codepawl/abo-glb
Viewer • Updated • 7.95k • 3.76k • 48
👋 Open to Work
melison
animemory
AI & ML interests
None yet
Recent Activity
liked a dataset about 1 hour ago
codepawl/abo-glb liked a Space 2 days ago
fastgpu/vram-and-gpu-cost-calculator liked a model 2 days ago
ccore/Qwen3.5-4B-GLB-3D-CoderOrganizations
liked a
dataset about 1 hour ago
liked a
Space 2 days ago
liked 3
models 2 days ago
liked a
model 3 days ago
reacted to savoji's post with 🔥 4 days ago
Post
1,816
One Qwen3-VL-8B checkpoint improves all three streaming spatial benchmarks at once: OST-Bench 50.52 to 63.93 (+13.41), UCS-Bench +7.44, OVO-S-Bench +4.91. The change is in the supervision, with no new memory module or annotation.
The ChronoReplay paper calls the failure mode interface lock-in: post-train on one answer format and that readout improves while others stall. A categorical-only control hits 58.03 on OVO-S but drops OST from 50.52 to 47.48.
🔍 The recipe
• Keep targets in native formats (option, metric value with units, timestamp)
• Replay episodes in source order, each target attached to its causal prefix
• Loss mass: 2/3 on 33,180 single-turn examples, 1/3 on 6,381 episodes (alpha = 0.5)
📊 The numbers
• Three-benchmark mean 56.86, against 50.74 (categorical-only) and 50.76 (trajectory-only)
• Chronological order beats a shifted-order control by about 2.41 OST points on two seeds; the 13.41 belongs to the whole recipe
• Adaptive frame selection adds +4.09 on OVO-S (57.98) with 80.50 frames instead of 128
⚠️ Caveats
• One backbone, indoor scenes only; the single-family comparison is confounded by data coverage
• The repo has a CPU smoke test and a --dry-run training command, but no license and no fine-tuned weights
ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence (2610.34283)
https://arxiv.org/abs/2610.34283
https://github.com/yihaohu0118/ChronoReplay
If you fine-tune VLMs for embodied work, do you score categorical, metric and temporal readouts together?
📚 Read it elsewhere
• The deep dive on Medium: https://medium.com/p/8d2fb1bf832d
• The long read on Substack: https://sajjadpakdamansavoji.substack.com/p/chronoreplay-lifts-qwen3-vl-8b-by
• The thread on X: https://x.com/saavoji/status/2116229682844877156
• Every version on sajjadpsavoji.github.io: https://sajjadpsavoji.github.io/blog#chronoreplay
The ChronoReplay paper calls the failure mode interface lock-in: post-train on one answer format and that readout improves while others stall. A categorical-only control hits 58.03 on OVO-S but drops OST from 50.52 to 47.48.
🔍 The recipe
• Keep targets in native formats (option, metric value with units, timestamp)
• Replay episodes in source order, each target attached to its causal prefix
• Loss mass: 2/3 on 33,180 single-turn examples, 1/3 on 6,381 episodes (alpha = 0.5)
📊 The numbers
• Three-benchmark mean 56.86, against 50.74 (categorical-only) and 50.76 (trajectory-only)
• Chronological order beats a shifted-order control by about 2.41 OST points on two seeds; the 13.41 belongs to the whole recipe
• Adaptive frame selection adds +4.09 on OVO-S (57.98) with 80.50 frames instead of 128
⚠️ Caveats
• One backbone, indoor scenes only; the single-family comparison is confounded by data coverage
• The repo has a CPU smoke test and a --dry-run training command, but no license and no fine-tuned weights
ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence (2610.34283)
https://arxiv.org/abs/2610.34283
https://github.com/yihaohu0118/ChronoReplay
If you fine-tune VLMs for embodied work, do you score categorical, metric and temporal readouts together?
📚 Read it elsewhere
• The deep dive on Medium: https://medium.com/p/8d2fb1bf832d
• The long read on Substack: https://sajjadpakdamansavoji.substack.com/p/chronoreplay-lifts-qwen3-vl-8b-by
• The thread on X: https://x.com/saavoji/status/2116229682844877156
• Every version on sajjadpsavoji.github.io: https://sajjadpsavoji.github.io/blog#chronoreplay
- 2 replies
liked 3
models 5 days ago
reacted to sergiopaniego's post with 🔥 5 days ago
Post
3,057
Mistral Large 4 (Le Chonk 🐈) is now live on the Hub and you can post-train it with TRL today!
SFT + LoRA example ready, runs on a single 8xB300 node
> model: mistralai/Mistral-Large-4-1T-A52B
> TRL example: https://github.com/huggingface/trl/tree/main/examples/sft_mistral_large_4
> blog: https://huggingface.co/blog/mistral-large4
SFT + LoRA example ready, runs on a single 8xB300 node
> model: mistralai/Mistral-Large-4-1T-A52B
> TRL example: https://github.com/huggingface/trl/tree/main/examples/sft_mistral_large_4
> blog: https://huggingface.co/blog/mistral-large4
liked a
model 5 days ago
upvoted a paper 5 days ago
liked 3
Spaces 8 days ago
liked 2
models 8 days ago
reacted to jiteshkprasad's post with 🔥 8 days ago
Post
3,665
We just released Vemana, a 278M Telugu base model trained from scratch, live in public, in about 16 hours on one H100. It learned from 5.1B tokens of public Telugu web text (Sangraha, FineWeb-2 and HPLT 3.0), seen about 2.4 times, so 12B tokens of training, with its own Telugu tokenizer.
On 416 Telugu Wikipedia pages written in Sep-Oct 2026, after nearly all the compared models were released, it scores 0.361 bits per byte. That is the lowest of every open base model under 1B we tested: nanochat-telugu-560M 0.383, Dhee-Pravega-OG Atom 0.393, Pothana Base v2 0.426, Gemma 3 1B 0.484. Same script and pages for every model, and the win rule was fixed before the run.
Sarvam-1 (2.5B) is still level or better, and on knowledge tests like Belebele and MILU Vemana is at chance, like most other small models. I think it’s most useful as a base for Telugu fine-tunes and for studying how a small model learns a language, so we put out all 12 checkpoints also. And you can run it right in your browser, on your own device.
Model: udgamlabs/Vemana-Base
Checkpoints: udgamlabs/Vemana-Checkpoints
GGUF: udgamlabs/Vemana-Base-GGUF
Try it in your browser: https://udgamlabs.com/models/vemana
Technical report: https://udgamlabs.com/research/vemana
On 416 Telugu Wikipedia pages written in Sep-Oct 2026, after nearly all the compared models were released, it scores 0.361 bits per byte. That is the lowest of every open base model under 1B we tested: nanochat-telugu-560M 0.383, Dhee-Pravega-OG Atom 0.393, Pothana Base v2 0.426, Gemma 3 1B 0.484. Same script and pages for every model, and the win rule was fixed before the run.
Sarvam-1 (2.5B) is still level or better, and on knowledge tests like Belebele and MILU Vemana is at chance, like most other small models. I think it’s most useful as a base for Telugu fine-tunes and for studying how a small model learns a language, so we put out all 12 checkpoints also. And you can run it right in your browser, on your own device.
Model: udgamlabs/Vemana-Base
Checkpoints: udgamlabs/Vemana-Checkpoints
GGUF: udgamlabs/Vemana-Base-GGUF
Try it in your browser: https://udgamlabs.com/models/vemana
Technical report: https://udgamlabs.com/research/vemana
- 2 replies
liked a
model 10 days ago
