What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models
Paper • 2601.06165 • Published • 16
AI & ML interests
None defined yet.
Recent Activity
View all activity
Cartinoe5930
authored 2
papers 6 days ago
Cartinoe5930
authored a
paper 7 days ago
Sri-Vigneshwar-DJ
posted an update 17 days ago
Post
124
We ran Feather DB v0.8.0 on LongMemEval (ICLR 2025) — 500 questions across real multi-session conversations, up to 115K tokens each.
**Score: 0.693** · GPT-4o full-context baseline: 0.640
Full 500-question run with Gemini-Flash: **$2.40**
Per-axis breakdown:
→ Info-extraction: **0.942**
→ Knowledge-update: **0.714**
→ Multi-session: **0.606**
→ Temporal: **0.477** ← the hard one, Phase 9 addresses this
Architecture: Hybrid BM25+dense · adaptive temporal decay · embedded (no server) · p50 = 0.19ms · MIT
Raw results + audit JSONs: Hawky-ai/longmemeval-results
We ran Feather DB v0.8.0 on LongMemEval (ICLR 2025) — 500 questions across real multi-session conversations, up to 115K tokens each.
**Score: 0.693** · GPT-4o full-context baseline: 0.640
Full 500-question run with Gemini-Flash: **$2.40**
Per-axis breakdown:
→ Info-extraction: **0.942**
→ Knowledge-update: **0.714**
→ Multi-session: **0.606**
→ Temporal: **0.477** ← the hard one, Phase 9 addresses this
Architecture: Hybrid BM25+dense · adaptive temporal decay · embedded (no server) · p50 = 0.19ms · MIT
pip install feather-dbRaw results + audit JSONs: Hawky-ai/longmemeval-results
alexrs
authored 5
papers 21 days ago
Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier
Paper • 2412.04261 • Published • 7
Command A: An Enterprise-Ready Large Language Model
Paper • 2504.00698 • Published • 29
Uncovering Cultural Representation Disparities in Vision-Language Models
Paper • 2505.14729 • Published • 1
One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers
Paper • 2506.10766 • Published • 1
Tiny Aya: Bridging Scale and Multilingual Depth
Paper • 2603.11510 • Published • 8
kenza-ily
authored a
paper about 2 months ago
peaceAsh
authored a
paper 2 months ago
kenza-ily
authored 3
papers 2 months ago
Machine Translation Hallucination Detection for Low and High Resource Languages using Large Language Models
Paper • 2407.16470 • Published
Retrieval or Representation? Reassessing Benchmark Gaps in Multilingual and Visually Rich RAG
Paper • 2603.04238 • Published
How Can We Diagnose and Treat Bias in Large Language Models for Clinical Decision-Making?
Paper • 2410.16574 • Published
Cartinoe5930
authored a
paper 3 months ago
Sri-Vigneshwar-DJ
posted an update 3 months ago
Post
1460
Just released a new dataset designed for training reasoning models on Meta (Facebook/Instagram) advertising fatigue detection!
What is it? A GRPO (Group Relative Policy Optimization) training dataset with 200+ carefully crafted scenarios covering:
🔍 Fatigue Signal Detection: CTR drops, CPM spikes, frequency analysis
🩺 Performance Diagnosis: Root cause analysis frameworks
📋 Strategy: Creative refresh cadence, testing frameworks
📊 Analysis: ROI calculations, metric interpretation
Why GRPO? GRPO training helps models learn structured reasoning. Each response follows the <thinking> and <answer> format.
Check it out here: Sri-Vigneshwar-DJ/meta-fatigue-grpo-dataset
What is it? A GRPO (Group Relative Policy Optimization) training dataset with 200+ carefully crafted scenarios covering:
🔍 Fatigue Signal Detection: CTR drops, CPM spikes, frequency analysis
🩺 Performance Diagnosis: Root cause analysis frameworks
📋 Strategy: Creative refresh cadence, testing frameworks
📊 Analysis: ROI calculations, metric interpretation
Why GRPO? GRPO training helps models learn structured reasoning. Each response follows the <thinking> and <answer> format.
Check it out here: Sri-Vigneshwar-DJ/meta-fatigue-grpo-dataset
Sri-Vigneshwar-DJ
posted an update 4 months ago
Post
241
🏙️ Hugging Face Community Post
Title: 🧬 Experimenting with "Dynamic Chaos" in Tamil SLMs
Hi everyone! I just published a new experimental study on Small Language Model (SLM) resilience.
I took the Qwen2.5-0.5B model and put it through a "Chaos Phase" to see how much weight data a tiny model can lose before its understanding of classical Tamil grammar breaks.
Key highlights of the study:
Target Data: Fine-tuned on the Thirukkural (1,330 couplets + modern explanations).
The Chaos Step: Applied 20% random weight pruning but implemented "Layer Protection" for the Token Embeddings and LM Head to keep the characters readable.
Compression: 4-bit (Q4_K_M) quantization for extreme efficiency.
Result: A surrealist classical Tamil model that is ultra-light (~300MB) and ultra-fast!
Check out the model and the experiment logic here: Sri-Vigneshwar-DJ/qwen-tamil-chaos-v1
Title: 🧬 Experimenting with "Dynamic Chaos" in Tamil SLMs
Hi everyone! I just published a new experimental study on Small Language Model (SLM) resilience.
I took the Qwen2.5-0.5B model and put it through a "Chaos Phase" to see how much weight data a tiny model can lose before its understanding of classical Tamil grammar breaks.
Key highlights of the study:
Target Data: Fine-tuned on the Thirukkural (1,330 couplets + modern explanations).
The Chaos Step: Applied 20% random weight pruning but implemented "Layer Protection" for the Token Embeddings and LM Head to keep the characters readable.
Compression: 4-bit (Q4_K_M) quantization for extreme efficiency.
Result: A surrealist classical Tamil model that is ultra-light (~300MB) and ultra-fast!
Check out the model and the experiment logic here: Sri-Vigneshwar-DJ/qwen-tamil-chaos-v1
bryanlimy
authored a
paper 4 months ago
BounharAbdelaziz
authored a
paper 4 months ago
BounharAbdelaziz
submitted a
paper to Daily Papers 4 months ago