Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

COMPANY · ENTITY #7538

Qwen3.5-4B

Related event timeline, sources and context from the news index.

EVENT TIMELINE

5

RESEARCH · 1 SOURCE · arXiv cs.AI

Counterfactual lesion erasure trains MedScope-4B to report only image-visible findings

The paper (arXiv:2611.13006v1) creates counterfactual views by inpainting lesions and matched control edits from public segmentation datasets and uses them to train MedScope-4B (Qwen3.5-4B, LoRA, image tools) on label-derived trajectories. On 507 internal cases across five imaging types MedScope-4B achieved an evidence sensitivity gap (ESG) of 0.758 and claimed erased lesions in 9.6% of cases versus frontier VLMs with ESG 0.27–0.47 and erased-lesion claims of 41–62%; the effect weakened without counterfactual views, replicated on MedGemma 1.5 4B and other inpainting tools, and held in external centres though frontier models found more real lesions and MedScope-4B missed some critical findings (e.g., 0 of 48 pneumothorax films in one external test).

7.0

RESEARCH · 1 SOURCE · arXiv cs.AI

ThinkJev (arXiv:2610.37732v1): hybrid fast–slow method for calibrated typed decisions

ThinkJev is a method that uses one hybrid-thinking language model to run a fast ‘System 1’ (read logits for option letters) and a slow ‘System 2’ (read logits after the model 'thinks') so a single sampled thought supplies answers for every thinking budget. On benchmarks, the paper reports that with a 5% target error Qwen3.5-27B lets System 1 answer 24.5% of decisions (realized error 3.9%), and that escalating thinking for the rest reaches similar accuracy to always-thinking while using substantially fewer thought tokens; code and data generators are provided on GitHub.

6.0

RESEARCH · 1 SOURCE · arXiv cs.AI

ClawLoop: framework for self-improving harness-based LLM agents (arXiv:2610.14118v1)

arXiv preprint arXiv:2610.14118v1 introduces ClawLoop, a closed training loop for harness-based LLM agents that iteratively synthesizes tasks, trains agents (SFT/RL), and diagnoses failures to generate next-round training data without relying on an external teacher model. Using Qwen3.6-27B as the loop model, the authors report consistent gains on SkillsBench, Claw-Eval-Live, and ClawGym-Bench, and show the synthesized tasks transfer performance improvements to smaller Qwen3.5 4B and 9B models.

7.0

RESEARCH · 1 SOURCE · Apple Machine Learning Research

SCLATE: a substrate for continual-learning agent training and evaluation

SCLATE is an execution substrate that unifies scheduling for benchmarks and unmodified agents via an open event scheduler and a hybrid simulated clock, compressing long multi-session scenarios into shorter runtime and recording every model call through an in-container proxy. The authors ported seven benchmarks and ran ten harness/memory configurations across ten models, finding that added memory systems do not consistently outperform native harness memory; they also post-trained Qwen3.5-4B using unmodified harnesses and memory, which reduced file reads, raised SWE-bench Verified pass rate by 16.7 points, and increased held-out MetaClaw accuracy by up to 11.8 points.

7.0

MODELS · 1 SOURCE · NVIDIA Developer

NVIDIA releases NV-Reason-CT — open 3D CT VLM with radiologist-style chain-of-thought

NVIDIA introduced NV-Reason-CT, an open research 3D vision-language model that combines a full 3D vision transformer encoder with a Qwen3.5-4B language model trained to generate radiologist-style chain-of-thought reasoning and structured reports for chest and abdominal CT. The model reports state-of-the-art results on the CT-RATE benchmark (Macro-F1 0.614, Macro-AUROC 0.871), was judged clinically plausible by NIH radiologists, and is offered as a foundation for post-training and integration with NVIDIA Medical AI tools (segmentation, synthetic data).

8.0