Add EmoDebt (AAMAS 2026) to research thread; fix EvoEmo label (arxiv only)
Browse files
README.md
CHANGED
|
@@ -13,6 +13,7 @@ tags:
|
|
| 13 |
- small-language-model
|
| 14 |
- edge-deployable
|
| 15 |
- arxiv:2605.26785
|
|
|
|
| 16 |
- arxiv:2511.03370
|
| 17 |
- arxiv:2509.04310
|
| 18 |
- arxiv:2604.07003
|
|
@@ -61,9 +62,10 @@ Evaluated on the **`credit_recovery`** subset of [`humanlong/emotion-negotiation
|
|
| 61 |
|
| 62 |
Companion baselines for direct comparison (same benchmark, same protocol):
|
| 63 |
|
|
|
|
| 64 |
- **[EQ-Negotiator](https://github.com/Yunbo-max/EQ-Negotiator)** (NeurIPS 2025, [arXiv:2511.03370](https://arxiv.org/abs/2511.03370)) — persona + HMM + WSLS, learning-free.
|
|
|
|
| 65 |
- **[EmoMAS](https://github.com/Yunbo-max/EmoMAS)** (ACL 2026 Main, top 9%, [arXiv:2604.07003](https://arxiv.org/abs/2604.07003)) — Bayesian multi-agent orchestration, no pre-training.
|
| 66 |
-
- **[EvoEmo](https://github.com/Yunbo-max/EvoEmo)** (AAMAS 2026, [arXiv:2509.04310](https://arxiv.org/abs/2509.04310)) — online evolutionary emotion policies.
|
| 67 |
- Vanilla 7B and fixed-emotion 7B baselines.
|
| 68 |
|
| 69 |
Headline result from the paper: **EmoDistill achieves the highest utility across all four domains**, surpassing both vanilla baselines and emotion-selection-only approaches. Full numbers will be cross-linked here when the checkpoint is uploaded.
|
|
@@ -114,8 +116,9 @@ Apache 2.0 — matches the base model.
|
|
| 114 |
|
| 115 |
| Work | Venue | Role |
|
| 116 |
|---|---|---|
|
|
|
|
| 117 |
| [EQ-Negotiator](https://github.com/Yunbo-max/EQ-Negotiator) | NeurIPS 2025 | Personas + HMM + WSLS for SLMs |
|
| 118 |
-
| [EvoEmo](https://github.com/Yunbo-max/EvoEmo) |
|
| 119 |
| [EmoMAS](https://github.com/Yunbo-max/EmoMAS) | ACL 2026 (top 9%) | Bayesian multi-agent orchestration + 4 benchmarks |
|
| 120 |
| **EmoDistill** *(this repo)* | under review | Offline distillation into a 7B SLM |
|
| 121 |
|
|
|
|
| 13 |
- small-language-model
|
| 14 |
- edge-deployable
|
| 15 |
- arxiv:2605.26785
|
| 16 |
+
- arxiv:2503.21080
|
| 17 |
- arxiv:2511.03370
|
| 18 |
- arxiv:2509.04310
|
| 19 |
- arxiv:2604.07003
|
|
|
|
| 62 |
|
| 63 |
Companion baselines for direct comparison (same benchmark, same protocol):
|
| 64 |
|
| 65 |
+
- **[EmoDebt](https://github.com/Yunbo-max/EmoDebt)** (AAMAS 2026 Main, [arXiv:2503.21080](https://arxiv.org/abs/2503.21080)) — Bayesian-optimized emotional intelligence engine (foundational).
|
| 66 |
- **[EQ-Negotiator](https://github.com/Yunbo-max/EQ-Negotiator)** (NeurIPS 2025, [arXiv:2511.03370](https://arxiv.org/abs/2511.03370)) — persona + HMM + WSLS, learning-free.
|
| 67 |
+
- **[EvoEmo](https://github.com/Yunbo-max/EvoEmo)** ([arXiv:2509.04310](https://arxiv.org/abs/2509.04310)) — online evolutionary emotion policies.
|
| 68 |
- **[EmoMAS](https://github.com/Yunbo-max/EmoMAS)** (ACL 2026 Main, top 9%, [arXiv:2604.07003](https://arxiv.org/abs/2604.07003)) — Bayesian multi-agent orchestration, no pre-training.
|
|
|
|
| 69 |
- Vanilla 7B and fixed-emotion 7B baselines.
|
| 70 |
|
| 71 |
Headline result from the paper: **EmoDistill achieves the highest utility across all four domains**, surpassing both vanilla baselines and emotion-selection-only approaches. Full numbers will be cross-linked here when the checkpoint is uploaded.
|
|
|
|
| 116 |
|
| 117 |
| Work | Venue | Role |
|
| 118 |
|---|---|---|
|
| 119 |
+
| [EmoDebt](https://github.com/Yunbo-max/EmoDebt) | AAMAS 2026 Main | Bayesian-optimized emotional intelligence (foundational) |
|
| 120 |
| [EQ-Negotiator](https://github.com/Yunbo-max/EQ-Negotiator) | NeurIPS 2025 | Personas + HMM + WSLS for SLMs |
|
| 121 |
+
| [EvoEmo](https://github.com/Yunbo-max/EvoEmo) | arXiv preprint | Online evolutionary emotion policies |
|
| 122 |
| [EmoMAS](https://github.com/Yunbo-max/EmoMAS) | ACL 2026 (top 9%) | Bayesian multi-agent orchestration + 4 benchmarks |
|
| 123 |
| **EmoDistill** *(this repo)* | under review | Offline distillation into a 7B SLM |
|
| 124 |
|