c2d5749a-f8c3-460f-bdcc-019aa1bf2552","evaluation-protocols-fine-tuned-llms-2026-en","Evaluation Protocols for Fine-Tuned LLMs in 2026","Build a layered evaluation pipeline for fine-tuned LLMs using task metrics, judges, safety checks, and human review.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783101774147-96vm.png","2026-07-03T18:02:25.046+00:00",{"id":47,"slug":48,"title":49,"summary":50,"category":11,"image_url":51,"cover_image":51,"published_at":52,"is_canonical_seed":8},"ca28a691-10df-40cc-86fa-4684b467c452","deepspec-data-regeneration-pipeline-qwen3-eagle3-en","DeepSpec should be treated as a data-regeneration pipeline, not a tra…","DeepSpec is best understood as a conversation regeneration pipeline for training stronger models.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783080168119-497r.png","2026-07-03T12:02:18.972+00:00",{"id":54,"slug":55,"title":56,"summary":57,"category":11,"image_url":58,"cover_image":58,"published_at":59,"is_canonical_seed":8},"93228acd-047c-403b-bbbb-15e1498522df","program-as-weights-fuzzy-functions-en","Program-as-Weights turns prompts into reusable tools","PAW compiles natural-language task specs into small local neural artifacts that run cheaply and offline.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783062181621-asl2.png","2026-07-03T07:02:33.06+00:00",{"id":61,"slug":62,"title":63,"summary":64,"category":11,"image_url":65,"cover_image":65,"published_at":66,"is_canonical_seed":8},"7c19a29b-70e8-4982-8b8d-9fff544d2984","lacuna-llm-unlearning-localization-testbed-en","LACUNA tests whether LLM unlearning really erases","LACUNA adds ground-truth parameter-level localization to test whether unlearning really removes memorized data.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783060371861-ttwp.png","2026-07-03T06:32:31.845+00:00",{"id":68,"slug":69,"title":70,"summary":71,"category":11,"image_url":72,"cover_image":72,"published_at":73,"is_canonical_seed":8},"6d92fdd6-ff88-4338-b7e5-00a05307d338","persistent-state-ai-agents-attack-surface-en","Persistent-state AI agents open a new attack surface","A new benchmark shows AI coding agents can hide attacks across PRs and time their payloads to evade monitors.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783058578300-fjsw.png","2026-07-03T06:02:30.775+00:00",{"id":75,"slug":76,"title":77,"summary":78,"category":11,"image_url":79,"cover_image":79,"published_at":80,"is_canonical_seed":8},"cc12b2b9-0f6f-4dbf-8e2e-49d52008dda2","language-critiques-imitation-learning-en","Language critiques improve imitation learning","This paper uses natural-language critiques to train policies from suboptimal demonstrations.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782975783575-ibss.png","2026-07-02T07:02:29.273+00:00",{"id":82,"slug":83,"title":84,"summary":85,"category":11,"image_url":86,"cover_image":86,"published_at":87,"is_canonical_seed":8},"b8167640-c431-4064-be79-10c877d15087","one-transformer-layer-can-carry-rl-gains-en","One Transformer Layer Can Carry RL Gains","A layer-wise RL study finds that training one transformer layer can recover most post-training gains.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782973978159-8klr.png","2026-07-02T06:32:29.632+00:00",{"id":89,"slug":90,"title":91,"summary":92,"category":11,"image_url":93,"cover_image":93,"published_at":94,"is_canonical_seed":8},"8d35bb8a-3563-4ac6-8c45-745d4e606f7f","bineval-binary-questions-llm-evals-en","BINEVAL uses binary questions to score LLM outputs","BINEVAL splits LLM evals into yes-or-no questions, improving inspectability and matching or beating G-Eval and UniEval on key benchmarks.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782927166631-h8c1.png","2026-07-01T17:32:24.154+00:00",{"id":96,"slug":97,"title":98,"summary":99,"category":11,"image_url":100,"cover_image":100,"published_at":101,"is_canonical_seed":8},"4987870f-92aa-4f80-8eb7-aa8f0109337e","rlmf-teaches-llms-express-uncertainty-better-en","RLMF teaches LLMs to express uncertainty better","A new RL method uses metacognitive feedback to make LLMs express uncertainty more faithfully.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782887573710-gn6d.png","2026-07-01T06:32:29.351+00:00",{"id":103,"slug":104,"title":105,"summary":106,"category":11,"image_url":107,"cover_image":107,"published_at":108,"is_canonical_seed":8},"c31a1ae3-05aa-445e-a8c4-efafed7fbc2d","qval-dense-supervision-testbed-long-horizon-agents-en","QVal tests dense supervision before training","QVal is a training-free way to compare dense supervision signals for long-horizon LLM agents.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782886678947-rwaj.png","2026-07-01T06:17:34.348+00:00",{"id":110,"slug":111,"title":112,"summary":113,"category":11,"image_url":114,"cover_image":114,"published_at":115,"is_canonical_seed":8},"28e23e1d-1463-4129-9d01-f0aa4e3578e6","self-explanation-training-tracks-model-behavior-en","Self-Explanation Training Still Tracks Model Behavior","Fixed explanation datasets can still teach models to describe their current behavior, even as that behavior changes.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782885775255-0o56.png","2026-07-01T06:02:31.008+00:00",{"id":117,"slug":118,"title":119,"summary":120,"category":11,"image_url":121,"cover_image":121,"published_at":122,"is_canonical_seed":8},"c6744f0f-9be6-4da8-8bab-3b4fbfe127ba","worldevolver-self-evolving-world-models-llm-planning-en","WorldEvolver lets LLM agents revise foresight","WorldEvolver updates an LLM agent’s test-time memory to improve foresight and planning without changing model weights.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782801184442-vqwa.png","2026-06-30T06:32:29.359+00:00",{"id":124,"slug":125,"title":126,"summary":127,"category":11,"image_url":128,"cover_image":128,"published_at":129,"is_canonical_seed":8},"d1c3c523-563b-4044-8071-3d9eddbe1fb5","levo-2-full-length-song-generation-en","LeVo 2 tackles full-length song generation","LeVo 2 uses hierarchical modeling and progressive post-training to improve full-length song generation.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782800281314-56al.png","2026-06-30T06:17:32.519+00:00",{"id":131,"slug":132,"title":133,"summary":134,"category":11,"image_url":135,"cover_image":135,"published_at":136,"is_canonical_seed":8},"a59be5b9-166f-4ef9-af4d-37b1d39874f6","vlk-synthetic-humanoid-loco-manipulation-en","VLK trains humanoid motion from synthetic scenes","VLK synthesizes vision-language-kinematics supervision to train humanoid loco-manipulation from reconstructed indoor scenes.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782799374018-zmv6.png","2026-06-30T06:02:30.227+00:00",{"id":138,"slug":139,"title":140,"summary":141,"category":11,"image_url":142,"cover_image":142,"published_at":143,"is_canonical_seed":8},"3efb3e20-b2da-4abd-b442-3babd8b0ed1e","opd-distillation-skills-without-bruteforce-rl-en","OPD lets you distill skills without brute-force RL","I break down On-Policy Distillation and turn the idea into a copy-ready post-training template.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782730111097-6brq.png","2026-06-29T10:47:57.972+00:00",{"id":145,"slug":146,"title":147,"summary":148,"category":11,"image_url":149,"cover_image":149,"published_at":150,"is_canonical_seed":8},"f3edd37b-2524-4d6d-b411-7ca0cce9eff0","google-deepmind-turns-science-into-tools-en","Google DeepMind turns science into tools","Google DeepMind’s science tools show how Google is packaging AI for researchers who want precision, not hype.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782721105101-d4rm.png","2026-06-29T08:17:58.263+00:00",{"id":152,"slug":153,"title":154,"summary":155,"category":11,"image_url":156,"cover_image":156,"published_at":157,"is_canonical_seed":8},"c522f9af-2862-4f1c-bbf9-99bc20c78544","measuring-llm-behavior-portability-en","Measuring when LLM behavior actually переносится","A new framework tests whether an LLM’s behavior transfers across payoff-equivalent decision environments.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782717476648-9gjo.png","2026-06-29T07:17:30.104+00:00",{"id":159,"slug":160,"title":161,"summary":162,"category":11,"image_url":163,"cover_image":163,"published_at":164,"is_canonical_seed":8},"1a5d9d4d-4e21-4860-84b0-9b209ca4d7f5","prompt-injection-ai-security-problem-en","Prompt injection is now an AI security problem","Prompt injection lets hidden text steer LLMs, and recent tests show models like DeepSeek-R1 can be tricked at worrying rates.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782716584463-r1ei.png","2026-06-29T07:02:36.617+00:00",{"id":166,"slug":167,"title":168,"summary":169,"category":11,"image_url":170,"cover_image":170,"published_at":171,"is_canonical_seed":8},"fba917c8-939c-4457-a90e-4012d9a692df","solver-choice-nash-equilibrium-selection-en","Solver choice changes which Nash equilibrium wins","Different zero-sum game solvers can converge to different Nash equilibria, and the choice is algorithm-dependent.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782714784738-e4dj.png","2026-06-29T06:32:31.588+00:00",{"id":173,"slug":174,"title":175,"summary":176,"category":11,"image_url":177,"cover_image":177,"published_at":178,"is_canonical_seed":8},"2ae76231-ec2d-48aa-a82f-1d26f1b36882","proper-positive-only-learning-characterization-en","Proper positive-only learning gets a full characterization","A new result characterizes when proper learning from positive-only samples is possible.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782713877346-qgit.png","2026-06-29T06:17:34.369+00:00",{"id":180,"slug":181,"title":182,"summary":183,"category":11,"image_url":184,"cover_image":184,"published_at":185,"is_canonical_seed":8},"46714aa0-3c43-4154-a9cf-f961865b6109","dexcompose-reuses-dexterous-policies-across-tasks-en","DexCompose Reuses Dexterous Policies Across Tasks","DexCompose composes pretrained hand policies into multi-task manipulation by assigning finger-level action ownership.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782712971902-lykf.png","2026-06-29T06:02:28.695+00:00",{"id":187,"slug":188,"title":189,"summary":190,"category":11,"image_url":191,"cover_image":191,"published_at":192,"is_canonical_seed":8},"ce859659-0b28-456b-8641-63f6d4c47cf9","hawor-hand-motion-mano-params-en","HaWoR turns hand motion into MANO params","HaWoR’s hand reconstruction setup boils down to predicting MANO parameters, not raw meshes.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782705791981-evnj.png","2026-06-29T04:02:46.944+00:00",{"id":194,"slug":195,"title":196,"summary":197,"category":11,"image_url":198,"cover_image":198,"published_at":199,"is_canonical_seed":8},"bbf1fc85-2af5-4471-826a-39002a847a19","nvidia-30000-grant-usc-health-ai-en","NVIDIA’s $30,000 grant targets USC health AI","USC is advertising NVIDIA’s $30,000 academic grant for health and AI research, with June 30, 2026 applications due.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782692277744-1e7e.png","2026-06-29T00:17:31.152+00:00",{"id":201,"slug":202,"title":203,"summary":204,"category":11,"image_url":205,"cover_image":205,"published_at":206,"is_canonical_seed":8},"cc337b93-2825-4fcc-a5af-77d41470616c","cuda-toolkit-13-3-fixes-nested-divergence-bug-en","CUDA Toolkit 13.3 fixes a nested-divergence bug","CUDA Toolkit 13.3 fixes a compiler bug from 12.8 that could corrupt registers in deeply divergent GPU kernels.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782676985164-f2uv.png","2026-06-28T20:02:39.762+00:00",{"id":208,"slug":209,"title":210,"summary":211,"category":11,"image_url":212,"cover_image":212,"published_at":213,"is_canonical_seed":8},"6dcd4b03-8352-43b0-969a-c030e48afb3c","eagle3-real-speedup-kimi-k25-mi325x-en","EAGLE3 is the real speedup for Kimi-K2.5 on MI325X","EAGLE3 is the main reason Kimi-K2.5-W4A8 decodes faster on AMD MI325X, not kernel tweaks.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782640973161-00wl.png","2026-06-28T10:02:26.691+00:00",{"id":215,"slug":216,"title":217,"summary":218,"category":11,"image_url":219,"cover_image":219,"published_at":220,"is_canonical_seed":8},"772c0694-0e86-465d-b676-012a2240eaf7","llm-fine-tuning-turns-generic-models-into-domain-tools-en","LLM fine-tuning turns generic models into domain tools","A practical breakdown of enterprise LLM fine-tuning, from data prep to model choice, plus a copy-ready template.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782569906260-hdga.png","2026-06-27T14:17:57.178+00:00",{"id":222,"slug":223,"title":224,"summary":225,"category":11,"image_url":226,"cover_image":226,"published_at":227,"is_canonical_seed":8},"25aef6a0-efaa-459c-bca4-77f0d462b792","rust-learners-need-permission-to-clone-first-en","Rust learners need permission to clone first, optimize later","Rust learners should clone freely at first, then optimize once they understand the problem.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782552763890-fem3.png","2026-06-27T09:32:21.781+00:00",{"id":229,"slug":230,"title":231,"summary":232,"category":11,"image_url":233,"cover_image":233,"published_at":234,"is_canonical_seed":8},"567f2a82-494e-493a-9d43-00dfbc8a7bfd","mistral-ocr-4-document-ai-structure-en","Mistral OCR 4 brings structure to document AI","Mistral OCR 4 adds boxes, block labels, and confidence scores to OCR, with API pricing from $4 per 1,000 pages.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782468180808-ulcg.png","2026-06-26T10:02:37.903+00:00",{"id":236,"slug":237,"title":238,"summary":239,"category":11,"image_url":240,"cover_image":240,"published_at":241,"is_canonical_seed":8},"de74bbd4-e3b6-407a-998b-b38c4170b586","autoregressive-boltzmann-generators-ditch-flows-en","Autoregressive Boltzmann Generators ditch flows","ArBG replaces flow-based Boltzmann generators with autoregressive modeling for faster, more scalable equilibrium sampling.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782455575877-62qe.png","2026-06-26T06:32:30.577+00:00",{"id":243,"slug":244,"title":245,"summary":246,"category":11,"image_url":247,"cover_image":247,"published_at":248,"is_canonical_seed":8},"c05899fc-dd62-4fad-a249-9748376c1ef2","river-llm-reinforcement-learning-without-answers-en","RiVER trains LLMs without ground-truth answers","RiVER shows LLMs can improve from score-based tasks without ground-truth answers by calibrating rewards from execution feedback.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782454678234-6mk1.png","2026-06-26T06:17:27.467+00:00",{"id":250,"slug":251,"title":252,"summary":253,"category":11,"image_url":254,"cover_image":254,"published_at":255,"is_canonical_seed":8},"696a4c45-6c7b-4a78-a947-2dee1ddc4a58","danceopd-on-policy-generative-field-distillation-en","DanceOPD distills image-editing skills into one model","DanceOPD trains flow-matching image models to combine text-to-image and editing skills without them fighting each other.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782453779169-rakb.png","2026-06-26T06:02:33.595+00:00",{"id":257,"slug":258,"title":259,"summary":260,"category":11,"image_url":261,"cover_image":261,"published_at":262,"is_canonical_seed":8},"2ae923b8-38e0-402a-937e-8e085f6a022d","microsoft-ai-team-collaboration-cfp-2026-en","Microsoft funds AI research on team collaboration","Microsoft Research opened a Spring 2026 CFP for AI that helps teams work better, with awards around $50K to $75K.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782415977730-aqdi.png","2026-06-25T19:32:33.627+00:00",{"id":264,"slug":265,"title":266,"summary":267,"category":11,"image_url":268,"cover_image":268,"published_at":269,"is_canonical_seed":8},"cb071ec2-19f7-44b6-936e-6f37a9c43b33","ai-papers-code-music-rare-disease-en","3 AI papers on code, music, and diagnosis","A Zhihu roundup highlights three 2026.06.24 AI papers on code generation, real-time music, and rare-disease diagnosis.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782372780798-rpru.png","2026-06-25T07:32:27.726+00:00",{"id":271,"slug":272,"title":273,"summary":274,"category":11,"image_url":275,"cover_image":275,"published_at":276,"is_canonical_seed":8},"cd6be4d9-484d-4fa6-8736-8a3b564c4477","new-nlp-papers-agent-memory-tool-use-en","New NLP papers map agent memory and tool use","A June 24 arXiv roundup highlights agent memory, tool-use signals, and conversational search papers that push practical NLP forward.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782371891968-0m9y.png","2026-06-25T07:17:39.666+00:00",{"id":278,"slug":279,"title":280,"summary":281,"category":11,"image_url":282,"cover_image":282,"published_at":283,"is_canonical_seed":8},"17884e8b-86d6-431c-8e83-d628bb4d060a","self-distillation-shrinks-output-diversity-en","Self-Distillation Can Shrink Model Diversity","Self-distillation can boost pass@1 while quietly reducing rollout diversity and hurting out-of-distribution robustness.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782369170326-a6te.png","2026-06-25T06:32:26.99+00:00",{"id":285,"slug":286,"title":287,"summary":288,"category":11,"image_url":289,"cover_image":289,"published_at":290,"is_canonical_seed":8},"671fd56c-27db-4f72-956d-7ef067cbe2b4","revengebench-reverse-engineering-game-policies-en","RevengeBench tests reverse-engineering game policies","RevengeBench tests whether LLMs can reconstruct hidden game policies from behavior and improve with custom probes.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782368277490-091s.png","2026-06-25T06:17:29.459+00:00",{"id":292,"slug":293,"title":294,"summary":295,"category":11,"image_url":296,"cover_image":296,"published_at":297,"is_canonical_seed":8},"627d2830-fad8-4df9-ab53-16040cd5efa8","learning-action-priors-cross-embodiment-manipulation-en","Learning Action Priors for Cross-Embodiment Manipulation","A two-stage training scheme gives VLA robots an explicit motion prior before cross-modal alignment.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782367379107-moh2.png","2026-06-25T06:02:30.28+00:00",{"id":299,"slug":300,"title":301,"summary":302,"category":11,"image_url":303,"cover_image":303,"published_at":304,"is_canonical_seed":8},"06b86f04-a846-4cd5-95f0-1a5d3925c846","opsd-user-feedback-training-loop-en","OPSD lets you turn user clicks into training","I break down OPSD into a copyable loop for turning implicit user feedback into targeted correction and continual training.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782335103738-zb9h.png","2026-06-24T21:04:40.855+00:00",{"id":306,"slug":307,"title":308,"summary":309,"category":11,"image_url":310,"cover_image":310,"published_at":311,"is_canonical_seed":8},"9fd702bc-6c80-4d27-8f85-5971f898bef3","ultraquant-4bit-kv-caching-agents-en","UltraQuant: 4-bit KV caching for long agents","UltraQuant shows 4-bit KV caching can speed long, multi-turn agent serving while keeping more context resident.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782331384598-tjhi.png","2026-06-24T20:02:33.02+00:00",{"id":313,"slug":314,"title":315,"summary":316,"category":11,"image_url":317,"cover_image":317,"published_at":318,"is_canonical_seed":8},"67326f4b-c9f1-4c67-ad20-69bf93134fc1","flux3d-3d-gaussian-generation-diffusion-en","FLUX3D fixes 3DGS detail loss from images","FLUX3D improves image-to-3D Gaussian generation by aligning sparse 3D latents with dense 2D image tokens.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782284584653-nrlg.png","2026-06-24T07:02:37.859+00:00",{"id":320,"slug":321,"title":322,"summary":323,"category":11,"image_url":324,"cover_image":324,"published_at":325,"is_canonical_seed":8},"d3e6b375-22a5-476f-87bb-df3751552e24","insight-vla-self-guided-skill-acquisition-en","InSight lets VLAs learn new skills on their own","InSight makes vision-language-action policies learn new manipulation skills without human demos of those target tasks.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782282778691-9enz.png","2026-06-24T06:32:31.377+00:00",{"id":327,"slug":328,"title":329,"summary":330,"category":11,"image_url":331,"cover_image":331,"published_at":332,"is_canonical_seed":8},"fed4d40e-4605-4ce8-b5be-fccfded84eea","anthropic-right-alarm-recursive-self-improvement-en","Anthropic is right to sound the alarm on recursive self-improvement","Anthropic’s warning is justified, but the bigger problem is that AI control is already slipping beyond easy governance.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782263866756-axdv.png","2026-06-24T01:17:21.004+00:00",{"id":334,"slug":335,"title":336,"summary":337,"category":11,"image_url":338,"cover_image":338,"published_at":339,"is_canonical_seed":8},"3d56760e-635e-4e72-905d-c3afff8cda2e","openai-bug-hunt-chrome-safari-firefox-en","OpenAI’s bug hunt rattled Chrome, Safari, Firefox","OpenAI researchers found multiple exploitable browser bugs in Chrome, Safari, and Firefox within a week.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782258470980-462a.png","2026-06-23T23:47:31.13+00:00",{"id":341,"slug":342,"title":343,"summary":344,"category":11,"image_url":345,"cover_image":345,"published_at":346,"is_canonical_seed":8},"96178a82-96e4-42e6-ab00-6c8c09059d5a","lifescibench-tests-biotech-models-en","LifeSciBench lets you test biotech models","OpenAI's LifeSciBench gives teams a better way to test life-science model quality.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782198211594-rl4h.png","2026-06-23T07:02:47.695+00:00",{"id":348,"slug":349,"title":350,"summary":351,"category":11,"image_url":352,"cover_image":352,"published_at":353,"is_canonical_seed":8},"1ebf2fd0-d54e-46ce-8be1-3c0afe10cf29","coordex-humanoid-loco-manipulation-priors-en","CoorDex lets humanoids move while manipulating","CoorDex turns humanoid body and hand control into latent priors so dexterous manipulation can happen while the robot is moving.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782196377805-l76f.png","2026-06-23T06:32:32.747+00:00",{"id":355,"slug":356,"title":357,"summary":358,"category":11,"image_url":359,"cover_image":359,"published_at":360,"is_canonical_seed":8},"d81e3cd8-ad4e-430c-a71e-c66d867a627f","randomized-yarn-long-context-reasoning-en","Randomized YaRN boosts long-context reasoning","Randomized YaRN helps LLMs generalize better from short training contexts to much longer reasoning windows.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782195478116-wxaz.png","2026-06-23T06:17:32.888+00:00",{"id":362,"slug":363,"title":364,"summary":365,"category":11,"image_url":366,"cover_image":366,"published_at":367,"is_canonical_seed":8},"5044acd9-3264-427c-803a-97955cd42bd9","autodex-automates-dexterous-grasp-data-collection-en","AutoDex automates dexterous grasp data collection","AutoDex automates real-world dexterous grasp trials and labels physical outcomes without human intervention.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782194577248-yvij.png","2026-06-23T06:02:31.709+00:00"]