跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 13:24 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 14:01 — 2026-11-09 14:01（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-09 13:24最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

18,172 已收录论文15,506 AI 相关4,527 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 4 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 13:22（北京时间）
新论文 · v1arXiv:2611.09014

Did I See It or Think It? Probing Reality Monitoring in Vision-Language Models with Concept Injection

Tina Khezresmaeilzadeh, Seyedarmin Azizi, Mehdi Kamal, Massoud Pedram

原文摘要

Recent work tests whether language models can introspect by injecting a concept direction into their activations and asking whether they notice it and can name it. These studies are text-only. Vision-language models (VLMs) face an additional problem, known in cognitive psychology as reality monitoring: they must keep internally generated content separate from what they actually see. We therefore ask: can VLMs distinguish injected concepts from image content? We introduce a paradigm that varies the image and the injected concept independently. On each trial, the model reports what it sees, whether a thought was injected, and what that thought is. This design scores both whether the model identifies the concept and which source it assigns to it. Across six VLMs, only Gemma-3-27B reliably identifies injected concepts (35% vs. 3% for steering alone), with almost no false alarms. Even then, the source it reports is fragile. Strong or visual-pathway injections are reported as seen, and a visible object nearly eliminates correct thought reports. The same failure appears in ordinary captioning, where injected objects appear in up to 87% of captions of real photographs. Evaluating multimodal self-reports therefore requires checking both their content and their reported source.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06147

SafeStart: Mitigating the Overlooked Safety Cost of Active Expert Reduction in MoE LLM Serving

Erfan Baghaei Potraghloo, Saeid Shokoufa, Seyedarmin Azizi, Arya Fayyazi, Souvik Kundu, Mehdi Kamal, Massoud Pedram

原文摘要

Mixture-of-Experts (MoE) language models send each token through a few of many expert subnetworks. Serving methods make these models faster by running even fewer experts per token, and they are validated on accuracy benchmarks. We show that these methods can weaken the model's refusal of harmful requests, and we introduce SafeStart, which largely restores refusal while keeping most of the speedup. In vLLM on one RTX A6000, keeping about two thirds of the selected experts speeds up offline decoding by 15 to 28% at batch size 8. We find that, at this setting, under a jailbreak that tells the model not to refuse, the share of harmful requests that the model answers rises by 18.4 percentage points on Qwen1.5-MoE, 9.5 on OLMoE, and 6.6 on DeepSeek-V2-Lite, the three of nine models where it rises significantly, while MMLU accuracy drops by less than two points. We discover that most of this increase arises while the model processes the prompt and generates its first few tokens. SafeStart therefore runs all experts for the prompt and the first eight generated tokens, and the reduced set of experts afterwards, through a fused kernel in vLLM. With experts removed, SafeStart keeps at least 85% of the offline decode speedup at batch sizes 8 and 32 and brings the change under this jailbreak to between -2.1 and +1.3 points for three expert-reduction methods on these three models. On 889 held-out requests, in an analysis fixed before generation, truncation raises harmful compliance by 5.8 to 21.4 points, and SafeStart leaves a rise of 0.6 to 2.6 points, non-inferior to the original model on two of the three models. Our results show that faster MoE serving need not cost safety: a serving system can keep most of the gain from running fewer experts by running all of them at the start of each response, and it should test refusal, not only accuracy, before it enables such a method.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05591

C-GRPO: Conformal Group Relative Policy Optimization

Arya Fayyazi, Seyedarmin Azizi, Mehdi Kamal, Massoud Pedram

原文摘要

Reasoning-oriented language model training increasingly relies on multiple on-policy rollouts, but standard Group Relative Policy Optimization (GRPO) uses a fixed group size, wasting compute on easy prompts and under-exploring hard ones. Existing adaptive-budget methods alleviate this inefficiency, yet their stopping rules are heuristic and do not provide a finite-sample calibration guarantee. We propose CGRPO, which replaces the fixed rollout budget of standard GPRO with calibrated conformal thresholds over task-specific nonconformity scores, combining Adaptive Prediction Set (APS)-style calibration for closed-form reasoning, a first-success score for execution-based code, automatic miscoverage selection, and periodic re-calibration. We prove finite-sample coverage for the resulting stopping rule and show that, under monotone policy improvement, recalibration induces a non-increasing expected training budget. Across six benchmarks spanning mathematics, graduate-level science, and code generation, CGRPO reduces mean training rollouts by 49-70% relative to fixed-budget GRPO while retaining strong fixed-budget accuracy, achieves the strongest pass@1 among evaluated static and dynamic baselines on different datasets, and transfers across model families with up to 82% rollout savings.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35017

When Pointing Becomes Profiling: Social Bias and Refusal in Text-Steerable Visual Encoders

Seyedarmin Azizi, Parsa Razmara, Sajjad Ghiasvand, Ardalan Aryashad, Tina Khezresmaeilzadeh

原文摘要

Text-steerable visual encoders condition a frozen Vision Transformer on a natural-language prompt and point at the matching image region, producing prompt-conditioned heatmaps and features. We audit the released SteerViT model and find that its steering interface turns language-driven pointing into demographic profiling. On counterfactual face mosaics and real multi-person photographs, "the person" selects a man more often than the base rate, crime words select Black people more often than occupation words do, "the man" among four women selects the Black woman 75.6% of the time on SocialCounterfactuals, and "the monkey" selects Black people. None of them is in the backbone's unsteered saliency, and the crime association is not in the frozen text encoder; the race effects grow with steering strength and enter through the last two cross-attention layers: giving the prompt to those layers alone reproduces them. Four other grounding models, CLIPSeg, Grounding-DINO, SAM 3, and Qwen2.5-VL, show no crime routing and weaker race routing. The model cannot refuse. Its patch softmax must place its mass somewhere, and its heatmap separates a groundable request ("the police officer") from one that is absent ("the pizza") or that would require a stereotyped demographic inference ("the criminal") only at chance (AUROC 0.52). We introduce SafeSteer, which adds a learned abstention output and counterfactual-invariance training on the same 23M steering parameters. SafeSteer separates should-point from should-abstain prompts at AUROC 0.997, generalizes to held-out sensitive and absent words (0.998; at a 0.5 threshold it refuses 99.8% of trained and 62% of held-out sensitive words) with no over-refusal of visible people on the benchmark, and removes most race routing while keeping localization and retrieval within 1 point of the released model. Code, benchmarks, and the curated mosaic sets will be released.

cs.CV

查看论文
arXiv ↗PDF ↗