[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.] #  @jiqizhixin 机器之心 JIQIZHIXIN 机器之心 JIQIZHIXIN posts on X about bytedance, voxels, 6969, $4751t the most. They currently have XXXXXX followers and XX posts still getting attention that total XXXXXX engagements in the last XX hours. ### Engagements: XXXXXX [#](/creator/twitter::819861340294524928/interactions)  - X Week XXXXXX -XX% - X Month XXXXXXX -XX% - X Months XXXXXXXXX +2,757% - X Year XXXXXXXXX +609,161% ### Mentions: XX [#](/creator/twitter::819861340294524928/posts_active)  - X Week XX +2.40% - X Month XXX -XX% - X Months XXX +798% - X Year XXX +44,600% ### Followers: XXXXXX [#](/creator/twitter::819861340294524928/followers)  - X Week XXXXXX +1.70% - X Month XXXXXX +10% - X Months XXXXXX +133% - X Year XXXXXX +146% ### CreatorRank: XXXXXXX [#](/creator/twitter::819861340294524928/influencer_rank)  ### Social Influence [#](/creator/twitter::819861340294524928/influence) --- **Social category influence** [technology brands](/list/technology-brands) XXXX% [nfts](/list/nfts) #3534 [countries](/list/countries) XXXX% [social networks](/list/social-networks) XXXX% **Social topic influence** [bytedance](/topic/bytedance) #3, [voxels](/topic/voxels) #17, [6969](/topic/6969) 1.75%, [$4751t](/topic/$4751t) 1.75%, [infrastructure](/topic/infrastructure) 1.75%, [breakthrough](/topic/breakthrough) #104, [university of](/topic/university-of) 1.75%, [china](/topic/china) 1.75%, [kuaishou](/topic/kuaishou) 1.75%, [kuaishou technology](/topic/kuaishou-technology) XXXX% **Top accounts mentioned or mentioned by** [@32showing](/creator/undefined) [@heydariai](/creator/undefined) [@ju4np3dz](/creator/undefined) [@nlituanie](/creator/undefined) **Top assets mentioned** [Voxels (voxels)](/topic/voxels) ### Top Social Posts [#](/creator/twitter::819861340294524928/posts) --- Top posts by engagements in the last XX hours "How well can multimodal LLMs understand long-distance travel videos Enter VIR-Bench a new benchmark with XXX real-world travel videos that challenges models to reconstruct itineraries and reason over extended geospatial-temporal trajectories. 🚗 Why it matters: mastering long-range video reasoning is key for embodied-AI planning and autonomous navigation. Findings: even top MLLMs struggle revealing major gaps in long-horizon understanding. A prototype travel agent built on VIR-Bench shows clear performance gains proving the benchmarks real-world value" [X Link](https://x.com/jiqizhixin/status/1979098765920473265) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-17T08:14Z 10.4K followers, 1114 engagements "📬 #PapersAccepted by Jiqizhixin Our report: VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction Waseda University CyberAgent and others Paper: Code:" [X Link](https://x.com/jiqizhixin/status/1979098770844602868) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-17T08:14Z 10.4K followers, XXX engagements "Huge ByteDance just unveiled their LLM training infrastructure ByteRobust is their GPU infrastructure system built for robust and continuous LLM training. It tackles common failuressuch as CUDA errors NaNs and job hangswith: - High-capacity fault tolerance - Fast fault demarcation and localization - Data-driven failure recovery Result: Deployed across 9600 GPUs ByteRobust achieves a XX% Effective Training Time Ratio (ETTR) over a three-month LLM training jobkeeping massive training pipelines stable and efficient" [X Link](https://x.com/jiqizhixin/status/1980520199158890529) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-21T06:23Z 10.4K followers, 1548 engagements "Kinematic-aware generation for next-gen animation & motion tasks Stability AI presents: Stable Part Diffusion 4D (SP4D) From a single video SP4D generates paired RGB + kinematic part videos going beyond appearance-based segmentation to capture true articulation. Key ideas: - Dual-branch diffusion (RGB + parts) - Spatial color encoding flexible part counts shared VAE - BiDiFuse + contrastive loss temporal & spatial consistency - New KinematicParts20K dataset (20K rigged objects) Results: ✨ Lift 2D part maps 3D skeletons & skinning weights 🌍 Generalizes to real-world novel objects rare poses" [X Link](https://x.com/jiqizhixin/status/1970332094049165610) [@jiqizhixin](/creator/x/jiqizhixin) 2025-09-23T03:39Z 10.4K followers, 1270 engagements "Our report: Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models Stanford SambaNova UC Berkeley Paper:" [X Link](https://x.com/jiqizhixin/status/1976903467181785184) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-11T06:51Z 10.4K followers, XXX engagements "Wow Multi-modal Diffusion Mamba MDM is a breakthrough architecture that fuses all modalities through a unified variational autoencoder and a Mamba-based multi-step diffusion process. Instead of separating image and text streams MDM jointly learns and refines representations enabling high-res image generation long-form text synthesis and visual QA & reasoning. MDM outperforms MonoFormer LlamaGen and Chameleon and rivals GPT-4V Gemini Pro and Mistral all while staying computationally efficient" [X Link](https://x.com/jiqizhixin/status/1980161738084602036) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-20T06:38Z 10.4K followers, 9157 engagements "Another breakthrough in world models VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents A new paper explores a frontier that enables vision-language (VLM) agents to build internal world models much like LLMs reason through text. By framing perception as a Partially Observable MDP the authors decompose reasoning into: - State Estimation Whats happening now - Transition Modeling What happens next They introduce: - World Modeling Reward for dense turn-level feedback - Bi-Level GAE for turn-aware credit assignment A 3B VLM agent scores XXXX across X benchmarks surpassing GPT-5" [X Link](https://x.com/jiqizhixin/status/1980555086674964886) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-21T08:41Z 10.4K followers, 4329 engagements "Are Gaussian Splatting's limitations holding back the future of 3D surface reconstruction 🤔 Enter GeoSVR a novel framework that leverages sparse voxels to create stunningly accurate detailed and complete 3D surfaces. By using a Voxel-Uncertainty Depth Constraint and Sparse Voxel Surface Regularization GeoSVR overcomes common challenges in the field ensuring geometric consistency and sharp details. Experiments show it outperforms existing methods in accuracy and completeness especially in difficult scenarios" [X Link](https://x.com/jiqizhixin/status/1978284197556183072) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-15T02:18Z 10.4K followers, 1317 engagements "📬 #PapersAccepted by Jiqizhixin Our report: GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction Beihang University Rawmantic AI and others Paper: Project: Code:" [X Link](https://x.com/jiqizhixin/status/1978284201800802580) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-15T02:18Z 10.4K followers, XXX engagements "Test-Time Scaling Law for robots just revealed. Meet RoboMonkey a clever framework that boosts Vision-Language-Action (VLA) models by scaling sampling and verification during inference. Researchers first uncover a key insight: VLA action errors follow a power-law decay with more samples revealing an inference-time scaling law. Building on that RoboMonkey: - Samples multiple candidate actions with Gaussian noise - Uses majority voting to form an action proposal distribution - Employs a VLM-based verifier (trained on synthetic data) to pick the best move The result 🚀 +25% on" [X Link](https://x.com/jiqizhixin/status/1978712036231217407) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-16T06:38Z 10.4K followers, 1197 engagements "Today's #1 Paper on Hugging Face Agentic Entropy-Balanced Policy Optimization (AEPO) With this method we can train smarter and more capable AI web agents without their learning processes collapsing. Its a reinforcement learning (RL) algorithm that addresses a key instability issue. Existing methods often over-rely on entropy (uncertainty) leading to training failures. AEPO intelligently balances this entropy during both exploration and policy updates. It uses a dynamic rollout that prevents the agent from getting stuck in uncertain loops and a novel optimization technique to learn from tricky" [X Link](https://x.com/jiqizhixin/status/1979161839121707043) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-17T12:25Z 10.4K followers, 1360 engagements "Agentic Entropy-Balanced Policy Optimization Renmin University of China Kuaishou Technology Paper: Code:" [X Link](https://x.com/jiqizhixin/status/1979161843890520288) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-17T12:25Z 10.4K followers, XXX engagements "Robust LLM Training Infrastructure at ByteDance" [X Link](https://x.com/jiqizhixin/status/1980520204108279863) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-21T06:23Z 10.4K followers, XXX engagements "Can high school geometry teach AI to understand space 📐 A new study tackles the critical challenge of spatial intelligence in Multimodal Large Language Models (MLLMs). Researchers found that fine-tuning models on Euclid30K a new dataset of 30000 Euclidean geometry problems confers broadly transferable spatial skills. After this geometry-centric training models achieved substantial zero-shot gains across four separate spatial reasoning benchmarks without any task-specific adaptation. For instance the average accuracy on the VSI-Bench benchmark rose from XXXX% to XXXX% showing this is a" [X Link](https://x.com/jiqizhixin/status/1980053599452303761) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-19T23:29Z 10.4K followers, 1137 engagements "Can todays LLMs safely stay on mission A new study introduces operational safety an LLMs ability to accept or refuse queries appropriately within its intended use. Researchers benchmarked XX open-weight models and found all remain highly unsafe for real-world deployment: - Qwen-3 (235B): XXXX% - Mistral (24B): XX% - GPTs: 6273% - Gemma & Llama-3: collapse to XX% XX% To fix this they propose prompt-based steering (Q-ground & P-ground) boosting safety by up to +41%. 📬 #PapersAccepted by Jiqizhixin Our report: OffTopicEval: When Large Language Models Enter the Wrong Chat Almost Always Nanyang" [X Link](https://x.com/jiqizhixin/status/1980157765751554555) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-20T06:22Z 10.4K followers, 1384 engagements "What is AGI Dan Hendrycks Yoshua Bengio Eric Schmidt Gary Marcus Max Tegmark and many others just released A Definition of AGI. Basically AGI is an AI that can match or exceed the cognitive versatility and proficiency of a well-educated adult. And no surprise GPT-4 and GPT-5 perform very poorly on the ten core cognitive components of their standard" [X Link](https://x.com/jiqizhixin/status/1979019210870395155) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-17T02:58Z 10.4K followers, 15.8K engagements "A big step toward stable scalable LLM agent training Rutgers University & Adobe just identifies a key pitfall in LLM agent training: the explorationexploitation cascade failure where agents first prematurely converge to bad strategies then collapse into chaotic exploration. To fix this they propose Entropy-regularized Policy Optimization (EPO) which: X Smooths entropy to prevent instability X Balances exploration & exploitation adaptively X Ensures monotonic entropy variance reduction Results: +152% on ScienceWorld +19.8% on ALFWorld. 📬 #PapersAccepted by Jiqizhixin Our report: EPO:" [X Link](https://x.com/jiqizhixin/status/1980299972684775584) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-20T15:48Z 10.4K followers, 2100 engagements "You can now generate 4-minute-long videos UCLA ByteDance and UCF have just released a new paper on this. It tackles a core challenge: long-horizon video quality collapse caused by error accumulation when models generate beyond their training length. Their simple but powerful solution: use the teachers own knowledge to guide the student through self-generated long segments no long-video data or retraining needed. ✨ Key results: - Scales video length XX beyond teachers limit - Generates X min XX sec videos (99.9% of positional span) - Fixes over-exposure & drift without overlap recomputation -" [X Link](https://x.com/jiqizhixin/status/1980711685686997412) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-21T19:04Z 10.4K followers, 12.7K engagements "Atlas is OpenAIs Mac browser built on Chromium" [X Link](https://x.com/jiqizhixin/status/1980798258881745081) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-22T00:48Z 10.4K followers, XXX engagements "When using AI browsers like ChatGPT Atlas or Comet you need to be extra careful Brave just released a report warning about a major threat: unseeable prompt injections in screenshots. Thats right: attackers can embed malicious instructions in web content that are invisible or barely noticeable to humans For example they might hide prompt injection commands inside images using faint light-blue text on a yellow background effectively concealing the malicious instructions from the user" [X Link](https://x.com/jiqizhixin/status/1980899350944547234) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-22T07:29Z 10.4K followers, XXX engagements "In fact Tsinghua University and Zhipu AI are conducting research similar to DeepSeek-OCR an approach that enables large language models (LLMs) to process up to a million tokens effortlessly. They introduce Glyph a framework that converts long text sequences into images and feeds them to vision-language models. This visual compression technique achieves a XX reduction in token count speeds up processing by approximately X and still matches the performance of top-tier LLMsunlocking million-token contexts and enhancing multimodal tasks such as document understanding" [X Link](https://x.com/jiqizhixin/status/1980910306844160165) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-22T08:13Z 10.4K followers, 1036 engagements "Glyph: Scaling Context Windows via Visual-Text Compression Tsinghua University Zhipu AI" [X Link](https://x.com/jiqizhixin/status/1980910311487205500) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-22T08:13Z 10.4K followers, XXX engagements "How can AI truly understand long videos without massive retraining or proprietary models Video-RAG might be an answer. It's a training-free plug-and-play method that boosts long video comprehension by retrieving visually aligned auxiliary textsfrom audio OCR and object cuesand feeding them into existing LVLMs. Its lightweight open and even outperforms Gemini-1.5-Pro and GPT-4o on long-video benchmarks. 📬 #PapersAccepted by Jiqizhixin Our report: Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension Xiamen University University of Rochester Project: Paper: Code:" [X Link](https://x.com/jiqizhixin/status/1980910746922787117) [@jiqizhixin](/creator/x/jiqizhixin) 2025-10-22T08:15Z 10.4K followers, XXX engagements
[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]
@jiqizhixin 机器之心 JIQIZHIXIN
机器之心 JIQIZHIXIN posts on X about bytedance, voxels, 6969, $4751t the most. They currently have XXXXXX followers and XX posts still getting attention that total XXXXXX engagements in the last XX hours.
Engagements: XXXXXX #
- X Week XXXXXX -XX%
- X Month XXXXXXX -XX%
- X Months XXXXXXXXX +2,757%
- X Year XXXXXXXXX +609,161%
Mentions: XX #
- X Week XX +2.40%
- X Month XXX -XX%
- X Months XXX +798%
- X Year XXX +44,600%
Followers: XXXXXX #
- X Week XXXXXX +1.70%
- X Month XXXXXX +10%
- X Months XXXXXX +133%
- X Year XXXXXX +146%
CreatorRank: XXXXXXX #
Social Influence #
Social category influence technology brands XXXX% nfts #3534 countries XXXX% social networks XXXX%
Social topic influence bytedance #3, voxels #17, 6969 1.75%, $4751t 1.75%, infrastructure 1.75%, breakthrough #104, university of 1.75%, china 1.75%, kuaishou 1.75%, kuaishou technology XXXX%
Top accounts mentioned or mentioned by @32showing @heydariai @ju4np3dz @nlituanie
Top assets mentioned Voxels (voxels)
Top Social Posts #
Top posts by engagements in the last XX hours
"How well can multimodal LLMs understand long-distance travel videos Enter VIR-Bench a new benchmark with XXX real-world travel videos that challenges models to reconstruct itineraries and reason over extended geospatial-temporal trajectories. 🚗 Why it matters: mastering long-range video reasoning is key for embodied-AI planning and autonomous navigation. Findings: even top MLLMs struggle revealing major gaps in long-horizon understanding. A prototype travel agent built on VIR-Bench shows clear performance gains proving the benchmarks real-world value"
X Link @jiqizhixin 2025-10-17T08:14Z 10.4K followers, 1114 engagements
"📬 #PapersAccepted by Jiqizhixin Our report: VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction Waseda University CyberAgent and others Paper: Code:"
X Link @jiqizhixin 2025-10-17T08:14Z 10.4K followers, XXX engagements
"Huge ByteDance just unveiled their LLM training infrastructure ByteRobust is their GPU infrastructure system built for robust and continuous LLM training. It tackles common failuressuch as CUDA errors NaNs and job hangswith: - High-capacity fault tolerance - Fast fault demarcation and localization - Data-driven failure recovery Result: Deployed across 9600 GPUs ByteRobust achieves a XX% Effective Training Time Ratio (ETTR) over a three-month LLM training jobkeeping massive training pipelines stable and efficient"
X Link @jiqizhixin 2025-10-21T06:23Z 10.4K followers, 1548 engagements
"Kinematic-aware generation for next-gen animation & motion tasks Stability AI presents: Stable Part Diffusion 4D (SP4D) From a single video SP4D generates paired RGB + kinematic part videos going beyond appearance-based segmentation to capture true articulation. Key ideas: - Dual-branch diffusion (RGB + parts) - Spatial color encoding flexible part counts shared VAE - BiDiFuse + contrastive loss temporal & spatial consistency - New KinematicParts20K dataset (20K rigged objects) Results: ✨ Lift 2D part maps 3D skeletons & skinning weights 🌍 Generalizes to real-world novel objects rare poses"
X Link @jiqizhixin 2025-09-23T03:39Z 10.4K followers, 1270 engagements
"Our report: Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models Stanford SambaNova UC Berkeley Paper:"
X Link @jiqizhixin 2025-10-11T06:51Z 10.4K followers, XXX engagements
"Wow Multi-modal Diffusion Mamba MDM is a breakthrough architecture that fuses all modalities through a unified variational autoencoder and a Mamba-based multi-step diffusion process. Instead of separating image and text streams MDM jointly learns and refines representations enabling high-res image generation long-form text synthesis and visual QA & reasoning. MDM outperforms MonoFormer LlamaGen and Chameleon and rivals GPT-4V Gemini Pro and Mistral all while staying computationally efficient"
X Link @jiqizhixin 2025-10-20T06:38Z 10.4K followers, 9157 engagements
"Another breakthrough in world models VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents A new paper explores a frontier that enables vision-language (VLM) agents to build internal world models much like LLMs reason through text. By framing perception as a Partially Observable MDP the authors decompose reasoning into: - State Estimation Whats happening now - Transition Modeling What happens next They introduce: - World Modeling Reward for dense turn-level feedback - Bi-Level GAE for turn-aware credit assignment A 3B VLM agent scores XXXX across X benchmarks surpassing GPT-5"
X Link @jiqizhixin 2025-10-21T08:41Z 10.4K followers, 4329 engagements
"Are Gaussian Splatting's limitations holding back the future of 3D surface reconstruction 🤔 Enter GeoSVR a novel framework that leverages sparse voxels to create stunningly accurate detailed and complete 3D surfaces. By using a Voxel-Uncertainty Depth Constraint and Sparse Voxel Surface Regularization GeoSVR overcomes common challenges in the field ensuring geometric consistency and sharp details. Experiments show it outperforms existing methods in accuracy and completeness especially in difficult scenarios"
X Link @jiqizhixin 2025-10-15T02:18Z 10.4K followers, 1317 engagements
"📬 #PapersAccepted by Jiqizhixin Our report: GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction Beihang University Rawmantic AI and others Paper: Project: Code:"
X Link @jiqizhixin 2025-10-15T02:18Z 10.4K followers, XXX engagements
"Test-Time Scaling Law for robots just revealed. Meet RoboMonkey a clever framework that boosts Vision-Language-Action (VLA) models by scaling sampling and verification during inference. Researchers first uncover a key insight: VLA action errors follow a power-law decay with more samples revealing an inference-time scaling law. Building on that RoboMonkey: - Samples multiple candidate actions with Gaussian noise - Uses majority voting to form an action proposal distribution - Employs a VLM-based verifier (trained on synthetic data) to pick the best move The result 🚀 +25% on"
X Link @jiqizhixin 2025-10-16T06:38Z 10.4K followers, 1197 engagements
"Today's #1 Paper on Hugging Face Agentic Entropy-Balanced Policy Optimization (AEPO) With this method we can train smarter and more capable AI web agents without their learning processes collapsing. Its a reinforcement learning (RL) algorithm that addresses a key instability issue. Existing methods often over-rely on entropy (uncertainty) leading to training failures. AEPO intelligently balances this entropy during both exploration and policy updates. It uses a dynamic rollout that prevents the agent from getting stuck in uncertain loops and a novel optimization technique to learn from tricky"
X Link @jiqizhixin 2025-10-17T12:25Z 10.4K followers, 1360 engagements
"Agentic Entropy-Balanced Policy Optimization Renmin University of China Kuaishou Technology Paper: Code:"
X Link @jiqizhixin 2025-10-17T12:25Z 10.4K followers, XXX engagements
"Robust LLM Training Infrastructure at ByteDance"
X Link @jiqizhixin 2025-10-21T06:23Z 10.4K followers, XXX engagements
"Can high school geometry teach AI to understand space 📐 A new study tackles the critical challenge of spatial intelligence in Multimodal Large Language Models (MLLMs). Researchers found that fine-tuning models on Euclid30K a new dataset of 30000 Euclidean geometry problems confers broadly transferable spatial skills. After this geometry-centric training models achieved substantial zero-shot gains across four separate spatial reasoning benchmarks without any task-specific adaptation. For instance the average accuracy on the VSI-Bench benchmark rose from XXXX% to XXXX% showing this is a"
X Link @jiqizhixin 2025-10-19T23:29Z 10.4K followers, 1137 engagements
"Can todays LLMs safely stay on mission A new study introduces operational safety an LLMs ability to accept or refuse queries appropriately within its intended use. Researchers benchmarked XX open-weight models and found all remain highly unsafe for real-world deployment: - Qwen-3 (235B): XXXX% - Mistral (24B): XX% - GPTs: 6273% - Gemma & Llama-3: collapse to XX% XX% To fix this they propose prompt-based steering (Q-ground & P-ground) boosting safety by up to +41%. 📬 #PapersAccepted by Jiqizhixin Our report: OffTopicEval: When Large Language Models Enter the Wrong Chat Almost Always Nanyang"
X Link @jiqizhixin 2025-10-20T06:22Z 10.4K followers, 1384 engagements
"What is AGI Dan Hendrycks Yoshua Bengio Eric Schmidt Gary Marcus Max Tegmark and many others just released A Definition of AGI. Basically AGI is an AI that can match or exceed the cognitive versatility and proficiency of a well-educated adult. And no surprise GPT-4 and GPT-5 perform very poorly on the ten core cognitive components of their standard"
X Link @jiqizhixin 2025-10-17T02:58Z 10.4K followers, 15.8K engagements
"A big step toward stable scalable LLM agent training Rutgers University & Adobe just identifies a key pitfall in LLM agent training: the explorationexploitation cascade failure where agents first prematurely converge to bad strategies then collapse into chaotic exploration. To fix this they propose Entropy-regularized Policy Optimization (EPO) which: X Smooths entropy to prevent instability X Balances exploration & exploitation adaptively X Ensures monotonic entropy variance reduction Results: +152% on ScienceWorld +19.8% on ALFWorld. 📬 #PapersAccepted by Jiqizhixin Our report: EPO:"
X Link @jiqizhixin 2025-10-20T15:48Z 10.4K followers, 2100 engagements
"You can now generate 4-minute-long videos UCLA ByteDance and UCF have just released a new paper on this. It tackles a core challenge: long-horizon video quality collapse caused by error accumulation when models generate beyond their training length. Their simple but powerful solution: use the teachers own knowledge to guide the student through self-generated long segments no long-video data or retraining needed. ✨ Key results: - Scales video length XX beyond teachers limit - Generates X min XX sec videos (99.9% of positional span) - Fixes over-exposure & drift without overlap recomputation -"
X Link @jiqizhixin 2025-10-21T19:04Z 10.4K followers, 12.7K engagements
"Atlas is OpenAIs Mac browser built on Chromium"
X Link @jiqizhixin 2025-10-22T00:48Z 10.4K followers, XXX engagements
"When using AI browsers like ChatGPT Atlas or Comet you need to be extra careful Brave just released a report warning about a major threat: unseeable prompt injections in screenshots. Thats right: attackers can embed malicious instructions in web content that are invisible or barely noticeable to humans For example they might hide prompt injection commands inside images using faint light-blue text on a yellow background effectively concealing the malicious instructions from the user"
X Link @jiqizhixin 2025-10-22T07:29Z 10.4K followers, XXX engagements
"In fact Tsinghua University and Zhipu AI are conducting research similar to DeepSeek-OCR an approach that enables large language models (LLMs) to process up to a million tokens effortlessly. They introduce Glyph a framework that converts long text sequences into images and feeds them to vision-language models. This visual compression technique achieves a XX reduction in token count speeds up processing by approximately X and still matches the performance of top-tier LLMsunlocking million-token contexts and enhancing multimodal tasks such as document understanding"
X Link @jiqizhixin 2025-10-22T08:13Z 10.4K followers, 1036 engagements
"Glyph: Scaling Context Windows via Visual-Text Compression Tsinghua University Zhipu AI"
X Link @jiqizhixin 2025-10-22T08:13Z 10.4K followers, XXX engagements
"How can AI truly understand long videos without massive retraining or proprietary models Video-RAG might be an answer. It's a training-free plug-and-play method that boosts long video comprehension by retrieving visually aligned auxiliary textsfrom audio OCR and object cuesand feeding them into existing LVLMs. Its lightweight open and even outperforms Gemini-1.5-Pro and GPT-4o on long-video benchmarks. 📬 #PapersAccepted by Jiqizhixin Our report: Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension Xiamen University University of Rochester Project: Paper: Code:"
X Link @jiqizhixin 2025-10-22T08:15Z 10.4K followers, XXX engagements