O1 replication journey (part 2) A critical examination of how simple model distillation can match O1's mathematical abilities, raising concerns about AI research practices. Problem: Replicating O1 model capabilities has encouraged the use of undisclosed distillation
@askalphaxiv
-
Critic-V: External Feedback Framework for Vision-Language Models
By
–
Critic-V A framework using an external critic model to refine vision-language model outputs through feedback. Problem: Vision-language models struggle with errors like hallucinations and irrelevant reasoning due to lack of external feedback. Method: Combines a Reasoner that
-
Janus Framework Unifies Multimodal AI Understanding and Generation
By
–
Introducing Janus, a novel framework that
unifies multimodal understanding and generation. By decoupling visual encodings, Janus can easily extend to new input types such as audio and EEG signals Excited to have the author @wu_chengyue from @deepseek_ai to discuss their work! -
TokenFormer: Efficient Transformer Architecture Scaling from 124M to 1.4B Parameters
By
–
TokenFormer, a new model architecture from @cvml_mpiinf and @PKU1898
, scales from 124M to 1.4B parameters by treating parameters as tokens, maintaining Transformer performance with lower cost. Talk to the team @haiyang73756134 @ferjadnaeem @xyongqin @janericlenssen @fedassa here! -
ENN Nuclear Fusion Roadmap Faces Criticism on alphaXiv
By
–
Trending on alphaXiv: criticism of a recent nuclear fusion roadmap from ENN – one of the largest clean energy distributors in China. Tune into the discussion in the links below
-
Model Swarms: Collaborative LLM Expert Algorithm via Swarm Intelligence
By
–
New from @UW and @GoogleDeepMind
: Model Swarms, a collaborative search algorithm that adapts LLM experts to single task, multi-task domains, and reward models via swarm intelligence. Talk to the team @ZifengWang315 @chl260 @YejinChoinka @tsvetshop here! https://
alphaxiv.org/abs/2410.11163
v1
… -
Agent-as-a-Judge: AI Agents Evaluating Other Agents
By
–
New from @metaai and @KAUST_News
! Introducing Agent-as-a-Judge, a new framework where AI agents evaluate other AI agents, leading to a 97% saving in time AND cost Talk to the team @MingchenZhuge
, @SchmidhuberAI
,
@tydsh
, @zechunliu
, @YoungXiong1
, Yangyang Shi, @vikasc here! -
Meta’s LongVU VideoLLM Authors Discuss Research
By
–
Authors of LongVU, the new VideoLLM from @AIatMeta
, discussing their work this week on alphaXiv! http://
alphaxiv.org/abs/2410.17434 Huge shoutout to the team @xiaoqian_shen @liuzhuang1234 @Hu_Hsu @garvinchen2 @klightlm @zechunliu @balakrishnan_vr Florian Bordes @Fanyi_Xiao @hyunwoojkim -
Make Sehun’s Dream Come True: New AI Research Breakthrough
By
–
Make Sehun's dream come true: https://
alphaxiv.org/abs/2410.14193 -
arXiv Papers Now Available in Dark Mode Reading
By
–
NEW: Read arXiv papers in dark mode! pic.twitter.com/PGTXfzWsNI
— alphaXiv (@askalphaxiv) 23 octobre 2024NEW: Read arXiv papers in dark mode!